mirrors
/
mmdeploy
mirror of https://github.com/open-mmlab/mmdeploy.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Update docs (#2114) 

* update docs from 1.x to main

* fix dead links

* fix tag_name

* Revert "fix tag_name"

This reverts commit fcf0c5841bf03a95fc1ddd109547908ef8111008.

* fix readthedocs for zh_cn
pull/2154/head
RunningLeon 2023-05-31 15:18:32 +08:00 committed by GitHub
parent 25cea0ac0f
commit a886f694c8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
32 changed files with 536 additions and 537 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
csrc/mmdeploy/codebase/mmocr/pixel_group.cpp
View File

@ -1,7 +1,7 @@
// Copyright (c) OpenMMLab. All rights reserved.
// Modified from https://github.com/WenmuZhou/PAN.pytorch
// and
// https://github.com/open-mmlab/mmcv/blob/master/mmcv/ops/csrc/pytorch/cpu/pixel_group.cpp
// https://github.com/open-mmlab/mmcv/blob/main/mmcv/ops/csrc/pytorch/cpu/pixel_group.cpp
#include <cmath>
#include <queue>

2
docs/en/02-how-to-run/convert_model.md
View File

@ -11,7 +11,7 @@ Notes:
### Prerequisite
1. Install and build your target backend. You could refer to [ONNXRuntime-install](../05-supported-backends/onnxruntime.md), [TensorRT-install](../05-supported-backends/tensorrt.md), [ncnn-install](../05-supported-backends/ncnn.md), [PPLNN-install](../05-supported-backends/pplnn.md), [OpenVINO-install](../05-supported-backends/openvino.md) for more information.
2. Install and build your target codebase. You could refer to [MMPretrain-install](https://github.com/open-mmlab/mmpretrain/blob/main/docs/en/get_started.md#installation), [MMDetection-install](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/en/get_started.md), [MMSegmentation-install](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/get_started.md#installation), [MMOCR-install](https://github.com/open-mmlab/mmocr/blob/1.x/docs/en/get_started/install.md), [MMagic-install](https://github.com/open-mmlab/mmagic/blob/main/docs/en/get_started/install.md).
2. Install and build your target codebase. You could refer to [MMPretrain-install](https://mmpretrain.readthedocs.io/en/latest/get_started.html#installation), [MMDetection-install](https://mmdetection.readthedocs.io/en/latest/get_started.html#installation), [MMSegmentation-install](https://mmsegmentation.readthedocs.io/en/latest/get_started.html#installation), [MMOCR-install](https://mmocr.readthedocs.io/en/latest/get_started/install.html#installation-steps), [MMagic-install](https://mmagic.readthedocs.io/en/latest/get_started/install.html#installation).
### Usage

2
docs/en/02-how-to-run/write_config.md
View File

@ -177,4 +177,4 @@ detection_tensorrt-int8_dynamic-320x320-1344x1344.py
## 6. How to write model config
According to model's codebase, write the model config file. Model's config file is used to initialize the model, referring to [MMPretrain](https://github.com/open-mmlab/mmpretrain/blob/main/docs/en/user_guides/config.md), [MMDetection](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/en/user_guides/config.md), [MMSegmentation](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/en/user_guides/1_config.md), [MMOCR](https://github.com/open-mmlab/mmocr/blob/1.x/docs/en/user_guides/config.md), [MMagic](https://github.com/open-mmlab/mmagic/blob/main/docs/en/user_guides/config.md).
According to model's codebase, write the model config file. Model's config file is used to initialize the model, referring to [MMPretrain](https://github.com/open-mmlab/mmpretrain/blob/main/docs/en/user_guides/config.md), [MMDetection](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/en/user_guides/config.md), [MMSegmentation](https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/1_config.md), [MMOCR](https://github.com/open-mmlab/mmocr/blob/main/docs/en/user_guides/config.md), [MMagic](https://github.com/open-mmlab/mmagic/blob/main/docs/en/user_guides/config.md).

116
docs/en/03-benchmark/benchmark.md
View File

@ -145,7 +145,7 @@ Users can directly test the speed through [model profiling](../02-how-to-run/pro
<td align="center" colspan="1">fp16</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/yolo/yolov3_d53_320_273e_coco.py">YOLOv3</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/yolo/yolov3_d53_320_273e_coco.py">YOLOv3</a></td>
<td align="center">320x320</td>
<td align="center">14.76</td>
<td align="center">24.92</td>
@ -154,7 +154,7 @@ Users can directly test the speed through [model profiling](../02-how-to-run/pro
<td align="center">18.07</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/ssd/ssdlite_mobilenetv2_scratch_600e_coco.py">SSD-Lite</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/ssd/ssdlite_mobilenetv2_scratch_600e_coco.py">SSD-Lite</a></td>
<td align="center">320x320</td>
<td align="center">8.84</td>
<td align="center">9.21</td>
@ -163,7 +163,7 @@ Users can directly test the speed through [model profiling](../02-how-to-run/pro
<td align="center">19.72</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/retinanet/retinanet_r50_fpn_1x_coco.py">RetinaNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/retinanet/retinanet_r50_fpn_1x_coco.py">RetinaNet</a></td>
<td align="center">800x1344</td>
<td align="center">97.09</td>
<td align="center">25.79</td>
@ -172,7 +172,7 @@ Users can directly test the speed through [model profiling](../02-how-to-run/pro
<td align="center">38.34</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/fcos/fcos_r50_caffe_fpn_gn-head_1x_coco.py">FCOS</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/fcos/fcos_r50_caffe_fpn_gn-head_1x_coco.py">FCOS</a></td>
<td align="center">800x1344</td>
<td align="center">84.06</td>
<td align="center">23.15</td>
@ -181,7 +181,7 @@ Users can directly test the speed through [model profiling](../02-how-to-run/pro
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/fsaf/fsaf_r50_fpn_1x_coco.py">FSAF</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/fsaf/fsaf_r50_fpn_1x_coco.py">FSAF</a></td>
<td align="center">800x1344</td>
<td align="center">82.96</td>
<td align="center">21.02</td>
@ -190,7 +190,7 @@ Users can directly test the speed through [model profiling](../02-how-to-run/pro
<td align="center">30.41</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py">Faster R-CNN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py">Faster R-CNN</a></td>
<td align="center">800x1344</td>
<td align="center">88.08</td>
<td align="center">26.52</td>
@ -326,7 +326,7 @@ Users can directly test the speed through [model profiling](../02-how-to-run/pro
<td align="center" colspan="1">fp32</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/dbnet/dbnet_resnet18_fpnc_1200e_icdar2015.py">DBNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/dbnet/dbnet_resnet18_fpnc_1200e_icdar2015.py">DBNet</a></td>
<td align="center">640x640</td>
<td align="center">10.70</td>
<td align="center">5.62</td>
@ -336,7 +336,7 @@ Users can directly test the speed through [model profiling](../02-how-to-run/pro
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py">CRNN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py">CRNN</a></td>
<td align="center">32x32</td>
<td align="center">1.93 </td>
<td align="center">1.40</td>
@ -373,7 +373,7 @@ Users can directly test the speed through [model profiling](../02-how-to-run/pro
<td align="center" colspan="1">fp16</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py">FCN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py">FCN</a></td>
<td align="center">512x1024</td>
<td align="center">128.42</td>
<td align="center">23.97</td>
@ -382,7 +382,7 @@ Users can directly test the speed through [model profiling](../02-how-to-run/pro
<td align="center">27.00</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py">PSPNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py">PSPNet</a></td>
<td align="center">1x3x512x1024</td>
<td align="center">119.77</td>
<td align="center">24.10</td>
@ -391,7 +391,7 @@ Users can directly test the speed through [model profiling](../02-how-to-run/pro
<td align="center">27.26</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/deeplabv3/deeplabv3/deeplabv3_r50-d8_4xb2-80k_cityscapes-512x1024.py">DeepLabV3</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3/deeplabv3/deeplabv3_r50-d8_4xb2-80k_cityscapes-512x1024.py">DeepLabV3</a></td>
<td align="center">512x1024</td>
<td align="center">226.75</td>
<td align="center">31.80</td>
@ -400,7 +400,7 @@ Users can directly test the speed through [model profiling](../02-how-to-run/pro
<td align="center">36.01</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-512x1024.py">DeepLabV3+</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-512x1024.py">DeepLabV3+</a></td>
<td align="center">512x1024</td>
<td align="center">151.25</td>
<td align="center">47.03</td>
@ -1160,7 +1160,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">fp32</td>
</tr>
<tr>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/dbnet/dbnet_resnet18_fpnc_1200e_icdar2015.py">DBNet*</a></td>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/dbnet/dbnet_resnet18_fpnc_1200e_icdar2015.py">DBNet*</a></td>
<td align="center" rowspan="3">TextDetection</td>
<td align="center" rowspan="3">ICDAR2015</td>
<td align="center">recall</td>
@ -1196,7 +1196,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">0.7950</td>
</tr>
<tr>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/dbnetpp/dbnetpp_resnet50_fpnc_1200e_icdar2015.py">DBNetpp</a></td>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/dbnetpp/dbnetpp_resnet50_fpnc_1200e_icdar2015.py">DBNetpp</a></td>
<td align="center" rowspan="3">TextDetection</td>
<td align="center" rowspan="3">ICDAR2015</td>
<td align="center">recall</td>
@ -1232,7 +1232,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">0.8622</td>
</tr>
<tr>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/psenet/psenet_resnet50_fpnf_600e_icdar2015.py">PSENet</a></td>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/psenet/psenet_resnet50_fpnf_600e_icdar2015.py">PSENet</a></td>
<td align="center" rowspan="3">TextDetection</td>
<td align="center" rowspan="3">ICDAR2015</td>
<td align="center">recall</td>
@ -1268,7 +1268,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">0.8057</td>
</tr>
<tr>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/panet/panet_resnet18_fpem-ffm_600e_icdar2015.py">PANet</a></td>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/panet/panet_resnet18_fpem-ffm_600e_icdar2015.py">PANet</a></td>
<td align="center" rowspan="3">TextDetection</td>
<td align="center" rowspan="3">ICDAR2015</td>
<td align="center">recall</td>
@ -1304,7 +1304,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">0.7955</td>
</tr>
<tr>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/textsnake/textsnake_resnet50_fpn-unet_1200e_ctw1500.py">TextSnake</a></td>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/textsnake/textsnake_resnet50_fpn-unet_1200e_ctw1500.py">TextSnake</a></td>
<td align="center" rowspan="3">TextDetection</td>
<td align="center" rowspan="3">CTW1500</td>
<td align="center">recall</td>
@ -1340,7 +1340,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/maskrcnn/mask-rcnn_resnet50_fpn_160e_icdar2015.py">MaskRCNN</a></td>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/maskrcnn/mask-rcnn_resnet50_fpn_160e_icdar2015.py">MaskRCNN</a></td>
<td align="center" rowspan="3">TextDetection</td>
<td align="center" rowspan="3">ICDAR2015</td>
<td align="center">recall</td>
@ -1376,7 +1376,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py">CRNN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py">CRNN</a></td>
<td align="center">TextRecognition</td>
<td align="center">IIIT5K</td>
<td align="center">acc</td>
@ -1390,7 +1390,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/sar/sar_resnet31_parallel-decoder_5e_st-sub_mj-sub_sa_real.py">SAR</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/sar/sar_resnet31_parallel-decoder_5e_st-sub_mj-sub_sa_real.py">SAR</a></td>
<td align="center">TextRecognition</td>
<td align="center">IIIT5K</td>
<td align="center">acc</td>
@ -1404,7 +1404,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/satrn/satrn_shallow-small_5e_st_mj.py">SATRN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/satrn/satrn_shallow-small_5e_st_mj.py">SATRN</a></td>
<td align="center">TextRecognition</td>
<td align="center">IIIT5K</td>
<td align="center">acc</td>
@ -1418,7 +1418,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/abinet/abinet_20e_st-an_mj.py">ABINet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/abinet/abinet_20e_st-an_mj.py">ABINet</a></td>
<td align="center">TextRecognition</td>
<td align="center">IIIT5K</td>
<td align="center">acc</td>
@ -1462,7 +1462,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">fp32</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py">FCN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py">FCN</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">72.25</td>
@ -1475,7 +1475,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">72.35</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py">PSPNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py">PSPNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">78.55</td>
@ -1488,7 +1488,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">78.67</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-512x1024.py">deeplabv3</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-512x1024.py">deeplabv3</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">79.09</td>
@ -1501,7 +1501,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">79.06</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_cityscapes-512x1024.py">deeplabv3+</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_cityscapes-512x1024.py">deeplabv3+</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">79.61</td>
@ -1514,7 +1514,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">79.51</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fastscnn/fast_scnn_8xb4-160k_cityscapes-512x1024.py">Fast-SCNN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fastscnn/fast_scnn_8xb4-160k_cityscapes-512x1024.py">Fast-SCNN</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">70.96</td>
@ -1527,7 +1527,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/unet/unet-s5-d16_fcn_4xb4-160k_cityscapes-512x1024.py">UNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/unet/unet-s5-d16_fcn_4xb4-160k_cityscapes-512x1024.py">UNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">69.10</td>
@ -1540,7 +1540,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/ann/ann_r50-d8_4xb2-40k_cityscapes-512x1024.py">ANN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/ann/ann_r50-d8_4xb2-40k_cityscapes-512x1024.py">ANN</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">77.40</td>
@ -1553,7 +1553,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/apcnet/apcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py">APCNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/apcnet/apcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py">APCNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">77.40</td>
@ -1566,7 +1566,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_cityscapes-1024x1024.py">BiSeNetV1</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_cityscapes-1024x1024.py">BiSeNetV1</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">74.44</td>
@ -1579,7 +1579,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/bisenetv2/bisenetv2_fcn_4xb4-160k_cityscapes-1024x1024.py">BiSeNetV2</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/bisenetv2/bisenetv2_fcn_4xb4-160k_cityscapes-1024x1024.py">BiSeNetV2</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">73.21</td>
@ -1592,7 +1592,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/cgnet/cgnet_fcn_4xb8-60k_cityscapes-512x1024.py">CGNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/cgnet/cgnet_fcn_4xb8-60k_cityscapes-512x1024.py">CGNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">68.25</td>
@ -1605,7 +1605,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/emanet/emanet_r50-d8_4xb2-80k_cityscapes-512x1024.py">EMANet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/emanet/emanet_r50-d8_4xb2-80k_cityscapes-512x1024.py">EMANet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">77.59</td>
@ -1618,7 +1618,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/encnet/encnet_r50-d8_4xb2-40k_cityscapes-512x1024.py">EncNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/encnet/encnet_r50-d8_4xb2-40k_cityscapes-512x1024.py">EncNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">75.67</td>
@ -1631,7 +1631,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/erfnet/erfnet_fcn_4xb4-160k_cityscapes-512x1024.py">ERFNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/erfnet/erfnet_fcn_4xb4-160k_cityscapes-512x1024.py">ERFNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">71.08</td>
@ -1644,7 +1644,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py">FastFCN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py">FastFCN</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">79.12</td>
@ -1657,7 +1657,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py">GCNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py">GCNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">77.69</td>
@ -1670,7 +1670,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/icnet/icnet_r18-d8_4xb2-80k_cityscapes-832x832.py">ICNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/icnet/icnet_r18-d8_4xb2-80k_cityscapes-832x832.py">ICNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">76.29</td>
@ -1683,7 +1683,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/isanet/isanet_r50-d8_4xb2-40k_cityscapes-512x1024.py">ISANet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/isanet/isanet_r50-d8_4xb2-40k_cityscapes-512x1024.py">ISANet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">78.49</td>
@ -1696,7 +1696,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024.py">OCRNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024.py">OCRNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">74.30</td>
@ -1709,7 +1709,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/point_rend/pointrend_r50_4xb2-80k_cityscapes-512x1024.py">PointRend</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/point_rend/pointrend_r50_4xb2-80k_cityscapes-512x1024.py">PointRend</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">76.47</td>
@ -1722,7 +1722,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/sem_fpn/fpn_r50_4xb2-80k_cityscapes-512x1024.py">Semantic FPN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/sem_fpn/fpn_r50_4xb2-80k_cityscapes-512x1024.py">Semantic FPN</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">74.52</td>
@ -1735,7 +1735,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/stdc/stdc1_in1k-pre_4xb12-80k_cityscapes-512x1024.py">STDC</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/stdc/stdc1_in1k-pre_4xb12-80k_cityscapes-512x1024.py">STDC</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">75.10</td>
@ -1748,7 +1748,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/stdc/stdc2_in1k-pre_4xb12-80k_cityscapes-512x1024.py">STDC</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/stdc/stdc2_in1k-pre_4xb12-80k_cityscapes-512x1024.py">STDC</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">77.17</td>
@ -1761,7 +1761,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/upernet/upernet_r50_4xb2-40k_cityscapes-512x1024.py">UPerNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/upernet/upernet_r50_4xb2-40k_cityscapes-512x1024.py">UPerNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">77.10</td>
@ -1774,7 +1774,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/blob/1.x/configs/segmenter/segmenter_vit-s_fcn_8xb1-160k_ade20k-512x512.py">Segmenter</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segmenter/segmenter_vit-s_fcn_8xb1-160k_ade20k-512x512.py">Segmenter</a></td>
<td align="center">ADE20K</td>
<td align="center">mIoU</td>
<td align="center">44.32</td>
@ -1815,7 +1815,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">fp32</td>
</tr>
<tr>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/1.x/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_hrnet-w48_8xb32-210e_coco-256x192.py">HRNet</a></td>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/main/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_hrnet-w48_8xb32-210e_coco-256x192.py">HRNet</a></td>
<td align="center" rowspan="2">Pose Detection</td>
<td align="center" rowspan="2">COCO</td>
<td align="center">AP</td>
@ -1836,7 +1836,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">0.802</td>
</tr>
<tr>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/1.x/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_litehrnet-30_8xb64-210e_coco-256x192.py">LiteHRNet</a></td>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/main/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_litehrnet-30_8xb64-210e_coco-256x192.py">LiteHRNet</a></td>
<td align="center" rowspan="2">Pose Detection</td>
<td align="center" rowspan="2">COCO</td>
<td align="center">AP</td>
@ -1857,7 +1857,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">0.728</td>
</tr>
<tr>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/1.x/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_4xmspn50_8xb32-210e_coco-256x192.py">MSPN</a></td>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/main/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_4xmspn50_8xb32-210e_coco-256x192.py">MSPN</a></td>
<td align="center" rowspan="2">Pose Detection</td>
<td align="center" rowspan="2">COCO</td>
<td align="center">AP</td>
@ -1878,7 +1878,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">0.825</td>
</tr>
<tr>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/1.x/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_hourglass52_8xb32-210e_coco-256x256.py">Hourglass</a></td>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/main/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_hourglass52_8xb32-210e_coco-256x256.py">Hourglass</a></td>
<td align="center" rowspan="2">Pose Detection</td>
<td align="center" rowspan="2">COCO</td>
<td align="center">AP</td>
@ -1899,7 +1899,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">0.774</td>
</tr>
<tr>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/1.x/configs/body_2d_keypoint/simcc/coco/simcc_mobilenetv2_wo-deconv-8xb64-210e_coco-256x192.py">SimCC</a></td>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/main/configs/body_2d_keypoint/simcc/coco/simcc_mobilenetv2_wo-deconv-8xb64-210e_coco-256x192.py">SimCC</a></td>
<td align="center" rowspan="2">Pose Detection</td>
<td align="center" rowspan="2">COCO</td>
<td align="center">AP</td>
@ -1949,7 +1949,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">fp32</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmrotate/tree/1.x/configs/rotated_retinanet/rotated-retinanet-hbox-oc_r50_fpn_1x_dota.py">RotatedRetinaNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmrotate/tree/main/configs/rotated_retinanet/rotated-retinanet-hbox-oc_r50_fpn_1x_dota.py">RotatedRetinaNet</a></td>
<td align="center">Rotated Detection</td>
<td align="center">DOTA-v1.0</td>
<td align="center">mAP</td>
@ -1961,7 +1961,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmrotate/tree/1.x/configs/oriented_rcnn/oriented-rcnn-le90_r50_fpn_1x_dota.py">Oriented RCNN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmrotate/tree/main/configs/oriented_rcnn/oriented-rcnn-le90_r50_fpn_1x_dota.py">Oriented RCNN</a></td>
<td align="center">Rotated Detection</td>
<td align="center">DOTA-v1.0</td>
<td align="center">mAP</td>
@ -1973,7 +1973,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmrotate/blob/1.x/configs/gliding_vertex/gliding-vertex-rbox_r50_fpn_1x_dota.py">GlidingVertex</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmrotate/blob/main/configs/gliding_vertex/gliding-vertex-rbox_r50_fpn_1x_dota.py">GlidingVertex</a></td>
<td align="center">Rotated Detection</td>
<td align="center">DOTA-v1.0</td>
<td align="center">mAP</td>
@ -1985,7 +1985,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmrotate/blob/1.x/configs/roi_trans/roi-trans-le90_r50_fpn_1x_dota.py">RoI Transformer</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmrotate/blob/main/configs/roi_trans/roi-trans-le90_r50_fpn_1x_dota.py">RoI Transformer</a></td>
<td align="center">Rotated Detection</td>
<td align="center">DOTA-v1.0</td>
<td align="center">mAP</td>
@ -2026,7 +2026,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">fp32</td>
</tr>
<tr>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmaction2/blob/1.x/configs/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x3-100e_kinetics400-rgb.py">TSN</a></td>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x3-100e_kinetics400-rgb.py">TSN</a></td>
<td align="center" rowspan="2">Recognition</td>
<td align="center" rowspan="2">Kinetics-400</td>
<td align="center">top-1</td>
@ -2047,7 +2047,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../
<td align="center">-</td>
</tr>
<tr>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmaction2/blob/1.x/configs/recognition/slowfast/slowfast_r50_8xb8-4x16x1-256e_kinetics400-rgb.py">SlowFast</a></td>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/slowfast/slowfast_r50_8xb8-4x16x1-256e_kinetics400-rgb.py">SlowFast</a></td>
<td align="center" rowspan="2">Recognition</td>
<td align="center" rowspan="2">Kinetics-400</td>
<td align="center">top-1</td>

