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

[Docs] Update mmcls pplnn benchmark (#316) 

* Update mmcls pplnn benchmark

* Update supported model list
pull/1/head
Yifan Zhou 2021-12-22 10:43:39 +08:00 committed by GitHub
parent e10a1b7c9e
commit 543777fe27
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 47 additions and 47 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
docs/en/benchmark.md
View File

@ -557,7 +557,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](doc
<td class="tg-c3ow">77.74</td>
<td class="tg-c3ow">77.75</td>
<td class="tg-c3ow">77.63</td>
<td class="tg-c3ow">?</td>
<td class="tg-c3ow">77.73</td>
<td class="tg-lboi" rowspan="2">$MMCLS_DIR/configs/resnext/resnext50_32x4d_b32x8_imagenet.py</td>
</tr>
<tr>
@ -567,7 +567,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](doc
<td class="tg-c3ow">93.84</td>
<td class="tg-c3ow">93.83</td>
<td class="tg-c3ow">93.72</td>
<td class="tg-c3ow">?</td>
<td class="tg-c3ow">93.84</td>
</tr>
<tr>
<td class="tg-9wq8" rowspan="2">ShuffleNetV1 1.0x</td>
@ -578,7 +578,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](doc
<td class="tg-c3ow">68.13</td>
<td class="tg-c3ow">68.13</td>
<td class="tg-c3ow">67.71</td>
<td class="tg-c3ow">?</td>
<td class="tg-c3ow">68.11</td>
<td class="tg-lboi" rowspan="2">$MMCLS_DIR/configs/shufflenet_v1/shufflenet_v1_1x_b64x16_linearlr_bn_nowd_imagenet.py</td>
</tr>
<tr>
@ -588,7 +588,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](doc
<td class="tg-c3ow">87.81</td>
<td class="tg-c3ow">87.81</td>
<td class="tg-c3ow">87.58</td>
<td class="tg-c3ow">?</td>
<td class="tg-c3ow">87.80</td>
</tr>
</tr>
<tr>
@ -600,7 +600,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](doc
<td class="tg-c3ow">69.55</td>
<td class="tg-c3ow">69.54</td>
<td class="tg-c3ow">69.10</td>
<td class="tg-c3ow">?</td>
<td class="tg-c3ow">69.54</td>
<td class="tg-lboi" rowspan="2">$MMCLS_DIR/configs/shufflenet_v2/shufflenet_v2_1x_b64x16_linearlr_bn_nowd_imagenet.py</td>
</tr>
<tr>
@ -610,7 +610,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](doc
<td class="tg-c3ow">88.92</td>
<td class="tg-c3ow">88.91</td>
<td class="tg-c3ow">88.58</td>
<td class="tg-c3ow">?</td>
<td class="tg-c3ow">88.92</td>
</tr>
</tr>
</tr>
@ -623,8 +623,8 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](doc
<td class="tg-c3ow">71.86</td>
<td class="tg-c3ow">71.87</td>
<td class="tg-c3ow">70.91</td>
<td class="tg-c3ow">?</td>
<td class="tg-lboi" rowspan="2">$MMEDIT_DIR/configs/restorers/real_esrgan/realesrnet_c64b23g32_12x4_lr2e-4_1000k_df2k_ost.py</td>
<td class="tg-c3ow">71.84</td>
<td class="tg-lboi" rowspan="2">$MMCLS_DIR/configs/mobilenet_v2/mobilenet_v2_b32x8_imagenet.py</td>
</tr>
<tr>
<td class="tg-0pky">top-5</td>
@ -633,7 +633,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](doc
<td class="tg-c3ow">90.42</td>
<td class="tg-c3ow">90.40</td>
<td class="tg-c3ow">89.85</td>
<td class="tg-c3ow">?</td>
<td class="tg-c3ow">90.41</td>
</tr>
</tbody>
</table>