18
docs/en/03-benchmark/benchmark_edge.md
View File

@ -22,15 +22,15 @@ tips:
## mmocr detection
| model | dataset | spatial | fp32 hmean | snpe gpu hybrid hmean | latency(ms) |
| :-------------------------------------------------------------------------------------------------------------------: | :-------: | :------: | :--------: | :-------------------: | :---------: |
| [PANet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/panet/panet_resnet18_fpem-ffm_600e_icdar2015.py) | ICDAR2015 | 1312x736 | 0.795 | 0.785 @thr=0.9 | 3100±100 |
| model | dataset | spatial | fp32 hmean | snpe gpu hybrid hmean | latency(ms) |
| :--------------------------------------------------------------------------------------------------------------------: | :-------: | :------: | :--------: | :-------------------: | :---------: |
| [PANet](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/panet/panet_resnet18_fpem-ffm_600e_icdar2015.py) | ICDAR2015 | 1312x736 | 0.795 | 0.785 @thr=0.9 | 3100±100 |
## mmpose
| model | dataset | spatial | snpe hybrid AR@IoU=0.50 | snpe hybrid AP@IoU=0.50 | latency(ms) |
| :--------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :--------: | :-----: | :---------------------: | :---------------------: | :---------: |
| [pose_hrnet_w32](https://github.com/open-mmlab/mmpose/blob/1.x/configs/animal_2d_keypoint/topdown_heatmap/animalpose/td-hm_hrnet-w32_8xb64-210e_animalpose-256x256.py) | Animalpose | 256x256 | 0.997 | 0.989 | 630±50 |
| model | dataset | spatial | snpe hybrid AR@IoU=0.50 | snpe hybrid AP@IoU=0.50 | latency(ms) |
| :---------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :--------: | :-----: | :---------------------: | :---------------------: | :---------: |
| [pose_hrnet_w32](https://github.com/open-mmlab/mmpose/blob/main/configs/animal_2d_keypoint/topdown_heatmap/animalpose/td-hm_hrnet-w32_8xb64-210e_animalpose-256x256.py) | Animalpose | 256x256 | 0.997 | 0.989 | 630±50 |
tips:
@ -38,9 +38,9 @@ tips:
## mmseg
| model | dataset | spatial | mIoU | latency(ms) |
| :-----------------------------------------------------------------------------------------------------------------: | :--------: | :------: | :---: | :---------: |
| [fcn](https://github.com/open-mmlab/mmsegmentation/blob/1.x/configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-512x1024.py) | Cityscapes | 512x1024 | 71.11 | 4915±500 |
| model | dataset | spatial | mIoU | latency(ms) |
| :------------------------------------------------------------------------------------------------------------------: | :--------: | :------: | :---: | :---------: |
| [fcn](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-512x1024.py) | Cityscapes | 512x1024 | 71.11 | 4915±500 |
tips:

54
docs/en/03-benchmark/benchmark_tvm.md
View File

@ -2,26 +2,26 @@
## Supported Models
| Model | Codebase | Model config |
| :---------------- | :------------- | :--------------------------------------------------------------------------------------: |
| RetinaNet | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/retinanet) |
| Faster R-CNN | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn) |
| YOLOv3 | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/yolo) |
| YOLOX | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/yolox) |
| Mask R-CNN | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn) |
| SSD | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/main/configs/ssd) |
| ResNet | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnet) |
| ResNeXt | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnext) |
| SE-ResNet | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/seresnet) |
| MobileNetV2 | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/mobilenet_v2) |
| ShuffleNetV1 | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v1) |
| ShuffleNetV2 | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v2) |
| VisionTransformer | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/vision_transformer) |
| FCN | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/fcn) |
| PSPNet | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/pspnet) |
| DeepLabV3 | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/deeplabv3) |
| DeepLabV3+ | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/deeplabv3plus) |
| UNet | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/unet) |
| Model | Codebase | Model config |
| :---------------- | :------------- | :-------------------------------------------------------------------------------------: |
| RetinaNet | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/main/configs/retinanet) |
| Faster R-CNN | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/main/configs/faster_rcnn) |
| YOLOv3 | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/main/configs/yolo) |
| YOLOX | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/main/configs/yolox) |
| Mask R-CNN | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/main/configs/mask_rcnn) |
| SSD | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/main/configs/ssd) |
| ResNet | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnet) |
| ResNeXt | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnext) |
| SE-ResNet | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/seresnet) |
| MobileNetV2 | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/mobilenet_v2) |
| ShuffleNetV1 | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v1) |
| ShuffleNetV2 | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v2) |
| VisionTransformer | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/vision_transformer) |
| FCN | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fcn) |
| PSPNet | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/pspnet) |
| DeepLabV3 | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3) |
| DeepLabV3+ | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3plus) |
| UNet | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/unet) |
The table above list the models that we have tested. Models not listed on the table might still be able to converted. Please have a try.
@ -39,13 +39,13 @@ The table above list the models that we have tested. Models not listed on the ta
<!-- | [Vision Transformer](https://github.com/open-mmlab/mmpretrain/blob/main/configs/vision_transformer/vit-base-p16_ft-64xb64_in1k-384.py) | top-1 | 85.43 | 84.01 | -->
| mmdet(\*) | metric | PyTorch | TVM |
| :-------------------------------------------------------------------------------------: | :----: | :-----: | :--: |
| [SSD](https://github.com/open-mmlab/mmdetection/tree/master/configs/ssd/ssd300_coco.py) | box AP | 25.5 | 25.5 |
| mmdet(\*) | metric | PyTorch | TVM |
| :-----------------------------------------------------------------------------------: | :----: | :-----: | :--: |
| [SSD](https://github.com/open-mmlab/mmdetection/tree/main/configs/ssd/ssd300_coco.py) | box AP | 25.5 | 25.5 |
\*: We only test model on ssd since dynamic shape is not supported for now.
| mmseg | metric | PyTorch | TVM |
| :------------------------------------------------------------------------------------------------------------------------: | :----: | :-----: | :---: |
| [FCN](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/fcn/fcn_r50-d8_512x1024_40k_cityscapes.py) | mIoU | 72.25 | 72.36 |
| [PSPNet](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes.py) | mIoU | 78.55 | 77.90 |
| mmseg | metric | PyTorch | TVM |
| :---------------------------------------------------------------------------------------------------------------------------: | :----: | :-----: | :---: |
| [FCN](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py) | mIoU | 72.25 | 72.36 |
| [PSPNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py) | mIoU | 78.55 | 77.90 |

14
docs/en/03-benchmark/quantization.md
View File

@ -20,17 +20,17 @@ Note:
### OCR detection
| model | dataset | fp32 hmean | int8 hmean |
| :------------------------------------------------------------------------------------------------------------------------------: | :-------: | :--------: | :------------: |
| [PANet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/panet/panet_resnet18_fpem-ffm_600e_icdar2015.py) | ICDAR2015 | 0.795 | 0.792 @thr=0.9 |
| [TextSnake](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/textsnake/textsnake_resnet50_fpn-unet_1200e_ctw1500.py) | CTW1500 | 0.817 | 0.818 |
| model | dataset | fp32 hmean | int8 hmean |
| :-------------------------------------------------------------------------------------------------------------------------------: | :-------: | :--------: | :------------: |
| [PANet](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/panet/panet_resnet18_fpem-ffm_600e_icdar2015.py) | ICDAR2015 | 0.795 | 0.792 @thr=0.9 |
| [TextSnake](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/textsnake/textsnake_resnet50_fpn-unet_1200e_ctw1500.py) | CTW1500 | 0.817 | 0.818 |
Note: [mmocr](https://github.com/open-mmlab/mmocr) Uses 'shapely' to compute IoU, which results in a slight difference in accuracy
### Pose detection
| model | dataset | fp32 AP | int8 AP |
| :---------------------------------------------------------------------------------------------------------------------------------------------------: | :------: | :-----: | :-----: |
| [Hourglass](https://github.com/open-mmlab/mmpose/blob/1.x/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_hourglass52_8xb32-210e_coco-256x256.py) | COCO2017 | 0.717 | 0.713 |
| model | dataset | fp32 AP | int8 AP |
| :----------------------------------------------------------------------------------------------------------------------------------------------------: | :------: | :-----: | :-----: |
| [Hourglass](https://github.com/open-mmlab/mmpose/blob/main/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_hourglass52_8xb32-210e_coco-256x256.py) | COCO2017 | 0.717 | 0.713 |
Note: MMPose models are tested with `flip_test` explicitly set to `False` in model configs.

172
docs/en/03-benchmark/supported_models.md
View File

@ -2,92 +2,92 @@
The table below lists the models that are guaranteed to be exportable to other backends.
| Model config | Codebase | TorchScript | OnnxRuntime | TensorRT | ncnn | PPLNN | OpenVINO | Ascend | RKNN |
| :------------------------------------------------------------------------------------------------------ | :--------------- | :---------: | :---------: | :------: | :--: | :---: | :------: | :----: | :--: |
| [RetinaNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/retinanet) | MMDetection | Y | Y | Y | Y | Y | Y | Y | Y |
| [Faster R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/faster_rcnn) | MMDetection | Y | Y | Y | Y | Y | Y | Y | N |
| [YOLOv3](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/yolo) | MMDetection | Y | Y | Y | Y | N | Y | Y | Y |
| [YOLOX](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/yolox) | MMDetection | Y | Y | Y | Y | N | Y | N | Y |
| [FCOS](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/fcos) | MMDetection | Y | Y | Y | Y | N | Y | N | N |
| [FSAF](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/fsaf) | MMDetection | Y | Y | Y | Y | Y | Y | N | Y |
| [Mask R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/mask_rcnn) | MMDetection | Y | Y | Y | N | N | Y | N | N |
| [SSD](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/ssd)[\*](#note) | MMDetection | Y | Y | Y | Y | N | Y | N | Y |
| [FoveaBox](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/foveabox) | MMDetection | Y | Y | N | N | N | Y | N | N |
| [ATSS](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/atss) | MMDetection | N | Y | Y | N | N | Y | N | N |
| [GFL](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/gfl) | MMDetection | N | Y | Y | N | ? | Y | N | N |
| [Cascade R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | MMDetection | N | Y | Y | N | Y | Y | N | N |
| [Cascade Mask R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | MMDetection | N | Y | Y | N | N | Y | N | N |
| [Swin Transformer](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/swin)[\*](#note) | MMDetection | N | Y | Y | N | N | N | N | N |
| [VFNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/vfnet) | MMDetection | N | N | N | N | N | Y | N | N |
| [RepPoints](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/reppoints) | MMDetection | N | N | Y | N | ? | Y | N | N |
| [DETR](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/detr) | MMDetection | N | Y | Y | N | ? | N | N | N |
| [CenterNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/centernet) | MMDetection | N | Y | Y | N | ? | N | N | N |
| [SOLO](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solo) | MMDetection | N | Y | N | N | N | Y | N | N |
| [SOLOv2](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solov2) | MMDetection | N | Y | N | N | N | Y | N | N |
| [ResNet](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnet) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [ResNeXt](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnext) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [SE-ResNet](https://github.com/open-mmlab/mmpretrain/tree/main/configs/seresnet) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [MobileNetV2](https://github.com/open-mmlab/mmpretrain/tree/main/configs/mobilenet_v2) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [ShuffleNetV1](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v1) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [ShuffleNetV2](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v2) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [VisionTransformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/vision_transformer) | MMPretrain | Y | Y | Y | Y | ? | Y | Y | N |
| [SwinTransformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/swin_transformer) | MMPretrain | Y | Y | Y | N | ? | N | ? | N |
| [MobileOne](https://github.com/open-mmlab/mmpretrain/tree/main/configs/mobileone) | MMPretrain | N | Y | Y | N | N | N | N | N |
| [FCN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fcn) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | Y |
| [PSPNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/pspnet)[\*static](#note) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | Y |
| [DeepLabV3](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/deeplabv3) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | N |
| [DeepLabV3+](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/deeplabv3plus) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | N |
| [Fast-SCNN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fastscnn)[\*static](#note) | MMSegmentation | Y | Y | Y | N | Y | Y | N | Y |
| [UNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/unet) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | Y |
| [ANN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/ann)[\*](#note) | MMSegmentation | Y | Y | Y | N | N | N | N | N |
| [APCNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/apcnet) | MMSegmentation | Y | Y | Y | Y | N | N | N | Y |
| [BiSeNetV1](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/bisenetv1) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [BiSeNetV2](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/bisenetv2) | MMSegmentation | Y | Y | Y | Y | N | Y | N | N |
| [CGNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/cgnet) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [DMNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/dmnet) | MMSegmentation | ? | Y | N | N | N | N | N | N |
| [DNLNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/dnlnet) | MMSegmentation | ? | Y | Y | Y | N | Y | N | N |
| [EMANet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/emanet) | MMSegmentation | Y | Y | Y | N | N | Y | N | N |
| [EncNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/encnet) | MMSegmentation | Y | Y | Y | N | N | Y | N | N |
| [ERFNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/erfnet) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [FastFCN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fastfcn) | MMSegmentation | Y | Y | Y | Y | N | Y | N | N |
| [GCNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/gcnet) | MMSegmentation | Y | Y | Y | N | N | N | N | N |
| [ICNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/icnet)[\*](#note) | MMSegmentation | Y | Y | Y | N | N | Y | N | N |
| [ISANet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/isanet)[\*static](#note) | MMSegmentation | N | Y | Y | N | N | Y | N | Y |
| [NonLocal Net](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/nonlocal_net) | MMSegmentation | ? | Y | Y | Y | N | Y | N | N |
| [OCRNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/ocrnet) | MMSegmentation | ? | Y | Y | Y | N | Y | N | Y |
| [PointRend](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/point_rend) | MMSegmentation | Y | Y | Y | N | N | Y | N | N |
| [Semantic FPN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/sem_fpn) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [STDC](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/stdc) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [UPerNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/upernet)[\*](#note) | MMSegmentation | ? | Y | Y | N | N | N | N | Y |
| [DANet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/danet) | MMSegmentation | ? | Y | Y | N | N | N | N | N |
| [Segmenter](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/segmenter) [\*static](#note) | MMSegmentation | Y | Y | Y | Y | N | Y | N | N |
| [SRCNN](https://github.com/open-mmlab/mmagic/tree/main/configs/srcnn) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [ESRGAN](https://github.com/open-mmlab/mmagic/tree/main/configs/esrgan) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [SRGAN](https://github.com/open-mmlab/mmagic/tree/main/configs/srgan_resnet) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [SRResNet](https://github.com/open-mmlab/mmagic/tree/main/configs/srgan_resnet) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [Real-ESRGAN](https://github.com/open-mmlab/mmagic/tree/main/configs/real_esrgan) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [EDSR](https://github.com/open-mmlab/mmagic/tree/main/configs/edsr) | MMagic | Y | Y | Y | Y | N | Y | N | N |
| [RDN](https://github.com/open-mmlab/mmagic/tree/main/configs/rdn) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [DBNet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/dbnet) | MMOCR | Y | Y | Y | Y | Y | Y | Y | N |
| [DBNetpp](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/dbnetpp) | MMOCR | Y | Y | Y | ? | ? | Y | ? | N |
| [PANet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/panet) | MMOCR | Y | Y | Y | Y | ? | Y | Y | N |
| [PSENet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/psenet) | MMOCR | Y | Y | Y | Y | ? | Y | Y | N |
| [TextSnake](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/textsnake) | MMOCR | Y | Y | Y | Y | ? | ? | ? | N |
| [MaskRCNN](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/maskrcnn) | MMOCR | Y | Y | Y | ? | ? | ? | ? | N |
| [CRNN](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/crnn) | MMOCR | Y | Y | Y | Y | Y | N | N | N |
| [SAR](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/sar) | MMOCR | N | Y | N | N | N | N | N | N |
| [SATRN](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/satrn) | MMOCR | Y | Y | Y | N | N | N | N | N |
| [ABINet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/abinet) | MMOCR | Y | Y | Y | N | N | N | N | N |
| [HRNet](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/backbones.html#hrnet-cvpr-2019) | MMPose | N | Y | Y | Y | N | Y | N | N |
| [MSPN](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/backbones.html#mspn-arxiv-2019) | MMPose | N | Y | Y | Y | N | Y | N | N |
| [LiteHRNet](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/backbones.html#litehrnet-cvpr-2021) | MMPose | N | Y | Y | N | N | Y | N | N |
| [Hourglass](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/backbones.html#hourglass-eccv-2016) | MMPose | N | Y | Y | Y | N | Y | N | N |
| [SimCC](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/algorithms.html#simcc-eccv-2022) | MMPose | N | Y | Y | Y | N | N | N | N |
| [PointPillars](https://github.com/open-mmlab/mmdetection3d/tree/dev-1.x/configs/pointpillars) | MMDetection3d | ? | Y | Y | N | N | Y | N | N |
| [CenterPoint (pillar)](https://github.com/open-mmlab/mmdetection3d/tree/dev-1.x/configs/centerpoint) | MMDetection3d | ? | Y | Y | N | N | Y | N | N |
| [RotatedRetinaNet](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/rotated_retinanet/README.md) | RotatedDetection | N | Y | Y | N | N | N | N | N |
| [Oriented RCNN](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/oriented_rcnn/README.md) | RotatedDetection | N | Y | Y | N | N | N | N | N |
| [Gliding Vertex](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/gliding_vertex/README.md) | RotatedDetection | N | N | Y | N | N | N | N | N |
| Model config | Codebase | TorchScript | OnnxRuntime | TensorRT | ncnn | PPLNN | OpenVINO | Ascend | RKNN |
| :------------------------------------------------------------------------------------------------------- | :--------------- | :---------: | :---------: | :------: | :--: | :---: | :------: | :----: | :--: |
| [RetinaNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/retinanet) | MMDetection | Y | Y | Y | Y | Y | Y | Y | Y |
| [Faster R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/faster_rcnn) | MMDetection | Y | Y | Y | Y | Y | Y | Y | N |
| [YOLOv3](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/yolo) | MMDetection | Y | Y | Y | Y | N | Y | Y | Y |
| [YOLOX](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/yolox) | MMDetection | Y | Y | Y | Y | N | Y | N | Y |
| [FCOS](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/fcos) | MMDetection | Y | Y | Y | Y | N | Y | N | N |
| [FSAF](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/fsaf) | MMDetection | Y | Y | Y | Y | Y | Y | N | Y |
| [Mask R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/mask_rcnn) | MMDetection | Y | Y | Y | N | N | Y | N | N |
| [SSD](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/ssd)[\*](#note) | MMDetection | Y | Y | Y | Y | N | Y | N | Y |
| [FoveaBox](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/foveabox) | MMDetection | Y | Y | N | N | N | Y | N | N |
| [ATSS](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/atss) | MMDetection | N | Y | Y | N | N | Y | N | N |
| [GFL](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/gfl) | MMDetection | N | Y | Y | N | ? | Y | N | N |
| [Cascade R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | MMDetection | N | Y | Y | N | Y | Y | N | N |
| [Cascade Mask R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | MMDetection | N | Y | Y | N | N | Y | N | N |
| [Swin Transformer](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/swin)[\*](#note) | MMDetection | N | Y | Y | N | N | N | N | N |
| [VFNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/vfnet) | MMDetection | N | N | N | N | N | Y | N | N |
| [RepPoints](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/reppoints) | MMDetection | N | N | Y | N | ? | Y | N | N |
| [DETR](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/detr) | MMDetection | N | Y | Y | N | ? | N | N | N |
| [CenterNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/centernet) | MMDetection | N | Y | Y | N | ? | N | N | N |
| [SOLO](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solo) | MMDetection | N | Y | N | N | N | Y | N | N |
| [SOLOv2](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solov2) | MMDetection | N | Y | N | N | N | Y | N | N |
| [ResNet](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnet) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [ResNeXt](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnext) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [SE-ResNet](https://github.com/open-mmlab/mmpretrain/tree/main/configs/seresnet) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [MobileNetV2](https://github.com/open-mmlab/mmpretrain/tree/main/configs/mobilenet_v2) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [ShuffleNetV1](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v1) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [ShuffleNetV2](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v2) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [VisionTransformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/vision_transformer) | MMPretrain | Y | Y | Y | Y | ? | Y | Y | N |
| [SwinTransformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/swin_transformer) | MMPretrain | Y | Y | Y | N | ? | N | ? | N |
| [MobileOne](https://github.com/open-mmlab/mmpretrain/tree/main/configs/mobileone) | MMPretrain | N | Y | Y | N | N | N | N | N |
| [FCN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fcn) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | Y |
| [PSPNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/pspnet)[\*static](#note) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | Y |
| [DeepLabV3](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | N |
| [DeepLabV3+](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3plus) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | N |
| [Fast-SCNN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fastscnn)[\*static](#note) | MMSegmentation | Y | Y | Y | N | Y | Y | N | Y |
| [UNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/unet) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | Y |
| [ANN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/ann)[\*](#note) | MMSegmentation | Y | Y | Y | N | N | N | N | N |
| [APCNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/apcnet) | MMSegmentation | Y | Y | Y | Y | N | N | N | Y |
| [BiSeNetV1](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/bisenetv1) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [BiSeNetV2](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/bisenetv2) | MMSegmentation | Y | Y | Y | Y | N | Y | N | N |
| [CGNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/cgnet) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [DMNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/dmnet) | MMSegmentation | ? | Y | N | N | N | N | N | N |
| [DNLNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/dnlnet) | MMSegmentation | ? | Y | Y | Y | N | Y | N | N |
| [EMANet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/emanet) | MMSegmentation | Y | Y | Y | N | N | Y | N | N |
| [EncNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/encnet) | MMSegmentation | Y | Y | Y | N | N | Y | N | N |
| [ERFNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/erfnet) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [FastFCN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fastfcn) | MMSegmentation | Y | Y | Y | Y | N | Y | N | N |
| [GCNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/gcnet) | MMSegmentation | Y | Y | Y | N | N | N | N | N |
| [ICNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/icnet)[\*](#note) | MMSegmentation | Y | Y | Y | N | N | Y | N | N |
| [ISANet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/isanet)[\*static](#note) | MMSegmentation | N | Y | Y | N | N | Y | N | Y |
| [NonLocal Net](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/nonlocal_net) | MMSegmentation | ? | Y | Y | Y | N | Y | N | N |
| [OCRNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/ocrnet) | MMSegmentation | ? | Y | Y | Y | N | Y | N | Y |
| [PointRend](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/point_rend) | MMSegmentation | Y | Y | Y | N | N | Y | N | N |
| [Semantic FPN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/sem_fpn) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [STDC](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/stdc) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [UPerNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/upernet)[\*](#note) | MMSegmentation | ? | Y | Y | N | N | N | N | Y |
| [DANet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/danet) | MMSegmentation | ? | Y | Y | N | N | N | N | N |
| [Segmenter](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/segmenter) [\*static](#note) | MMSegmentation | Y | Y | Y | Y | N | Y | N | N |
| [SRCNN](https://github.com/open-mmlab/mmagic/tree/main/configs/srcnn) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [ESRGAN](https://github.com/open-mmlab/mmagic/tree/main/configs/esrgan) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [SRGAN](https://github.com/open-mmlab/mmagic/tree/main/configs/srgan_resnet) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [SRResNet](https://github.com/open-mmlab/mmagic/tree/main/configs/srgan_resnet) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [Real-ESRGAN](https://github.com/open-mmlab/mmagic/tree/main/configs/real_esrgan) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [EDSR](https://github.com/open-mmlab/mmagic/tree/main/configs/edsr) | MMagic | Y | Y | Y | Y | N | Y | N | N |
| [RDN](https://github.com/open-mmlab/mmagic/tree/main/configs/rdn) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [DBNet](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/dbnet) | MMOCR | Y | Y | Y | Y | Y | Y | Y | N |
| [DBNetpp](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/dbnetpp) | MMOCR | Y | Y | Y | ? | ? | Y | ? | N |
| [PANet](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/panet) | MMOCR | Y | Y | Y | Y | ? | Y | Y | N |
| [PSENet](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/psenet) | MMOCR | Y | Y | Y | Y | ? | Y | Y | N |
| [TextSnake](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/textsnake) | MMOCR | Y | Y | Y | Y | ? | ? | ? | N |
| [MaskRCNN](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/maskrcnn) | MMOCR | Y | Y | Y | ? | ? | ? | ? | N |
| [CRNN](https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/crnn) | MMOCR | Y | Y | Y | Y | Y | N | N | N |
| [SAR](https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/sar) | MMOCR | N | Y | N | N | N | N | N | N |
| [SATRN](https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/satrn) | MMOCR | Y | Y | Y | N | N | N | N | N |
| [ABINet](https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/abinet) | MMOCR | Y | Y | Y | N | N | N | N | N |
| [HRNet](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#hrnet-cvpr-2019) | MMPose | N | Y | Y | Y | N | Y | N | N |
| [MSPN](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#mspn-arxiv-2019) | MMPose | N | Y | Y | Y | N | Y | N | N |
| [LiteHRNet](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#litehrnet-cvpr-2021) | MMPose | N | Y | Y | N | N | Y | N | N |
| [Hourglass](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#hourglass-eccv-2016) | MMPose | N | Y | Y | Y | N | Y | N | N |
| [SimCC](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/algorithms.html#simcc-eccv-2022) | MMPose | N | Y | Y | Y | N | N | N | N |
| [PointPillars](https://github.com/open-mmlab/mmdetection3d/tree/main/configs/pointpillars) | MMDetection3d | ? | Y | Y | N | N | Y | N | N |
| [CenterPoint (pillar)](https://github.com/open-mmlab/mmdetection3d/tree/main/configs/centerpoint) | MMDetection3d | ? | Y | Y | N | N | Y | N | N |
| [RotatedRetinaNet](https://github.com/open-mmlab/mmrotate/blob/main/configs/rotated_retinanet/README.md) | RotatedDetection | N | Y | Y | N | N | N | N | N |
| [Oriented RCNN](https://github.com/open-mmlab/mmrotate/blob/main/configs/oriented_rcnn/README.md) | RotatedDetection | N | Y | Y | N | N | N | N | N |
| [Gliding Vertex](https://github.com/open-mmlab/mmrotate/blob/main/configs/gliding_vertex/README.md) | RotatedDetection | N | N | Y | N | N | N | N | N |
### Note

10
docs/en/04-supported-codebases/mmdet3d.md
View File

@ -74,10 +74,10 @@ The caller needs to refer to the corresponding [python implementation](../../../
## Supported models
| model | dataset | onnxruntime | openvino | tensorrt\* |
| :---------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------: | :---------: | :------: | :--------: |
| [centerpoint](https://github.com/open-mmlab/mmdetection3d/blob/dev-1.x/configs/centerpoint/centerpoint_pillar02_second_secfpn_head-circlenms_8xb4-cyclic-20e_nus-3d.py) | nuScenes | ✔️ | ✔️ | ✔️ |
| [pointpillars](https://github.com/open-mmlab/mmdetection3d/blob/dev-1.x/configs/pointpillars/pointpillars_hv_secfpn_sbn-all_8xb4-2x_nus-3d.py) | nuScenes | ✔️ | ✔️ | ✔️ |
| [pointpillars](https://github.com/open-mmlab/mmdetection3d/blob/dev-1.x/configs/pointpillars/pointpillars_hv_secfpn_8xb6-160e_kitti-3d-3class.py) | KITTI | ✔️ | ✔️ | ✔️ |
| model | dataset | onnxruntime | openvino | tensorrt\* |
| :------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------: | :---------: | :------: | :--------: |
| [centerpoint](https://github.com/open-mmlab/mmdetection3d/blob/main/configs/centerpoint/centerpoint_pillar02_second_secfpn_head-circlenms_8xb4-cyclic-20e_nus-3d.py) | nuScenes | ✔️ | ✔️ | ✔️ |
| [pointpillars](https://github.com/open-mmlab/mmdetection3d/blob/main/configs/pointpillars/pointpillars_hv_secfpn_sbn-all_8xb4-2x_nus-3d.py) | nuScenes | ✔️ | ✔️ | ✔️ |
| [pointpillars](https://github.com/open-mmlab/mmdetection3d/blob/main/configs/pointpillars/pointpillars_hv_secfpn_8xb6-160e_kitti-3d-3class.py) | KITTI | ✔️ | ✔️ | ✔️ |
- Make sure trt >= 8.4 for some bug fixed, such as ScatterND, dynamic shape crash and so on.

26
docs/en/04-supported-codebases/mmocr.md
View File

@ -18,7 +18,7 @@
______________________________________________________________________
[MMOCR](https://github.com/open-mmlab/mmocr/tree/1.x) aka `mmocr` is an open-source toolbox based on PyTorch and mmdetection for text detection, text recognition, and the corresponding downstream tasks including key information extraction. It is a part of the [OpenMMLab](https://openmmlab.com/) project.
[MMOCR](https://github.com/open-mmlab/mmocr/tree/main) aka `mmocr` is an open-source toolbox based on PyTorch and mmdetection for text detection, text recognition, and the corresponding downstream tasks including key information extraction. It is a part of the [OpenMMLab](https://openmmlab.com/) project.
## Installation
@ -234,18 +234,18 @@ Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Inter
## Supported models
| Model | Task | TorchScript | OnnxRuntime | TensorRT | ncnn | PPLNN | OpenVINO |
| :---------------------------------------------------------------------------------- | :--------------- | :---------: | :---------: | :------: | :--: | :---: | :------: |
| [DBNet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/dbnet) | text-detection | Y | Y | Y | Y | Y | Y |
| [DBNetpp](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/dbnetpp) | text-detection | N | Y | Y | ? | ? | Y |
| [PSENet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/psenet) | text-detection | Y | Y | Y | Y | N | Y |
| [PANet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/panet) | text-detection | Y | Y | Y | Y | N | Y |
| [TextSnake](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/textsnake) | text-detection | Y | Y | Y | ? | ? | ? |
| [MaskRCNN](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/maskrcnn) | text-detection | Y | Y | Y | ? | ? | ? |
| [CRNN](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/crnn) | text-recognition | Y | Y | Y | Y | Y | N |
| [SAR](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/sar) | text-recognition | N | Y | Y | N | N | N |
| [SATRN](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/satrn) | text-recognition | Y | Y | Y | N | N | N |
| [ABINet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/abinet) | text-recognition | Y | Y | Y | ? | ? | ? |
| Model | Task | TorchScript | OnnxRuntime | TensorRT | ncnn | PPLNN | OpenVINO |
| :----------------------------------------------------------------------------------- | :--------------- | :---------: | :---------: | :------: | :--: | :---: | :------: |
| [DBNet](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/dbnet) | text-detection | Y | Y | Y | Y | Y | Y |
| [DBNetpp](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/dbnetpp) | text-detection | N | Y | Y | ? | ? | Y |
| [PSENet](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/psenet) | text-detection | Y | Y | Y | Y | N | Y |
| [PANet](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/panet) | text-detection | Y | Y | Y | Y | N | Y |
| [TextSnake](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/textsnake) | text-detection | Y | Y | Y | ? | ? | ? |
| [MaskRCNN](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/maskrcnn) | text-detection | Y | Y | Y | ? | ? | ? |
| [CRNN](https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/crnn) | text-recognition | Y | Y | Y | Y | Y | N |
| [SAR](https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/sar) | text-recognition | N | Y | Y | N | N | N |
| [SATRN](https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/satrn) | text-recognition | Y | Y | Y | N | N | N |
| [ABINet](https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/abinet) | text-recognition | Y | Y | Y | ? | ? | ? |
## Reminder

20
docs/en/04-supported-codebases/mmpose.md
View File

@ -13,13 +13,13 @@
______________________________________________________________________
[MMPose](https://github.com/open-mmlab/mmpose/tree/1.x) aka `mmpose` is an open-source toolbox for pose estimation based on PyTorch. It is a part of the [OpenMMLab](https://openmmlab.com/) project.
[MMPose](https://github.com/open-mmlab/mmpose/tree/main) aka `mmpose` is an open-source toolbox for pose estimation based on PyTorch. It is a part of the [OpenMMLab](https://openmmlab.com/) project.
## Installation
### Install mmpose
Please follow the [best practice](https://mmpose.readthedocs.io/en/1.x/installation.html#best-practices) to install mmpose.
Please follow the [best practice](https://mmpose.readthedocs.io/en/latest/installation.html#best-practices) to install mmpose.
### Install mmdeploy
@ -152,11 +152,11 @@ TODO
## Supported models
| Model | Task | ONNX Runtime | TensorRT | ncnn | PPLNN | OpenVINO |
| :----------------------------------------------------------------------------------------------------- | :------------ | :----------: | :------: | :--: | :---: | :------: |
| [HRNet](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/backbones.html#hrnet-cvpr-2019) | PoseDetection | Y | Y | Y | N | Y |
| [MSPN](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/backbones.html#mspn-arxiv-2019) | PoseDetection | Y | Y | Y | N | Y |
| [LiteHRNet](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/backbones.html#litehrnet-cvpr-2021) | PoseDetection | Y | Y | Y | N | Y |
| [Hourglass](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/algorithms.html#hourglass-eccv-2016) | PoseDetection | Y | Y | Y | N | Y |
| [SimCC](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/algorithms.html#simcc-eccv-2022) | PoseDetection | Y | Y | Y | N | N |
| [RTMPose](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose) | PoseDetection | Y | Y | Y | N | Y |
| Model | Task | ONNX Runtime | TensorRT | ncnn | PPLNN | OpenVINO |
| :-------------------------------------------------------------------------------------------------------- | :------------ | :----------: | :------: | :--: | :---: | :------: |
| [HRNet](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#hrnet-cvpr-2019) | PoseDetection | Y | Y | Y | N | Y |
| [MSPN](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#mspn-arxiv-2019) | PoseDetection | Y | Y | Y | N | Y |
| [LiteHRNet](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#litehrnet-cvpr-2021) | PoseDetection | Y | Y | Y | N | Y |
| [Hourglass](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/algorithms.html#hourglass-eccv-2016) | PoseDetection | Y | Y | Y | N | Y |
| [SimCC](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/algorithms.html#simcc-eccv-2022) | PoseDetection | Y | Y | Y | N | N |
| [RTMPose](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose) | PoseDetection | Y | Y | Y | N | Y |

2
docs/en/04-supported-codebases/mmpretrain.md
View File

@ -168,7 +168,7 @@ for label_id, score in result:
print(label_id, score)
```
Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Interface), such as C, C++, C#, Java and so on. You can learn their usage from [demos](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo).
Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Interface), such as C, C++, C#, Java and so on. You can learn their usage from [demos](https://github.com/open-mmlab/mmdeploy/tree/main/demo).
## Supported models

72
docs/en/04-supported-codebases/mmseg.md
View File

@ -14,7 +14,7 @@
______________________________________________________________________
[MMSegmentation](https://github.com/open-mmlab/mmsegmentation/tree/1.x) aka `mmseg` is an open source semantic segmentation toolbox based on PyTorch. It is a part of the [OpenMMLab](https://openmmlab.com/) project.
[MMSegmentation](https://github.com/open-mmlab/mmsegmentation/tree/main) aka `mmseg` is an open source semantic segmentation toolbox based on PyTorch. It is a part of the [OpenMMLab](https://openmmlab.com/) project.
## Installation
@ -188,41 +188,41 @@ Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Inter
## Supported models
| Model | TorchScript | OnnxRuntime | TensorRT | ncnn | PPLNN | OpenVino |
| :------------------------------------------------------------------------------------------------------- | :---------: | :---------: | :------: | :--: | :---: | :------: |
| [FCN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fcn) | Y | Y | Y | Y | Y | Y |
| [PSPNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/pspnet)[\*](#static_shape) | Y | Y | Y | Y | Y | Y |
| [DeepLabV3](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/deeplabv3) | Y | Y | Y | Y | Y | Y |
| [DeepLabV3+](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/deeplabv3plus) | Y | Y | Y | Y | Y | Y |
| [Fast-SCNN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fastscnn)[\*](#static_shape) | Y | Y | Y | N | Y | Y |
| [UNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/unet) | Y | Y | Y | Y | Y | Y |
| [ANN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/ann)[\*](#static_shape) | Y | Y | Y | N | N | N |
| [APCNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/apcnet) | Y | Y | Y | Y | N | N |
| [BiSeNetV1](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/bisenetv1) | Y | Y | Y | Y | N | Y |
| [BiSeNetV2](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/bisenetv2) | Y | Y | Y | Y | N | Y |
| [CGNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/cgnet) | Y | Y | Y | Y | N | Y |
| [DMNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/dmnet) | ? | Y | N | N | N | N |
| [DNLNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/dnlnet) | ? | Y | Y | Y | N | Y |
| [EMANet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/emanet) | Y | Y | Y | N | N | Y |
| [EncNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/encnet) | Y | Y | Y | N | N | Y |
| [ERFNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/erfnet) | Y | Y | Y | Y | N | Y |
| [FastFCN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fastfcn) | Y | Y | Y | Y | N | Y |
| [GCNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/gcnet) | Y | Y | Y | N | N | N |
| [ICNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/icnet)[\*](#static_shape) | Y | Y | Y | N | N | Y |
| [ISANet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/isanet)[\*](#static_shape) | N | Y | Y | N | N | Y |
| [NonLocal Net](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/nonlocal_net) | ? | Y | Y | Y | N | Y |
| [OCRNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/ocrnet) | Y | Y | Y | Y | N | Y |
| [PointRend](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/point_rend)[\*](#static_shape) | Y | Y | Y | N | N | N |
| [Semantic FPN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/sem_fpn) | Y | Y | Y | Y | N | Y |
| [STDC](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/stdc) | Y | Y | Y | Y | N | Y |
| [UPerNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/upernet)[\*](#static_shape) | N | Y | Y | N | N | N |
| [DANet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/danet) | ? | Y | Y | N | N | Y |
| [Segmenter](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/segmenter)[\*](#static_shape) | N | Y | Y | Y | N | Y |
| [SegFormer](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/segformer)[\*](#static_shape) | ? | Y | Y | N | N | Y |
| [SETR](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/setr) | ? | Y | N | N | N | Y |
| [CCNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/ccnet) | ? | N | N | N | N | N |
| [PSANet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/psanet) | ? | N | N | N | N | N |
| [DPT](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/dpt) | ? | N | N | N | N | N |
| Model | TorchScript | OnnxRuntime | TensorRT | ncnn | PPLNN | OpenVino |
| :-------------------------------------------------------------------------------------------------------- | :---------: | :---------: | :------: | :--: | :---: | :------: |
| [FCN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fcn) | Y | Y | Y | Y | Y | Y |
| [PSPNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/pspnet)[\*](#static_shape) | Y | Y | Y | Y | Y | Y |
| [DeepLabV3](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3) | Y | Y | Y | Y | Y | Y |
| [DeepLabV3+](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3plus) | Y | Y | Y | Y | Y | Y |
| [Fast-SCNN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fastscnn)[\*](#static_shape) | Y | Y | Y | N | Y | Y |
| [UNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/unet) | Y | Y | Y | Y | Y | Y |
| [ANN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/ann)[\*](#static_shape) | Y | Y | Y | N | N | N |
| [APCNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/apcnet) | Y | Y | Y | Y | N | N |
| [BiSeNetV1](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/bisenetv1) | Y | Y | Y | Y | N | Y |
| [BiSeNetV2](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/bisenetv2) | Y | Y | Y | Y | N | Y |
| [CGNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/cgnet) | Y | Y | Y | Y | N | Y |
| [DMNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/dmnet) | ? | Y | N | N | N | N |
| [DNLNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/dnlnet) | ? | Y | Y | Y | N | Y |
| [EMANet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/emanet) | Y | Y | Y | N | N | Y |
| [EncNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/encnet) | Y | Y | Y | N | N | Y |
| [ERFNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/erfnet) | Y | Y | Y | Y | N | Y |
| [FastFCN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fastfcn) | Y | Y | Y | Y | N | Y |
| [GCNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/gcnet) | Y | Y | Y | N | N | N |
| [ICNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/icnet)[\*](#static_shape) | Y | Y | Y | N | N | Y |
| [ISANet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/isanet)[\*](#static_shape) | N | Y | Y | N | N | Y |
| [NonLocal Net](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/nonlocal_net) | ? | Y | Y | Y | N | Y |
| [OCRNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/ocrnet) | Y | Y | Y | Y | N | Y |
| [PointRend](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/point_rend)[\*](#static_shape) | Y | Y | Y | N | N | N |
| [Semantic FPN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/sem_fpn) | Y | Y | Y | Y | N | Y |
| [STDC](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/stdc) | Y | Y | Y | Y | N | Y |
| [UPerNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/upernet)[\*](#static_shape) | N | Y | Y | N | N | N |
| [DANet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/danet) | ? | Y | Y | N | N | Y |
| [Segmenter](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/segmenter)[\*](#static_shape) | N | Y | Y | Y | N | Y |
| [SegFormer](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/segformer)[\*](#static_shape) | ? | Y | Y | N | N | Y |
| [SETR](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/setr) | ? | Y | N | N | N | Y |
| [CCNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/ccnet) | ? | N | N | N | N | N |
| [PSANet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/psanet) | ? | N | N | N | N | N |
| [DPT](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/dpt) | ? | N | N | N | N | N |
## Reminder

2
docs/zh_cn/01-how-to-build/android.md
View File

@ -98,7 +98,7 @@ make -j$(nproc) install
<tr>
<td>OpenJDK </td>
<td>编译Java API之前需要先准备OpenJDK开发环境</br>
请参考 <a href='https://github.com/open-mmlab/mmdeploy/tree/1.x/csrc/mmdeploy/apis/java/README.md'> Java API 编译 </a> 进行构建.
请参考 <a href='https://github.com/open-mmlab/mmdeploy/tree/main/csrc/mmdeploy/apis/java/README.md'> Java API 编译 </a> 进行构建.
</td>
</tr>
</tbody>

4
docs/zh_cn/01-how-to-build/build_from_source.md
View File

@ -5,7 +5,7 @@
## 下载
```bash
git clone -b 1.x git@github.com:open-mmlab/mmdeploy.git --recursive
git clone -b main git@github.com:open-mmlab/mmdeploy.git --recursive
```
### FAQ
@ -32,7 +32,7 @@ git clone -b 1.x git@github.com:open-mmlab/mmdeploy.git --recursive
- 如果以 `SSH` 方式 `git clone` 代码失败，您可以尝试使用 `HTTPS` 协议下载代码：
```bash
git clone -b 1.x https://github.com/open-mmlab/mmdeploy.git MMDeploy
git clone -b main https://github.com/open-mmlab/mmdeploy.git MMDeploy
cd MMDeploy
git submodule update --init --recursive
```

2
docs/zh_cn/01-how-to-build/jetsons.md
View File

@ -214,7 +214,7 @@ conda activate mmdeploy
## 安装 MMDeploy
```shell
git clone -b 1.x --recursive https://github.com/open-mmlab/mmdeploy.git
git clone -b main --recursive https://github.com/open-mmlab/mmdeploy.git
cd mmdeploy
export MMDEPLOY_DIR=$(pwd)
```

2
docs/zh_cn/02-how-to-run/convert_model.md
View File

@ -26,7 +26,7 @@
### 准备工作
1. 安装您的目标后端。 您可以参考 [ONNXRuntime-install](../05-supported-backends/onnxruntime.md) ，[TensorRT-install](../05-supported-backends/tensorrt.md) ，[ncnn-install](../05-supported-backends/ncnn.md) ，[PPLNN-install](../05-supported-backends/pplnn.md), [OpenVINO-install](../05-supported-backends/openvino.md)。
2. 安装您的目标代码库。 您可以参考 [MMPretrain-install](https://github.com/open-mmlab/mmpretrain/blob/main/docs/zh_CN/get_started.md#%E5%AE%89%E8%A3%85)， [MMDetection-install](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/zh_cn/get_started.md)， [MMSegmentation-install](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/zh_cn/get_started.md#installation)， [MMOCR-install](https://github.com/open-mmlab/mmocr/blob/1.x/docs/zh_cn/get_started/install.md)， [MMagic-install](https://github.com/open-mmlab/mmagic/blob/main/docs/en/get_started/install.md)。
2. 安装您的目标代码库。 您可以参考 [MMPretrain-install](https://mmpretrain.readthedocs.io/en/latest/get_started.html#installation)，[MMDetection-install](https://mmdetection.readthedocs.io/en/latest/get_started.html#installation)，[MMSegmentation-install](https://mmsegmentation.readthedocs.io/en/latest/get_started.html#installation)，[MMOCR-install](https://mmocr.readthedocs.io/en/latest/get_started/install.html#installation-steps)，[MMagic-install](https://mmagic.readthedocs.io/en/latest/get_started/install.html#installation)。
### 使用方法

4
docs/zh_cn/02-how-to-run/prebuilt_package_windows.md
View File

@ -56,7 +56,7 @@ ______________________________________________________________________
2. 克隆mmdeploy仓库
```bash
git clone -b 1.x https://github.com/open-mmlab/mmdeploy.git
git clone -b main https://github.com/open-mmlab/mmdeploy.git
```
:point_right: 这里主要为了使用configs文件，所以没有加`--recursive`来下载submodule，也不需要编译`mmdeploy`
@ -64,7 +64,7 @@ ______________________________________________________________________
3. 安装mmpretrain
```bash
git clone -b 1.x https://github.com/open-mmlab/mmpretrain.git
git clone -b main https://github.com/open-mmlab/mmpretrain.git
cd mmpretrain
pip install -e .
```

2
docs/zh_cn/02-how-to-run/write_config.md
View File

@ -187,4 +187,4 @@ detection_tensorrt-int8_dynamic-320x320-1344x1344.py
## 6. 如何编写模型配置文件
请根据模型具体任务的代码库，编写模型配置文件。 模型配置文件用于初始化模型，详情请参考[MMPretrain](https://github.com/open-mmlab/mmpretrain/blob/main/docs/zh_CN/user_guides/config.md)，[MMDetection](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/zh_cn/user_guides/config.md)， [MMSegmentation](https://github.com/open-mmlab/mmsegmentation/blob/1.x/docs/zh_cn/user_guides/1_config.md)， [MMOCR](https://github.com/open-mmlab/mmocr/blob/1.x/docs/en/user_guides/config.md)，[MMagic](https://github.com/open-mmlab/mmagic/blob/main/docs/en/user_guides/config.md)。
请根据模型具体任务的代码库，编写模型配置文件。 模型配置文件用于初始化模型，详情请参考[MMPretrain](https://github.com/open-mmlab/mmpretrain/blob/main/docs/zh_CN/user_guides/config.md)，[MMDetection](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/zh_cn/user_guides/config.md)， [MMSegmentation](https://github.com/open-mmlab/mmsegmentation/blob/main/docs/zh_cn/user_guides/1_config.md)， [MMOCR](https://github.com/open-mmlab/mmocr/blob/main/docs/en/user_guides/config.md)，[MMagic](https://github.com/open-mmlab/mmagic/blob/main/docs/en/user_guides/config.md)。

146
docs/zh_cn/03-benchmark/benchmark.md
View File

@ -142,7 +142,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center" colspan="1">fp16</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/yolo/yolov3_d53_320_273e_coco.py">YOLOv3</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/yolo/yolov3_d53_320_273e_coco.py">YOLOv3</a></td>
<td align="center">320x320</td>
<td align="center">14.76</td>
<td align="center">24.92</td>
@ -151,7 +151,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">18.07</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/ssd/ssdlite_mobilenetv2_scratch_600e_coco.py">SSD-Lite</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/ssd/ssdlite_mobilenetv2_scratch_600e_coco.py">SSD-Lite</a></td>
<td align="center">320x320</td>
<td align="center">8.84</td>
<td align="center">9.21</td>
@ -160,7 +160,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">19.72</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/retinanet/retinanet_r50_fpn_1x_coco.py">RetinaNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/retinanet/retinanet_r50_fpn_1x_coco.py">RetinaNet</a></td>
<td align="center">800x1344</td>
<td align="center">97.09</td>
<td align="center">25.79</td>
@ -169,7 +169,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">38.34</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/fcos/fcos_r50_caffe_fpn_gn-head_1x_coco.py">FCOS</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/fcos/fcos_r50_caffe_fpn_gn-head_1x_coco.py">FCOS</a></td>
<td align="center">800x1344</td>
<td align="center">84.06</td>
<td align="center">23.15</td>
@ -178,7 +178,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/fsaf/fsaf_r50_fpn_1x_coco.py">FSAF</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/fsaf/fsaf_r50_fpn_1x_coco.py">FSAF</a></td>
<td align="center">800x1344</td>
<td align="center">82.96</td>
<td align="center">21.02</td>
@ -187,7 +187,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">30.41</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py">Faster R-CNN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py">Faster R-CNN</a></td>
<td align="center">800x1344</td>
<td align="center">88.08</td>
<td align="center">26.52</td>
@ -196,7 +196,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">65.40</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py">Mask R-CNN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py">Mask R-CNN</a></td>
<td align="center">800x1344</td>
<td align="center">104.83</td>
<td align="center">58.27</td>
@ -228,19 +228,19 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center" colspan="1">fp32</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/yolo/yolov3_mobilenetv2_mstrain-416_300e_coco.py">MobileNetv2-YOLOv3</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/yolo/yolov3_mobilenetv2_mstrain-416_300e_coco.py">MobileNetv2-YOLOv3</a></td>
<td align="center">320x320</td>
<td align="center">48.57</td>
<td align="center">66.55</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/ssd/ssdlite_mobilenetv2_scratch_600e_coco.py">SSD-Lite</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/ssd/ssdlite_mobilenetv2_scratch_600e_coco.py">SSD-Lite</a></td>
<td align="center">320x320</td>
<td align="center">44.91</td>
<td align="center">66.19</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/yolox/yolox_tiny_8x8_300e_coco.py">YOLOX</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/yolox/yolox_tiny_8x8_300e_coco.py">YOLOX</a></td>
<td align="center">416x416</td>
<td align="center">111.60</td>
<td align="center">134.50</td>
@ -323,7 +323,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center" colspan="1">fp32</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/dbnet/dbnet_resnet18_fpnc_1200e_icdar2015.py">DBNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/dbnet/dbnet_resnet18_fpnc_1200e_icdar2015.py">DBNet</a></td>
<td align="center">640x640</td>
<td align="center">10.70</td>
<td align="center">5.62</td>
@ -333,7 +333,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py">CRNN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py">CRNN</a></td>
<td align="center">32x32</td>
<td align="center">1.93 </td>
<td align="center">1.40</td>
@ -370,7 +370,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center" colspan="1">fp16</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py">FCN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py">FCN</a></td>
<td align="center">512x1024</td>
<td align="center">128.42</td>
<td align="center">23.97</td>
@ -379,7 +379,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">27.00</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py">PSPNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py">PSPNet</a></td>
<td align="center">1x3x512x1024</td>
<td align="center">119.77</td>
<td align="center">24.10</td>
@ -388,7 +388,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">27.26</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/deeplabv3/deeplabv3/deeplabv3_r50-d8_4xb2-80k_cityscapes-512x1024.py">DeepLabV3</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3/deeplabv3/deeplabv3_r50-d8_4xb2-80k_cityscapes-512x1024.py">DeepLabV3</a></td>
<td align="center">512x1024</td>
<td align="center">226.75</td>
<td align="center">31.80</td>
@ -397,7 +397,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">36.01</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-512x1024.py">DeepLabV3+</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-80k_cityscapes-512x1024.py">DeepLabV3+</a></td>
<td align="center">512x1024</td>
<td align="center">151.25</td>
<td align="center">47.03</td>
@ -653,7 +653,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">fp32</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/yolo/yolov3_d53_320_273e_coco.py">YOLOV3</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/yolo/yolov3_d53_320_273e_coco.py">YOLOV3</a></td>
<td align="center">Object Detection</td>
<td align="center">COCO2017</td>
<td align="center">box AP</td>
@ -668,7 +668,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/ssd/ssd300_coco.py">SSD</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/ssd/ssd300_coco.py">SSD</a></td>
<td align="center">Object Detection</td>
<td align="center">COCO2017</td>
<td align="center">box AP</td>
@ -683,7 +683,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/retinanet/retinanet_r50_fpn_1x_coco.py">RetinaNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/retinanet/retinanet_r50_fpn_1x_coco.py">RetinaNet</a></td>
<td align="center">Object Detection</td>
<td align="center">COCO2017</td>
<td align="center">box AP</td>
@ -698,7 +698,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/fcos/fcos_r50_caffe_fpn_gn-head_1x_coco.py">FCOS</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/fcos/fcos_r50_caffe_fpn_gn-head_1x_coco.py">FCOS</a></td>
<td align="center">Object Detection</td>
<td align="center">COCO2017</td>
<td align="center">box AP</td>
@ -713,7 +713,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/fsaf/fsaf_r50_fpn_1x_coco.py">FSAF</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/fsaf/fsaf_r50_fpn_1x_coco.py">FSAF</a></td>
<td align="center">Object Detection</td>
<td align="center">COCO2017</td>
<td align="center">box AP</td>
@ -743,7 +743,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/yolox/yolox_s_8x8_300e_coco.py">YOLOX</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/yolox/yolox_s_8x8_300e_coco.py">YOLOX</a></td>
<td align="center">Object Detection</td>
<td align="center">COCO2017</td>
<td align="center">box AP</td>
@ -758,7 +758,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py">Faster R-CNN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py">Faster R-CNN</a></td>
<td align="center">Object Detection</td>
<td align="center">COCO2017</td>
<td align="center">box AP</td>
@ -773,7 +773,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/atss/atss_r50_fpn_1x_coco.py">ATSS</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/atss/atss_r50_fpn_1x_coco.py">ATSS</a></td>
<td align="center">Object Detection</td>
<td align="center">COCO2017</td>
<td align="center">box AP</td>
@ -788,7 +788,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/cascade_rcnn/cascade_rcnn_r50_caffe_fpn_1x_coco.py">Cascade R-CNN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/cascade_rcnn/cascade_rcnn_r50_caffe_fpn_1x_coco.py">Cascade R-CNN</a></td>
<td align="center">Object Detection</td>
<td align="center">COCO2017</td>
<td align="center">box AP</td>
@ -803,7 +803,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/gfl/gfl_r50_fpn_1x_coco.py">GFL</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/gfl/gfl_r50_fpn_1x_coco.py">GFL</a></td>
<td align="center">Object Detection</td>
<td align="center">COCO2017</td>
<td align="center">box AP</td>
@ -818,7 +818,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/reppoints/reppoints_moment_r50_fpn_1x_coco.py">RepPoints</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/reppoints/reppoints_moment_r50_fpn_1x_coco.py">RepPoints</a></td>
<td align="center">Object Detection</td>
<td align="center">COCO2017</td>
<td align="center">box AP</td>
@ -833,7 +833,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/detr/detr_r50_8x2_150e_coco.py">DETR</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/detr/detr_r50_8x2_150e_coco.py">DETR</a></td>
<td align="center">Object Detection</td>
<td align="center">COCO2017</td>
<td align="center">box AP</td>
@ -848,7 +848,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py">Mask R-CNN</a></td>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmdetection/tree/main/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py">Mask R-CNN</a></td>
<td align="center" rowspan="2">Instance Segmentation</td>
<td align="center" rowspan="2">COCO2017</td>
<td align="center">box AP</td>
@ -875,7 +875,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmdetection/blob/master/configs/swin/mask_rcnn_swin-t-p4-w7_fpn_1x_coco.py">Swin-Transformer</a></td>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmdetection/blob/main/configs/swin/mask_rcnn_swin-t-p4-w7_fpn_1x_coco.py">Swin-Transformer</a></td>
<td align="center" rowspan="2">Instance Segmentation</td>
<td align="center" rowspan="2">COCO2017</td>
<td align="center">box AP</td>
@ -1153,7 +1153,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">fp32</td>
</tr>
<tr>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/dbnet/dbnet_resnet18_fpnc_1200e_icdar2015.py">DBNet*</a></td>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/dbnet/dbnet_resnet18_fpnc_1200e_icdar2015.py">DBNet*</a></td>
<td align="center" rowspan="3">TextDetection</td>
<td align="center" rowspan="3">ICDAR2015</td>
<td align="center">recall</td>
@ -1189,7 +1189,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">0.7950</td>
</tr>
<tr>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/dbnetpp/dbnetpp_resnet50_fpnc_1200e_icdar2015.py">DBNetpp</a></td>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/dbnetpp/dbnetpp_resnet50_fpnc_1200e_icdar2015.py">DBNetpp</a></td>
<td align="center" rowspan="3">TextDetection</td>
<td align="center" rowspan="3">ICDAR2015</td>
<td align="center">recall</td>
@ -1225,7 +1225,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">0.8622</td>
</tr>
<tr>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/psenet/psenet_resnet50_fpnf_600e_icdar2015.py">PSENet</a></td>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/psenet/psenet_resnet50_fpnf_600e_icdar2015.py">PSENet</a></td>
<td align="center" rowspan="3">TextDetection</td>
<td align="center" rowspan="3">ICDAR2015</td>
<td align="center">recall</td>
@ -1261,7 +1261,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">0.8057</td>
</tr>
<tr>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/panet/panet_resnet18_fpem-ffm_600e_icdar2015.py">PANet</a></td>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/panet/panet_resnet18_fpem-ffm_600e_icdar2015.py">PANet</a></td>
<td align="center" rowspan="3">TextDetection</td>
<td align="center" rowspan="3">ICDAR2015</td>
<td align="center">recall</td>
@ -1297,7 +1297,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">0.7955</td>
</tr>
<tr>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/textsnake/textsnake_resnet50_fpn-unet_1200e_ctw1500.py">TextSnake</a></td>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/textsnake/textsnake_resnet50_fpn-unet_1200e_ctw1500.py">TextSnake</a></td>
<td align="center" rowspan="3">TextDetection</td>
<td align="center" rowspan="3">CTW1500</td>
<td align="center">recall</td>
@ -1333,7 +1333,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/maskrcnn/mask-rcnn_resnet50_fpn_160e_icdar2015.py">MaskRCNN</a></td>
<td align="center" rowspan="3"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/maskrcnn/mask-rcnn_resnet50_fpn_160e_icdar2015.py">MaskRCNN</a></td>
<td align="center" rowspan="3">TextDetection</td>
<td align="center" rowspan="3">ICDAR2015</td>
<td align="center">recall</td>
@ -1369,7 +1369,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py">CRNN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/crnn/crnn_mini-vgg_5e_mj.py">CRNN</a></td>
<td align="center">TextRecognition</td>
<td align="center">IIIT5K</td>
<td align="center">acc</td>
@ -1383,7 +1383,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/sar/sar_resnet31_parallel-decoder_5e_st-sub_mj-sub_sa_real.py">SAR</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/sar/sar_resnet31_parallel-decoder_5e_st-sub_mj-sub_sa_real.py">SAR</a></td>
<td align="center">TextRecognition</td>
<td align="center">IIIT5K</td>
<td align="center">acc</td>
@ -1397,7 +1397,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/satrn/satrn_shallow-small_5e_st_mj.py">SATRN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/satrn/satrn_shallow-small_5e_st_mj.py">SATRN</a></td>
<td align="center">TextRecognition</td>
<td align="center">IIIT5K</td>
<td align="center">acc</td>
@ -1411,7 +1411,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/abinet/abinet_20e_st-an_mj.py">ABINet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/abinet/abinet_20e_st-an_mj.py">ABINet</a></td>
<td align="center">TextRecognition</td>
<td align="center">IIIT5K</td>
<td align="center">acc</td>
@ -1455,7 +1455,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">fp32</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py">FCN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py">FCN</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">72.25</td>
@ -1468,7 +1468,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">72.35</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py">PSPNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py">PSPNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">78.55</td>
@ -1481,7 +1481,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">78.67</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-512x1024.py">deeplabv3</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3/deeplabv3_r50-d8_4xb2-40k_cityscapes-512x1024.py">deeplabv3</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">79.09</td>
@ -1494,7 +1494,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">79.06</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_cityscapes-512x1024.py">deeplabv3+</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3plus/deeplabv3plus_r50-d8_4xb2-40k_cityscapes-512x1024.py">deeplabv3+</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">79.61</td>
@ -1507,7 +1507,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">79.51</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fastscnn/fast_scnn_8xb4-160k_cityscapes-512x1024.py">Fast-SCNN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fastscnn/fast_scnn_8xb4-160k_cityscapes-512x1024.py">Fast-SCNN</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">70.96</td>
@ -1520,7 +1520,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/unet/unet-s5-d16_fcn_4xb4-160k_cityscapes-512x1024.py">UNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/unet/unet-s5-d16_fcn_4xb4-160k_cityscapes-512x1024.py">UNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">69.10</td>
@ -1533,7 +1533,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/ann/ann_r50-d8_4xb2-40k_cityscapes-512x1024.py">ANN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/ann/ann_r50-d8_4xb2-40k_cityscapes-512x1024.py">ANN</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">77.40</td>
@ -1546,7 +1546,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/apcnet/apcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py">APCNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/apcnet/apcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py">APCNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">77.40</td>
@ -1559,7 +1559,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_cityscapes-1024x1024.py">BiSeNetV1</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/bisenetv1/bisenetv1_r18-d32_4xb4-160k_cityscapes-1024x1024.py">BiSeNetV1</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">74.44</td>
@ -1572,7 +1572,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/bisenetv2/bisenetv2_fcn_4xb4-160k_cityscapes-1024x1024.py">BiSeNetV2</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/bisenetv2/bisenetv2_fcn_4xb4-160k_cityscapes-1024x1024.py">BiSeNetV2</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">73.21</td>
@ -1585,7 +1585,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/cgnet/cgnet_fcn_4xb8-60k_cityscapes-512x1024.py">CGNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/cgnet/cgnet_fcn_4xb8-60k_cityscapes-512x1024.py">CGNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">68.25</td>
@ -1598,7 +1598,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/emanet/emanet_r50-d8_4xb2-80k_cityscapes-512x1024.py">EMANet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/emanet/emanet_r50-d8_4xb2-80k_cityscapes-512x1024.py">EMANet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">77.59</td>
@ -1611,7 +1611,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/encnet/encnet_r50-d8_4xb2-40k_cityscapes-512x1024.py">EncNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/encnet/encnet_r50-d8_4xb2-40k_cityscapes-512x1024.py">EncNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">75.67</td>
@ -1624,7 +1624,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/erfnet/erfnet_fcn_4xb4-160k_cityscapes-512x1024.py">ERFNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/erfnet/erfnet_fcn_4xb4-160k_cityscapes-512x1024.py">ERFNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">71.08</td>
@ -1637,7 +1637,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py">FastFCN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fastfcn/fastfcn_r50-d32_jpu_aspp_4xb2-80k_cityscapes-512x1024.py">FastFCN</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">79.12</td>
@ -1650,7 +1650,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py">GCNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/gcnet/gcnet_r50-d8_4xb2-40k_cityscapes-512x1024.py">GCNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">77.69</td>
@ -1663,7 +1663,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/icnet/icnet_r18-d8_4xb2-80k_cityscapes-832x832.py">ICNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/icnet/icnet_r18-d8_4xb2-80k_cityscapes-832x832.py">ICNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">76.29</td>
@ -1676,7 +1676,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/isanet/isanet_r50-d8_4xb2-40k_cityscapes-512x1024.py">ISANet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/isanet/isanet_r50-d8_4xb2-40k_cityscapes-512x1024.py">ISANet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">78.49</td>
@ -1689,7 +1689,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024.py">OCRNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/ocrnet/ocrnet_hr18s_4xb2-40k_cityscapes-512x1024.py">OCRNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">74.30</td>
@ -1702,7 +1702,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/point_rend/pointrend_r50_4xb2-80k_cityscapes-512x1024.py">PointRend</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/point_rend/pointrend_r50_4xb2-80k_cityscapes-512x1024.py">PointRend</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">76.47</td>
@ -1715,7 +1715,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/sem_fpn/fpn_r50_4xb2-80k_cityscapes-512x1024.py">Semantic FPN</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/sem_fpn/fpn_r50_4xb2-80k_cityscapes-512x1024.py">Semantic FPN</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">74.52</td>
@ -1728,7 +1728,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/stdc/stdc1_in1k-pre_4xb12-80k_cityscapes-512x1024.py">STDC</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/stdc/stdc1_in1k-pre_4xb12-80k_cityscapes-512x1024.py">STDC</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">75.10</td>
@ -1741,7 +1741,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/stdc/stdc2_in1k-pre_4xb12-80k_cityscapes-512x1024.py">STDC</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/stdc/stdc2_in1k-pre_4xb12-80k_cityscapes-512x1024.py">STDC</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">77.17</td>
@ -1754,7 +1754,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/upernet/upernet_r50_4xb2-40k_cityscapes-512x1024.py">UPerNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/tree/main/configs/upernet/upernet_r50_4xb2-40k_cityscapes-512x1024.py">UPerNet</a></td>
<td align="center">Cityscapes</td>
<td align="center">mIoU</td>
<td align="center">77.10</td>
@ -1767,7 +1767,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/blob/1.x/configs/segmenter/segmenter_vit-s_fcn_8xb1-160k_ade20k-512x512.py">Segmenter</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmsegmentation/blob/main/configs/segmenter/segmenter_vit-s_fcn_8xb1-160k_ade20k-512x512.py">Segmenter</a></td>
<td align="center">ADE20K</td>
<td align="center">mIoU</td>
<td align="center">44.32</td>
@ -1808,7 +1808,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">fp32</td>
</tr>
<tr>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/1.x/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_hrnet-w48_8xb32-210e_coco-256x192.py">HRNet</a></td>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/main/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_hrnet-w48_8xb32-210e_coco-256x192.py">HRNet</a></td>
<td align="center" rowspan="2">Pose Detection</td>
<td align="center" rowspan="2">COCO</td>
<td align="center">AP</td>
@ -1829,7 +1829,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">0.802</td>
</tr>
<tr>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/1.x/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_litehrnet-30_8xb64-210e_coco-256x192.py">LiteHRNet</a></td>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/main/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_litehrnet-30_8xb64-210e_coco-256x192.py">LiteHRNet</a></td>
<td align="center" rowspan="2">Pose Detection</td>
<td align="center" rowspan="2">COCO</td>
<td align="center">AP</td>
@ -1850,7 +1850,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">0.728</td>
</tr>
<tr>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/1.x/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_4xmspn50_8xb32-210e_coco-256x192.py">MSPN</a></td>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/main/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_4xmspn50_8xb32-210e_coco-256x192.py">MSPN</a></td>
<td align="center" rowspan="2">Pose Detection</td>
<td align="center" rowspan="2">COCO</td>
<td align="center">AP</td>
@ -1871,7 +1871,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">0.825</td>
</tr>
<tr>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/1.x/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_hourglass52_8xb32-210e_coco-256x256.py">Hourglass</a></td>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/main/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_hourglass52_8xb32-210e_coco-256x256.py">Hourglass</a></td>
<td align="center" rowspan="2">Pose Detection</td>
<td align="center" rowspan="2">COCO</td>
<td align="center">AP</td>
@ -1892,7 +1892,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">0.774</td>
</tr>
<tr>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/1.x/configs/body_2d_keypoint/simcc/coco/simcc_mobilenetv2_wo-deconv-8xb64-210e_coco-256x192.py">SimCC</a></td>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmpose/blob/main/configs/body_2d_keypoint/simcc/coco/simcc_mobilenetv2_wo-deconv-8xb64-210e_coco-256x192.py">SimCC</a></td>
<td align="center" rowspan="2">Pose Detection</td>
<td align="center" rowspan="2">COCO</td>
<td align="center">AP</td>
@ -1942,7 +1942,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">fp32</td>
</tr>
<tr>
<td align="center"><a href="https://github.com/open-mmlab/mmrotate/tree/1.x/configs/rotated_retinanet/rotated-retinanet-hbox-oc_r50_fpn_1x_dota.py">RotatedRetinaNet</a></td>
<td align="center"><a href="https://github.com/open-mmlab/mmrotate/tree/main/configs/rotated_retinanet/rotated-retinanet-hbox-oc_r50_fpn_1x_dota.py">RotatedRetinaNet</a></td>
<td align="center">Rotated Detection</td>
<td align="center">DOTA-v1.0</td>
<td align="center">mAP</td>
@ -2019,7 +2019,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">fp32</td>
</tr>
<tr>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmaction2/blob/1.x/configs/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x3-100e_kinetics400-rgb.py">TSN</a></td>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/tsn/tsn_imagenet-pretrained-r50_8xb32-1x1x3-100e_kinetics400-rgb.py">TSN</a></td>
<td align="center" rowspan="2">Recognition</td>
<td align="center" rowspan="2">Kinetics-400</td>
<td align="center">top-1</td>
@ -2040,7 +2040,7 @@ GPU: ncnn, TensorRT, PPLNN
<td align="center">-</td>
</tr>
<tr>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmaction2/blob/1.x/configs/recognition/slowfast/slowfast_r50_8xb8-4x16x1-256e_kinetics400-rgb.py">SlowFast</a></td>
<td align="center" rowspan="2"><a href="https://github.com/open-mmlab/mmaction2/blob/main/configs/recognition/slowfast/slowfast_r50_8xb8-4x16x1-256e_kinetics400-rgb.py">SlowFast</a></td>
<td align="center" rowspan="2">Recognition</td>
<td align="center" rowspan="2">Kinetics-400</td>
<td align="center">top-1</td>

18
docs/zh_cn/03-benchmark/benchmark_edge.md
View File

@ -22,15 +22,15 @@ tips:
## mmocr 检测
| model | dataset | spatial | fp32 hmean | snpe gpu hybrid hmean | latency(ms) |
| :-------------------------------------------------------------------------------------------------------------------: | :-------: | :------: | :--------: | :-------------------: | :---------: |
| [PANet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/panet/panet_resnet18_fpem-ffm_600e_icdar2015.py) | ICDAR2015 | 1312x736 | 0.795 | 0.785 @thr=0.9 | 3100±100 |
| model | dataset | spatial | fp32 hmean | snpe gpu hybrid hmean | latency(ms) |
| :--------------------------------------------------------------------------------------------------------------------: | :-------: | :------: | :--------: | :-------------------: | :---------: |
| [PANet](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/panet/panet_resnet18_fpem-ffm_600e_icdar2015.py) | ICDAR2015 | 1312x736 | 0.795 | 0.785 @thr=0.9 | 3100±100 |
## mmpose 模型
| model | dataset | spatial | snpe hybrid AR@IoU=0.50 | snpe hybrid AP@IoU=0.50 | latency(ms) |
| :--------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :--------: | :-----: | :---------------------: | :---------------------: | :---------: |
| [pose_hrnet_w32](https://github.com/open-mmlab/mmpose/blob/1.x/configs/animal_2d_keypoint/topdown_heatmap/animalpose/td-hm_hrnet-w32_8xb64-210e_animalpose-256x256.py) | Animalpose | 256x256 | 0.997 | 0.989 | 630±50 |
| model | dataset | spatial | snpe hybrid AR@IoU=0.50 | snpe hybrid AP@IoU=0.50 | latency(ms) |
| :---------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :--------: | :-----: | :---------------------: | :---------------------: | :---------: |
| [pose_hrnet_w32](https://github.com/open-mmlab/mmpose/blob/main/configs/animal_2d_keypoint/topdown_heatmap/animalpose/td-hm_hrnet-w32_8xb64-210e_animalpose-256x256.py) | Animalpose | 256x256 | 0.997 | 0.989 | 630±50 |
tips:
@ -38,9 +38,9 @@ tips:
## mmseg
| model | dataset | spatial | mIoU | latency(ms) |
| :-----------------------------------------------------------------------------------------------------------------: | :--------: | :------: | :---: | :---------: |
| [fcn](https://github.com/open-mmlab/mmsegmentation/blob/1.x/configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-512x1024.py) | Cityscapes | 512x1024 | 71.11 | 4915±500 |
| model | dataset | spatial | mIoU | latency(ms) |
| :------------------------------------------------------------------------------------------------------------------: | :--------: | :------: | :---: | :---------: |
| [fcn](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r18-d8_4xb2-80k_cityscapes-512x1024.py) | Cityscapes | 512x1024 | 71.11 | 4915±500 |
tips:

54
docs/zh_cn/03-benchmark/benchmark_tvm.md
View File

@ -2,26 +2,26 @@
## 支持模型列表
| Model | Codebase | Model config |
| :---------------- | :------------- | :--------------------------------------------------------------------------------------: |
| RetinaNet | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/retinanet) |
| Faster R-CNN | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/faster_rcnn) |
| YOLOv3 | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/yolo) |
| YOLOX | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/yolox) |
| Mask R-CNN | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn) |
| SSD | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/master/configs/ssd) |
| ResNet | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnet) |
| ResNeXt | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnext) |
| SE-ResNet | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/seresnet) |
| MobileNetV2 | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/mobilenet_v2) |
| ShuffleNetV1 | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v1) |
| ShuffleNetV2 | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v2) |
| VisionTransformer | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/vision_transformer) |
| FCN | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/fcn) |
| PSPNet | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/pspnet) |
| DeepLabV3 | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/deeplabv3) |
| DeepLabV3+ | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/deeplabv3plus) |
| UNet | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/unet) |
| Model | Codebase | Model config |
| :---------------- | :------------- | :-------------------------------------------------------------------------------------: |
| RetinaNet | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/main/configs/retinanet) |
| Faster R-CNN | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/main/configs/faster_rcnn) |
| YOLOv3 | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/main/configs/yolo) |
| YOLOX | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/main/configs/yolox) |
| Mask R-CNN | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/main/configs/mask_rcnn) |
| SSD | MMDetection | [config](https://github.com/open-mmlab/mmdetection/tree/main/configs/ssd) |
| ResNet | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnet) |
| ResNeXt | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnext) |
| SE-ResNet | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/seresnet) |
| MobileNetV2 | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/mobilenet_v2) |
| ShuffleNetV1 | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v1) |
| ShuffleNetV2 | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v2) |
| VisionTransformer | MMPretrain | [config](https://github.com/open-mmlab/mmpretrain/tree/main/configs/vision_transformer) |
| FCN | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fcn) |
| PSPNet | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/pspnet) |
| DeepLabV3 | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3) |
| DeepLabV3+ | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3plus) |
| UNet | MMSegmentation | [config](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/unet) |
表中仅列出已测试模型，未列出的模型可能同样支持，可以自行尝试转换。
@ -39,13 +39,13 @@
<!-- | [Vision Transformer](https://github.com/open-mmlab/mmpretrain/blob/main/configs/vision_transformer/vit-base-p16_ft-64xb64_in1k-384.py) | top-1 | 85.43 | 84.01 | -->
| mmdet(\*) | metric | PyTorch | TVM |
| :-------------------------------------------------------------------------------------: | :----: | :-----: | :--: |
| [SSD](https://github.com/open-mmlab/mmdetection/tree/master/configs/ssd/ssd300_coco.py) | box AP | 25.5 | 25.5 |
| mmdet(\*) | metric | PyTorch | TVM |
| :-----------------------------------------------------------------------------------: | :----: | :-----: | :--: |
| [SSD](https://github.com/open-mmlab/mmdetection/tree/main/configs/ssd/ssd300_coco.py) | box AP | 25.5 | 25.5 |
\*: 由于暂时不支持动态转换，因此仅提供 SSD 的精度测试结果。
| mmseg | metric | PyTorch | TVM |
| :------------------------------------------------------------------------------------------------------------------------: | :----: | :-----: | :---: |
| [FCN](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/fcn/fcn_r50-d8_512x1024_40k_cityscapes.py) | mIoU | 72.25 | 72.36 |
| [PSPNet](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes.py) | mIoU | 78.55 | 77.90 |
| mmseg | metric | PyTorch | TVM |
| :---------------------------------------------------------------------------------------------------------------------------: | :----: | :-----: | :---: |
| [FCN](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-512x1024.py) | mIoU | 72.25 | 72.36 |
| [PSPNet](https://github.com/open-mmlab/mmsegmentation/blob/main/configs/pspnet/pspnet_r50-d8_4xb2-80k_cityscapes-512x1024.py) | mIoU | 78.55 | 77.90 |

14
docs/zh_cn/03-benchmark/quantization.md
View File

@ -20,17 +20,17 @@
### OCR 检测任务
| model | dataset | fp32 hmean | int8 hmean |
| :------------------------------------------------------------------------------------------------------------------------------: | :-------: | :--------: | :------------: |
| [PANet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/panet/panet_resnet18_fpem-ffm_600e_icdar2015.py) | ICDAR2015 | 0.795 | 0.792 @thr=0.9 |
| [TextSnake](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/textsnake/textsnake_resnet50_fpn-unet_1200e_ctw1500.py) | CTW1500 | 0.817 | 0.818 |
| model | dataset | fp32 hmean | int8 hmean |
| :-------------------------------------------------------------------------------------------------------------------------------: | :-------: | :--------: | :------------: |
| [PANet](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/panet/panet_resnet18_fpem-ffm_600e_icdar2015.py) | ICDAR2015 | 0.795 | 0.792 @thr=0.9 |
| [TextSnake](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/textsnake/textsnake_resnet50_fpn-unet_1200e_ctw1500.py) | CTW1500 | 0.817 | 0.818 |
备注：[mmocr](https://github.com/open-mmlab/mmocr) 使用 `shapely` 计算 IoU，实现方法会导致轻微的精度差异
### 姿态检测任务
| model | dataset | fp32 AP | int8 AP |
| :---------------------------------------------------------------------------------------------------------------------------------------------------: | :------: | :-----: | :-----: |
| [Hourglass](https://github.com/open-mmlab/mmpose/blob/1.x/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_hourglass52_8xb32-210e_coco-256x256.py) | COCO2017 | 0.717 | 0.713 |
| model | dataset | fp32 AP | int8 AP |
| :----------------------------------------------------------------------------------------------------------------------------------------------------: | :------: | :-----: | :-----: |
| [Hourglass](https://github.com/open-mmlab/mmpose/blob/main/configs/body_2d_keypoint/topdown_heatmap/coco/td-hm_hourglass52_8xb32-210e_coco-256x256.py) | COCO2017 | 0.717 | 0.713 |
备注：测试转换后的模型精度时，对于 mmpose 模型，在模型配置文件中 `flip_test` 需设置为 `False`。

172
docs/zh_cn/03-benchmark/supported_models.md
View File

@ -2,92 +2,92 @@
自测完成的 model-backend 组合：
| Model config | Codebase | TorchScript | OnnxRuntime | TensorRT | ncnn | PPLNN | OpenVINO | Ascend | RKNN |
| :------------------------------------------------------------------------------------------------------ | :--------------- | :---------: | :---------: | :------: | :--: | :---: | :------: | :----: | :--: |
| [RetinaNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/retinanet) | MMDetection | Y | Y | Y | Y | Y | Y | Y | Y |
| [Faster R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/faster_rcnn) | MMDetection | Y | Y | Y | Y | Y | Y | Y | N |
| [YOLOv3](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/yolo) | MMDetection | Y | Y | Y | Y | N | Y | Y | Y |
| [YOLOX](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/yolox) | MMDetection | Y | Y | Y | Y | N | Y | N | Y |
| [FCOS](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/fcos) | MMDetection | Y | Y | Y | Y | N | Y | N | N |
| [FSAF](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/fsaf) | MMDetection | Y | Y | Y | Y | Y | Y | N | Y |
| [Mask R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/mask_rcnn) | MMDetection | Y | Y | Y | N | N | Y | N | N |
| [SSD](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/ssd)[\*](#note) | MMDetection | Y | Y | Y | Y | N | Y | N | Y |
| [FoveaBox](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/foveabox) | MMDetection | Y | Y | N | N | N | Y | N | N |
| [ATSS](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/atss) | MMDetection | N | Y | Y | N | N | Y | N | N |
| [GFL](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/gfl) | MMDetection | N | Y | Y | N | ? | Y | N | N |
| [Cascade R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | MMDetection | N | Y | Y | N | Y | Y | N | N |
| [Cascade Mask R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | MMDetection | N | Y | Y | N | N | Y | N | N |
| [Swin Transformer](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/swin)[\*](#note) | MMDetection | N | Y | Y | N | N | N | N | N |
| [VFNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/vfnet) | MMDetection | N | N | N | N | N | Y | N | N |
| [RepPoints](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/reppoints) | MMDetection | N | N | Y | N | ? | Y | N | N |
| [DETR](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/detr) | MMDetection | N | Y | Y | N | ? | N | N | N |
| [CenterNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/centernet) | MMDetection | N | Y | Y | N | ? | N | N | N |
| [SOLO](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solo) | MMDetection | N | Y | N | N | N | Y | N | N |
| [SOLOv2](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solov2) | MMDetection | N | Y | N | N | N | Y | N | N |
| [ResNet](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnet) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [ResNeXt](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnext) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [SE-ResNet](https://github.com/open-mmlab/mmpretrain/tree/main/configs/seresnet) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [MobileNetV2](https://github.com/open-mmlab/mmpretrain/tree/main/configs/mobilenet_v2) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [ShuffleNetV1](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v1) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [ShuffleNetV2](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v2) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [VisionTransformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/vision_transformer) | MMPretrain | Y | Y | Y | Y | ? | Y | Y | N |
| [SwinTransformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/swin_transformer) | MMPretrain | Y | Y | Y | N | ? | N | ? | N |
| [MobileOne](https://github.com/open-mmlab/mmpretrain/tree/main/configs/mobileone) | MMPretrain | N | Y | Y | N | N | N | N | N |
| [FCN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fcn) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | Y |
| [PSPNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/pspnet)[\*static](#note) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | Y |
| [DeepLabV3](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/deeplabv3) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | N |
| [DeepLabV3+](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/deeplabv3plus) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | N |
| [Fast-SCNN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fastscnn)[\*static](#note) | MMSegmentation | Y | Y | Y | N | Y | Y | N | Y |
| [UNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/unet) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | Y |
| [ANN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/ann)[\*](#note) | MMSegmentation | Y | Y | Y | N | N | N | N | N |
| [APCNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/apcnet) | MMSegmentation | Y | Y | Y | Y | N | N | N | Y |
| [BiSeNetV1](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/bisenetv1) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [BiSeNetV2](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/bisenetv2) | MMSegmentation | Y | Y | Y | Y | N | Y | N | N |
| [CGNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/cgnet) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [DMNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/dmnet) | MMSegmentation | ? | Y | N | N | N | N | N | N |
| [DNLNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/dnlnet) | MMSegmentation | ? | Y | Y | Y | N | Y | N | N |
| [EMANet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/emanet) | MMSegmentation | Y | Y | Y | N | N | Y | N | N |
| [EncNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/encnet) | MMSegmentation | Y | Y | Y | N | N | Y | N | N |
| [ERFNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/erfnet) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [FastFCN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fastfcn) | MMSegmentation | Y | Y | Y | Y | N | Y | N | N |
| [GCNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/gcnet) | MMSegmentation | Y | Y | Y | N | N | N | N | N |
| [ICNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/icnet)[\*](#note) | MMSegmentation | Y | Y | Y | N | N | Y | N | N |
| [ISANet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/isanet)[\*static](#note) | MMSegmentation | N | Y | Y | N | N | Y | N | Y |
| [NonLocal Net](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/nonlocal_net) | MMSegmentation | ? | Y | Y | Y | N | Y | N | N |
| [OCRNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/ocrnet) | MMSegmentation | ? | Y | Y | Y | N | Y | N | Y |
| [PointRend](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/point_rend) | MMSegmentation | Y | Y | Y | N | N | Y | N | N |
| [Semantic FPN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/sem_fpn) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [STDC](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/stdc) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [UPerNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/upernet)[\*](#note) | MMSegmentation | ? | Y | Y | N | N | N | N | Y |
| [DANet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/danet) | MMSegmentation | ? | Y | Y | N | N | N | N | N |
| [Segmenter](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/segmenter) [\*static](#note) | MMSegmentation | Y | Y | Y | Y | N | Y | N | N |
| [SRCNN](https://github.com/open-mmlab/mmagic/tree/main/configs/srcnn) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [ESRGAN](https://github.com/open-mmlab/mmagic/tree/main/configs/esrgan) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [SRGAN](https://github.com/open-mmlab/mmagic/tree/main/configs/srgan_resnet) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [SRResNet](https://github.com/open-mmlab/mmagic/tree/main/configs/srgan_resnet) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [Real-ESRGAN](https://github.com/open-mmlab/mmagic/tree/main/configs/real_esrgan) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [EDSR](https://github.com/open-mmlab/mmagic/tree/main/configs/edsr) | MMagic | Y | Y | Y | Y | N | Y | N | N |
| [RDN](https://github.com/open-mmlab/mmagic/tree/main/configs/rdn) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [DBNet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/dbnet) | MMOCR | Y | Y | Y | Y | Y | Y | Y | N |
| [DBNetpp](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/dbnetpp) | MMOCR | Y | Y | Y | ? | ? | Y | ? | N |
| [PANet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/panet) | MMOCR | Y | Y | Y | Y | ? | Y | Y | N |
| [PSENet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/psenet) | MMOCR | Y | Y | Y | Y | ? | Y | Y | N |
| [TextSnake](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/textsnake) | MMOCR | Y | Y | Y | Y | ? | ? | ? | N |
| [MaskRCNN](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/maskrcnn) | MMOCR | Y | Y | Y | ? | ? | ? | ? | N |
| [CRNN](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/crnn) | MMOCR | Y | Y | Y | Y | Y | N | N | N |
| [SAR](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/sar) | MMOCR | N | Y | N | N | N | N | N | N |
| [SATRN](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/satrn) | MMOCR | Y | Y | Y | N | N | N | N | N |
| [ABINet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/abinet) | MMOCR | Y | Y | Y | N | N | N | N | N |
| [HRNet](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/backbones.html#hrnet-cvpr-2019) | MMPose | N | Y | Y | Y | N | Y | N | N |
| [MSPN](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/backbones.html#mspn-arxiv-2019) | MMPose | N | Y | Y | Y | N | Y | N | N |
| [LiteHRNet](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/backbones.html#litehrnet-cvpr-2021) | MMPose | N | Y | Y | N | N | Y | N | N |
| [Hourglass](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/backbones.html#hourglass-eccv-2016) | MMPose | N | Y | Y | Y | N | Y | N | N |
| [SimCC](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/algorithms.html#simcc-eccv-2022) | MMPose | N | Y | Y | Y | N | N | N | N |
| [PointPillars](https://github.com/open-mmlab/mmdetection3d/tree/dev-1.x/configs/pointpillars) | MMDetection3d | ? | Y | Y | N | N | Y | N | N |
| [CenterPoint (pillar)](https://github.com/open-mmlab/mmdetection3d/tree/dev-1.x/configs/centerpoint) | MMDetection3d | ? | Y | Y | N | N | Y | N | N |
| [RotatedRetinaNet](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/rotated_retinanet/README.md) | RotatedDetection | N | Y | Y | N | N | N | N | N |
| [Oriented RCNN](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/oriented_rcnn/README.md) | RotatedDetection | N | Y | Y | N | N | N | N | N |
| [Gliding Vertex](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/gliding_vertex/README.md) | RotatedDetection | N | N | Y | N | N | N | N | N |
| Model config | Codebase | TorchScript | OnnxRuntime | TensorRT | ncnn | PPLNN | OpenVINO | Ascend | RKNN |
| :------------------------------------------------------------------------------------------------------- | :--------------- | :---------: | :---------: | :------: | :--: | :---: | :------: | :----: | :--: |
| [RetinaNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/retinanet) | MMDetection | Y | Y | Y | Y | Y | Y | Y | Y |
| [Faster R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/faster_rcnn) | MMDetection | Y | Y | Y | Y | Y | Y | Y | N |
| [YOLOv3](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/yolo) | MMDetection | Y | Y | Y | Y | N | Y | Y | Y |
| [YOLOX](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/yolox) | MMDetection | Y | Y | Y | Y | N | Y | N | Y |
| [FCOS](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/fcos) | MMDetection | Y | Y | Y | Y | N | Y | N | N |
| [FSAF](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/fsaf) | MMDetection | Y | Y | Y | Y | Y | Y | N | Y |
| [Mask R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/mask_rcnn) | MMDetection | Y | Y | Y | N | N | Y | N | N |
| [SSD](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/ssd)[\*](#note) | MMDetection | Y | Y | Y | Y | N | Y | N | Y |
| [FoveaBox](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/foveabox) | MMDetection | Y | Y | N | N | N | Y | N | N |
| [ATSS](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/atss) | MMDetection | N | Y | Y | N | N | Y | N | N |
| [GFL](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/gfl) | MMDetection | N | Y | Y | N | ? | Y | N | N |
| [Cascade R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | MMDetection | N | Y | Y | N | Y | Y | N | N |
| [Cascade Mask R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | MMDetection | N | Y | Y | N | N | Y | N | N |
| [Swin Transformer](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/swin)[\*](#note) | MMDetection | N | Y | Y | N | N | N | N | N |
| [VFNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/vfnet) | MMDetection | N | N | N | N | N | Y | N | N |
| [RepPoints](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/reppoints) | MMDetection | N | N | Y | N | ? | Y | N | N |
| [DETR](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/detr) | MMDetection | N | Y | Y | N | ? | N | N | N |
| [CenterNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/centernet) | MMDetection | N | Y | Y | N | ? | N | N | N |
| [SOLO](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solo) | MMDetection | N | Y | N | N | N | Y | N | N |
| [SOLOv2](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solov2) | MMDetection | N | Y | N | N | N | Y | N | N |
| [ResNet](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnet) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [ResNeXt](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnext) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [SE-ResNet](https://github.com/open-mmlab/mmpretrain/tree/main/configs/seresnet) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [MobileNetV2](https://github.com/open-mmlab/mmpretrain/tree/main/configs/mobilenet_v2) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [ShuffleNetV1](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v1) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [ShuffleNetV2](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v2) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
| [VisionTransformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/vision_transformer) | MMPretrain | Y | Y | Y | Y | ? | Y | Y | N |
| [SwinTransformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/swin_transformer) | MMPretrain | Y | Y | Y | N | ? | N | ? | N |
| [MobileOne](https://github.com/open-mmlab/mmpretrain/tree/main/configs/mobileone) | MMPretrain | N | Y | Y | N | N | N | N | N |
| [FCN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fcn) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | Y |
| [PSPNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/pspnet)[\*static](#note) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | Y |
| [DeepLabV3](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | N |
| [DeepLabV3+](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3plus) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | N |
| [Fast-SCNN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fastscnn)[\*static](#note) | MMSegmentation | Y | Y | Y | N | Y | Y | N | Y |
| [UNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/unet) | MMSegmentation | Y | Y | Y | Y | Y | Y | Y | Y |
| [ANN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/ann)[\*](#note) | MMSegmentation | Y | Y | Y | N | N | N | N | N |
| [APCNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/apcnet) | MMSegmentation | Y | Y | Y | Y | N | N | N | Y |
| [BiSeNetV1](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/bisenetv1) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [BiSeNetV2](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/bisenetv2) | MMSegmentation | Y | Y | Y | Y | N | Y | N | N |
| [CGNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/cgnet) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [DMNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/dmnet) | MMSegmentation | ? | Y | N | N | N | N | N | N |
| [DNLNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/dnlnet) | MMSegmentation | ? | Y | Y | Y | N | Y | N | N |
| [EMANet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/emanet) | MMSegmentation | Y | Y | Y | N | N | Y | N | N |
| [EncNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/encnet) | MMSegmentation | Y | Y | Y | N | N | Y | N | N |
| [ERFNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/erfnet) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [FastFCN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fastfcn) | MMSegmentation | Y | Y | Y | Y | N | Y | N | N |
| [GCNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/gcnet) | MMSegmentation | Y | Y | Y | N | N | N | N | N |
| [ICNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/icnet)[\*](#note) | MMSegmentation | Y | Y | Y | N | N | Y | N | N |
| [ISANet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/isanet)[\*static](#note) | MMSegmentation | N | Y | Y | N | N | Y | N | Y |
| [NonLocal Net](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/nonlocal_net) | MMSegmentation | ? | Y | Y | Y | N | Y | N | N |
| [OCRNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/ocrnet) | MMSegmentation | ? | Y | Y | Y | N | Y | N | Y |
| [PointRend](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/point_rend) | MMSegmentation | Y | Y | Y | N | N | Y | N | N |
| [Semantic FPN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/sem_fpn) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [STDC](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/stdc) | MMSegmentation | Y | Y | Y | Y | N | Y | N | Y |
| [UPerNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/upernet)[\*](#note) | MMSegmentation | ? | Y | Y | N | N | N | N | Y |
| [DANet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/danet) | MMSegmentation | ? | Y | Y | N | N | N | N | N |
| [Segmenter](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/segmenter) [\*static](#note) | MMSegmentation | Y | Y | Y | Y | N | Y | N | N |
| [SRCNN](https://github.com/open-mmlab/mmagic/tree/main/configs/srcnn) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [ESRGAN](https://github.com/open-mmlab/mmagic/tree/main/configs/esrgan) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [SRGAN](https://github.com/open-mmlab/mmagic/tree/main/configs/srgan_resnet) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [SRResNet](https://github.com/open-mmlab/mmagic/tree/main/configs/srgan_resnet) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [Real-ESRGAN](https://github.com/open-mmlab/mmagic/tree/main/configs/real_esrgan) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [EDSR](https://github.com/open-mmlab/mmagic/tree/main/configs/edsr) | MMagic | Y | Y | Y | Y | N | Y | N | N |
| [RDN](https://github.com/open-mmlab/mmagic/tree/main/configs/rdn) | MMagic | Y | Y | Y | Y | Y | Y | N | N |
| [DBNet](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/dbnet) | MMOCR | Y | Y | Y | Y | Y | Y | Y | N |
| [DBNetpp](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/dbnetpp) | MMOCR | Y | Y | Y | ? | ? | Y | ? | N |
| [PANet](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/panet) | MMOCR | Y | Y | Y | Y | ? | Y | Y | N |
| [PSENet](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/psenet) | MMOCR | Y | Y | Y | Y | ? | Y | Y | N |
| [TextSnake](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/textsnake) | MMOCR | Y | Y | Y | Y | ? | ? | ? | N |
| [MaskRCNN](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/maskrcnn) | MMOCR | Y | Y | Y | ? | ? | ? | ? | N |
| [CRNN](https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/crnn) | MMOCR | Y | Y | Y | Y | Y | N | N | N |
| [SAR](https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/sar) | MMOCR | N | Y | N | N | N | N | N | N |
| [SATRN](https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/satrn) | MMOCR | Y | Y | Y | N | N | N | N | N |
| [ABINet](https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/abinet) | MMOCR | Y | Y | Y | N | N | N | N | N |
| [HRNet](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#hrnet-cvpr-2019) | MMPose | N | Y | Y | Y | N | Y | N | N |
| [MSPN](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#mspn-arxiv-2019) | MMPose | N | Y | Y | Y | N | Y | N | N |
| [LiteHRNet](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#litehrnet-cvpr-2021) | MMPose | N | Y | Y | N | N | Y | N | N |
| [Hourglass](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#hourglass-eccv-2016) | MMPose | N | Y | Y | Y | N | Y | N | N |
| [SimCC](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/algorithms.html#simcc-eccv-2022) | MMPose | N | Y | Y | Y | N | N | N | N |
| [PointPillars](https://github.com/open-mmlab/mmdetection3d/tree/main/configs/pointpillars) | MMDetection3d | ? | Y | Y | N | N | Y | N | N |
| [CenterPoint (pillar)](https://github.com/open-mmlab/mmdetection3d/tree/main/configs/centerpoint) | MMDetection3d | ? | Y | Y | N | N | Y | N | N |
| [RotatedRetinaNet](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/rotated_retinanet/README.md) | RotatedDetection | N | Y | Y | N | N | N | N | N |
| [Oriented RCNN](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/oriented_rcnn/README.md) | RotatedDetection | N | Y | Y | N | N | N | N | N |
| [Gliding Vertex](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/gliding_vertex/README.md) | RotatedDetection | N | N | Y | N | N | N | N | N |
## Note

10
docs/zh_cn/04-supported-codebases/mmdet3d.md
View File

@ -72,10 +72,10 @@ ls -lah centerpoint
## 模型支持列表
| model | dataset | onnxruntime | openvino | tensorrt\* |
| :---------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------: | :---------: | :------: | :--------: |
| [centerpoint](https://github.com/open-mmlab/mmdetection3d/blob/dev-1.x/configs/centerpoint/centerpoint_pillar02_second_secfpn_head-circlenms_8xb4-cyclic-20e_nus-3d.py) | nuScenes | ✔️ | ✔️ | ✔️ |
| [pointpillars](https://github.com/open-mmlab/mmdetection3d/blob/dev-1.x/configs/pointpillars/pointpillars_hv_secfpn_sbn-all_8xb4-2x_nus-3d.py) | nuScenes | ✔️ | ✔️ | ✔️ |
| [pointpillars](https://github.com/open-mmlab/mmdetection3d/blob/dev-1.x/configs/pointpillars/pointpillars_hv_secfpn_8xb6-160e_kitti-3d-3class.py) | KITTI | ✔️ | ✔️ | ✔️ |
| model | dataset | onnxruntime | openvino | tensorrt\* |
| :------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :------: | :---------: | :------: | :--------: |
| [centerpoint](https://github.com/open-mmlab/mmdetection3d/blob/main/configs/centerpoint/centerpoint_pillar02_second_secfpn_head-circlenms_8xb4-cyclic-20e_nus-3d.py) | nuScenes | ✔️ | ✔️ | ✔️ |
| [pointpillars](https://github.com/open-mmlab/mmdetection3d/blob/main/configs/pointpillars/pointpillars_hv_secfpn_sbn-all_8xb4-2x_nus-3d.py) | nuScenes | ✔️ | ✔️ | ✔️ |
| [pointpillars](https://github.com/open-mmlab/mmdetection3d/blob/main/configs/pointpillars/pointpillars_hv_secfpn_8xb6-160e_kitti-3d-3class.py) | KITTI | ✔️ | ✔️ | ✔️ |
- 考虑到 ScatterND、动态 shape 等已知问题，请确保 trt >= 8.4

26
docs/zh_cn/04-supported-codebases/mmocr.md
View File

@ -18,7 +18,7 @@
______________________________________________________________________
[MMOCR](https://github.com/open-mmlab/mmocr/tree/1.x)，又称 `mmocr`，是基于 PyTorch 和 mmdetection 的开源工具箱，专注于文本检测，文本识别以及相应的下游任务，如关键信息提取。 它是 [OpenMMLab](https://openmmlab.com/) 项目的一部分。
[MMOCR](https://github.com/open-mmlab/mmocr/tree/main)，又称 `mmocr`，是基于 PyTorch 和 mmdetection 的开源工具箱，专注于文本检测，文本识别以及相应的下游任务，如关键信息提取。 它是 [OpenMMLab](https://openmmlab.com/) 项目的一部分。
## 安装
@ -238,18 +238,18 @@ print(texts)
## 模型支持列表
| Model | Task | TorchScript | OnnxRuntime | TensorRT | ncnn | PPLNN | OpenVINO |
| :---------------------------------------------------------------------------------- | :--------------- | :---------: | :---------: | :------: | :--: | :---: | :------: |
| [DBNet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/dbnet) | text-detection | Y | Y | Y | Y | Y | Y |
| [DBNetpp](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/dbnetpp) | text-detection | N | Y | Y | ? | ? | Y |
| [PSENet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/psenet) | text-detection | Y | Y | Y | Y | N | Y |
| [PANet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/panet) | text-detection | Y | Y | Y | Y | N | Y |
| [TextSnake](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/textsnake) | text-detection | Y | Y | Y | ? | ? | ? |
| [MaskRCNN](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textdet/maskrcnn) | text-detection | Y | Y | Y | ? | ? | ? |
| [CRNN](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/crnn) | text-recognition | Y | Y | Y | Y | Y | N |
| [SAR](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/sar) | text-recognition | N | Y | Y | N | N | N |
| [SATRN](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/satrn) | text-recognition | Y | Y | Y | N | N | N |
| [ABINet](https://github.com/open-mmlab/mmocr/blob/1.x/configs/textrecog/abinet) | text-recognition | Y | Y | Y | ? | ? | ? |
| Model | Task | TorchScript | OnnxRuntime | TensorRT | ncnn | PPLNN | OpenVINO |
| :----------------------------------------------------------------------------------- | :--------------- | :---------: | :---------: | :------: | :--: | :---: | :------: |
| [DBNet](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/dbnet) | text-detection | Y | Y | Y | Y | Y | Y |
| [DBNetpp](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/dbnetpp) | text-detection | N | Y | Y | ? | ? | Y |
| [PSENet](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/psenet) | text-detection | Y | Y | Y | Y | N | Y |
| [PANet](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/panet) | text-detection | Y | Y | Y | Y | N | Y |
| [TextSnake](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/textsnake) | text-detection | Y | Y | Y | ? | ? | ? |
| [MaskRCNN](https://github.com/open-mmlab/mmocr/blob/main/configs/textdet/maskrcnn) | text-detection | Y | Y | Y | ? | ? | ? |
| [CRNN](https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/crnn) | text-recognition | Y | Y | Y | Y | Y | N |
| [SAR](https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/sar) | text-recognition | N | Y | Y | N | N | N |
| [SATRN](https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/satrn) | text-recognition | Y | Y | Y | N | N | N |
| [ABINet](https://github.com/open-mmlab/mmocr/blob/main/configs/textrecog/abinet) | text-recognition | Y | Y | Y | ? | ? | ? |
## 注意事项

20
docs/zh_cn/04-supported-codebases/mmpose.md
View File

@ -13,13 +13,13 @@
______________________________________________________________________
[MMPose](https://github.com/open-mmlab/mmpose/tree/1.x)，又称 `mmpose`，是一个基于 PyTorch 的姿态估计的开源工具箱，是 [OpenMMLab](https://openmmlab.com/) 项目的成员之一。
[MMPose](https://github.com/open-mmlab/mmpose/tree/main)，又称 `mmpose`，是一个基于 PyTorch 的姿态估计的开源工具箱，是 [OpenMMLab](https://openmmlab.com/) 项目的成员之一。
## 安装
### 安装 mmpose
请参考[官网安装指南](https://mmpose.readthedocs.io/en/1.x/installation.html#best-practices)。
请参考[官网安装指南](https://mmpose.readthedocs.io/en/latest/installation.html#best-practices)。
### 安装 mmdeploy
@ -156,11 +156,11 @@ task_processor.visualize(
## 模型支持列表
| Model | Task | ONNX Runtime | TensorRT | ncnn | PPLNN | OpenVINO |
| :----------------------------------------------------------------------------------------------------- | :------------ | :----------: | :------: | :--: | :---: | :------: |
| [HRNet](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/backbones.html#hrnet-cvpr-2019) | PoseDetection | Y | Y | Y | N | Y |
| [MSPN](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/backbones.html#mspn-arxiv-2019) | PoseDetection | Y | Y | Y | N | Y |
| [LiteHRNet](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/backbones.html#litehrnet-cvpr-2021) | PoseDetection | Y | Y | Y | N | Y |
| [Hourglass](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/algorithms.html#hourglass-eccv-2016) | PoseDetection | Y | Y | Y | N | Y |
| [SimCC](https://mmpose.readthedocs.io/en/1.x/model_zoo_papers/algorithms.html#simcc-eccv-2022) | PoseDetection | Y | Y | Y | N | N |
| [RTMPose](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose) | PoseDetection | Y | Y | Y | N | Y |
| Model | Task | ONNX Runtime | TensorRT | ncnn | PPLNN | OpenVINO |
| :-------------------------------------------------------------------------------------------------------- | :------------ | :----------: | :------: | :--: | :---: | :------: |
| [HRNet](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#hrnet-cvpr-2019) | PoseDetection | Y | Y | Y | N | Y |
| [MSPN](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#mspn-arxiv-2019) | PoseDetection | Y | Y | Y | N | Y |
| [LiteHRNet](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#litehrnet-cvpr-2021) | PoseDetection | Y | Y | Y | N | Y |
| [Hourglass](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/algorithms.html#hourglass-eccv-2016) | PoseDetection | Y | Y | Y | N | Y |
| [SimCC](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/algorithms.html#simcc-eccv-2022) | PoseDetection | Y | Y | Y | N | N |
| [RTMPose](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose) | PoseDetection | Y | Y | Y | N | Y |

2
docs/zh_cn/04-supported-codebases/mmrotate.md
View File

@ -19,7 +19,7 @@ ______________________________________________________________________
### 安装 mmrotate
请参考[官网安装指南](https://mmrotate.readthedocs.io/zh_CN/1.x/get_started.html)。
请参考[官网安装指南](https://mmrotate.readthedocs.io/zh_CN/latest/get_started.html)。
### 安装 mmdeploy

72
docs/zh_cn/04-supported-codebases/mmseg.md
View File

@ -14,7 +14,7 @@
______________________________________________________________________
[MMSegmentation](https://github.com/open-mmlab/mmsegmentation/tree/1.x) 又称`mmseg`，是一个基于 PyTorch 的开源对象分割工具箱。它是 [OpenMMLab](https://openmmlab.com/) 项目的一部分。
[MMSegmentation](https://github.com/open-mmlab/mmsegmentation/tree/main) 又称`mmseg`，是一个基于 PyTorch 的开源对象分割工具箱。它是 [OpenMMLab](https://openmmlab.com/) 项目的一部分。
## 安装
@ -192,41 +192,41 @@ cv2.imwrite('output_segmentation.png', img)
## 模型支持列表
| Model | TorchScript | OnnxRuntime | TensorRT | ncnn | PPLNN | OpenVino |
| :------------------------------------------------------------------------------------------------------- | :---------: | :---------: | :------: | :--: | :---: | :------: |
| [FCN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fcn) | Y | Y | Y | Y | Y | Y |
| [PSPNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/pspnet)[\*](#static_shape) | Y | Y | Y | Y | Y | Y |
| [DeepLabV3](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/deeplabv3) | Y | Y | Y | Y | Y | Y |
| [DeepLabV3+](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/deeplabv3plus) | Y | Y | Y | Y | Y | Y |
| [Fast-SCNN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fastscnn)[\*](#static_shape) | Y | Y | Y | N | Y | Y |
| [UNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/unet) | Y | Y | Y | Y | Y | Y |
| [ANN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/ann)[\*](#static_shape) | Y | Y | Y | N | N | N |
| [APCNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/apcnet) | Y | Y | Y | Y | N | N |
| [BiSeNetV1](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/bisenetv1) | Y | Y | Y | Y | N | Y |
| [BiSeNetV2](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/bisenetv2) | Y | Y | Y | Y | N | Y |
| [CGNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/cgnet) | Y | Y | Y | Y | N | Y |
| [DMNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/dmnet) | ? | Y | N | N | N | N |
| [DNLNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/dnlnet) | ? | Y | Y | Y | N | Y |
| [EMANet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/emanet) | Y | Y | Y | N | N | Y |
| [EncNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/encnet) | Y | Y | Y | N | N | Y |
| [ERFNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/erfnet) | Y | Y | Y | Y | N | Y |
| [FastFCN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/fastfcn) | Y | Y | Y | Y | N | Y |
| [GCNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/gcnet) | Y | Y | Y | N | N | N |
| [ICNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/icnet)[\*](#static_shape) | Y | Y | Y | N | N | Y |
| [ISANet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/isanet)[\*](#static_shape) | N | Y | Y | N | N | Y |
| [NonLocal Net](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/nonlocal_net) | ? | Y | Y | Y | N | Y |
| [OCRNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/ocrnet) | Y | Y | Y | Y | N | Y |
| [PointRend](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/point_rend)[\*](#static_shape) | Y | Y | Y | N | N | N |
| [Semantic FPN](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/sem_fpn) | Y | Y | Y | Y | N | Y |
| [STDC](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/stdc) | Y | Y | Y | Y | N | Y |
| [UPerNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/upernet)[\*](#static_shape) | N | Y | Y | N | N | N |
| [DANet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/danet) | ? | Y | Y | N | N | Y |
| [Segmenter](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/segmenter)[\*](#static_shape) | N | Y | Y | Y | N | Y |
| [SegFormer](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/segformer)[\*](#static_shape) | ? | Y | Y | N | N | Y |
| [SETR](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/setr) | ? | Y | N | N | N | Y |
| [CCNet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/ccnet) | ? | N | N | N | N | N |
| [PSANet](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/psanet) | ? | N | N | N | N | N |
| [DPT](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/dpt) | ? | N | N | N | N | N |
| Model | TorchScript | OnnxRuntime | TensorRT | ncnn | PPLNN | OpenVino |
| :-------------------------------------------------------------------------------------------------------- | :---------: | :---------: | :------: | :--: | :---: | :------: |
| [FCN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fcn) | Y | Y | Y | Y | Y | Y |
| [PSPNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/pspnet)[\*](#static_shape) | Y | Y | Y | Y | Y | Y |
| [DeepLabV3](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3) | Y | Y | Y | Y | Y | Y |
| [DeepLabV3+](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/deeplabv3plus) | Y | Y | Y | Y | Y | Y |
| [Fast-SCNN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fastscnn)[\*](#static_shape) | Y | Y | Y | N | Y | Y |
| [UNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/unet) | Y | Y | Y | Y | Y | Y |
| [ANN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/ann)[\*](#static_shape) | Y | Y | Y | N | N | N |
| [APCNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/apcnet) | Y | Y | Y | Y | N | N |
| [BiSeNetV1](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/bisenetv1) | Y | Y | Y | Y | N | Y |
| [BiSeNetV2](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/bisenetv2) | Y | Y | Y | Y | N | Y |
| [CGNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/cgnet) | Y | Y | Y | Y | N | Y |
| [DMNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/dmnet) | ? | Y | N | N | N | N |
| [DNLNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/dnlnet) | ? | Y | Y | Y | N | Y |
| [EMANet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/emanet) | Y | Y | Y | N | N | Y |
| [EncNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/encnet) | Y | Y | Y | N | N | Y |
| [ERFNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/erfnet) | Y | Y | Y | Y | N | Y |
| [FastFCN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/fastfcn) | Y | Y | Y | Y | N | Y |
| [GCNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/gcnet) | Y | Y | Y | N | N | N |
| [ICNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/icnet)[\*](#static_shape) | Y | Y | Y | N | N | Y |
| [ISANet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/isanet)[\*](#static_shape) | N | Y | Y | N | N | Y |
| [NonLocal Net](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/nonlocal_net) | ? | Y | Y | Y | N | Y |
| [OCRNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/ocrnet) | Y | Y | Y | Y | N | Y |
| [PointRend](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/point_rend)[\*](#static_shape) | Y | Y | Y | N | N | N |
| [Semantic FPN](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/sem_fpn) | Y | Y | Y | Y | N | Y |
| [STDC](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/stdc) | Y | Y | Y | Y | N | Y |
| [UPerNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/upernet)[\*](#static_shape) | N | Y | Y | N | N | N |
| [DANet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/danet) | ? | Y | Y | N | N | Y |
| [Segmenter](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/segmenter)[\*](#static_shape) | N | Y | Y | Y | N | Y |
| [SegFormer](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/segformer)[\*](#static_shape) | ? | Y | Y | N | N | Y |
| [SETR](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/setr) | ? | Y | N | N | N | Y |
| [CCNet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/ccnet) | ? | N | N | N | N | N |
| [PSANet](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/psanet) | ? | N | N | N | N | N |
| [DPT](https://github.com/open-mmlab/mmsegmentation/tree/main/configs/dpt) | ? | N | N | N | N | N |
## 注意事项

8
docs/zh_cn/tutorial/07_write_a_plugin.md
View File

@ -182,7 +182,9 @@ with torch.no_grad():
执行上述脚本，我们导出成功了一个ONNX模型 `srcnn.onnx`。用[netron](https://netron.app/)打开这个模型可视化如下：
![](../../../resources/tutorial/srcnn.svg)
<div align="center">
<img src="https://user-images.githubusercontent.com/28671653/241883709-e21d60d0-1b1d-4665-af14-9c1240484773.png"/>
</div>
直接将该模型转换成TensorRT模型也是不可行的，这是因为TensorRT还无法解析 `DynamicTRTResize` 节点。而想要解析该节点，我们必须为TensorRT添加c++代码，实现该插件。
@ -274,7 +276,9 @@ class DynamicTRTResizeCreator : public TRTPluginCreatorBase {
在这样一份头文件中，DynamicTRTResize类进行了如下的套娃继承：
![](../../../resources/tutorial/IPluginV2DynamicExt.svg)
<div align="center">
<img src="https://user-images.githubusercontent.com/28671653/241883700-0bee87a0-6d6a-478b-8a71-983a4e47b670.png"/>
</div>
从上面的图片和代码中我们发现，插件类`DynamicTRTResize`中我们定义了私有变量`mAlignCorners`，该变量表示是否`align corners`。此外只要实现构造析构函数和TensoRT中三个基类的方法即可。其中构造函数有二，分别用于创建插件和反序列化插件。而基类方法中：

4
resources/tutorial/IPluginV2DynamicExt.svg
View File

File diff suppressed because one or more lines are too long
Side by Side

Before

Width:  |  Height:  |  Size: 11 KiB

1
resources/tutorial/srcnn.svg
View File

File diff suppressed because one or more lines are too long
Side by Side

Before

Width:  |  Height:  |  Size: 15 KiB