62
docs/en/tutorials/how_to_convert_model.md
View File

@ -84,38 +84,38 @@ You can try to evaluate model, referring to [how_to_evaluate_a_model](./how_to_e
### List of supported models exportable to other backends
The table below lists the models that are guaranteed to be exportable to other backend.
The table below lists the models that are guaranteed to be exportable to other backends.
| Model | codebase | OnnxRuntime | TensorRT | NCNN | PPLNN | OpenVINO | model config file(example) |
|--------------------|------------------|:-----------:|:--------:|:----:|:-----:|:--------:|:--------------------------------------------------------------------------------------|
| RetinaNet | MMDetection | Y | Y | Y | Y | Y | $MMDET_DIR/configs/retinanet/retinanet_r50_fpn_1x_coco.py |
| Faster R-CNN | MMDetection | Y | Y | Y | Y | Y | $MMDET_DIR/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py |
| YOLOv3 | MMDetection | Y | Y | Y | Y | Y | $MMDET_DIR/configs/yolo/yolov3_d53_mstrain-608_273e_coco.py |
| YOLOX | MMDetection | Y | Y | ? | ? | Y | $MMDET_DIR/configs/yolox/yolox_tiny_8x8_300e_coco.py |
| FCOS | MMDetection | Y | Y | Y | N | Y | $MMDET_DIR/configs/fcos/fcos_r50_caffe_fpn_gn-head_4x4_1x_coco. |
| FSAF | MMDetection | Y | Y | Y | Y | Y | $MMDET_DIR/configs/fsaf/fsaf_r50_fpn_1x_coco.py |
| Mask R-CNN | MMDetection | Y | Y | N | Y | Y | $MMDET_DIR/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py |
| SSD | MMDetection | Y | Y | Y | Y | Y | $MMDET_DIR/configs/ssd/ssd300_coco.py |
| FoveaBox | MMDetection | Y | ? | ? | ? | Y | $MMDET_DIR/configs/foveabox/fovea_r50_fpn_4x4_1x_coco.py |
| ATSS | MMDetection | Y | Y | ? | ? | Y | $MMDET_DIR/configs/atss/atss_r50_fpn_1x_coco.py |
| Cascade R-CNN | MMDetection | Y | ? | ? | Y | Y | $MMDET_DIR/configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.py |
| Cascade Mask R-CNN | MMDetection | Y | ? | ? | Y | Y | $MMDET_DIR/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.py |
| VFNet | MMDetection | N | ? | ? | ? | Y | $MMDET_DIR/configs/vfnet/vfnet_r50_fpn_1x_coco.py |
| ResNet | MMClassification | Y | Y | Y | Y | N | $MMCLS_DIR/configs/resnet/resnet18_b32x8_imagenet.py |
| ResNeXt | MMClassification | Y | Y | Y | Y | N | $MMCLS_DIR/configs/resnext/resnext50_32x4d_b32x8_imagenet.py |
| SE-ResNet | MMClassification | Y | Y | Y | Y | N | $MMCLS_DIR/configs/seresnet/seresnet50_b32x8_imagenet.py |
| MobileNetV2 | MMClassification | Y | Y | Y | Y | N | $MMCLS_DIR/configs/mobilenet_v2/mobilenet_v2_b32x8_imagenet.py |
| ShuffleNetV1 | MMClassification | Y | Y | Y | Y | N | $MMCLS_DIR/configs/shufflenet_v1/shufflenet_v1_1x_b64x16_linearlr_bn_nowd_imagenet.py |
| ShuffleNetV2 | MMClassification | Y | Y | Y | Y | N | $MMCLS_DIR/configs/shufflenet_v2/shufflenet_v2_1x_b64x16_linearlr_bn_nowd_imagenet.py |
| FCN | MMSegmentation | Y | Y | Y | Y | Y | $MMSEG_DIR/configs/fcn/fcn_r50-d8_512x1024_40k_cityscapes.py |
| PSPNet | MMSegmentation | Y | Y | N | Y | Y | $MMSEG_DIR/configs/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes.py |
| DeepLabV3 | MMSegmentation | Y | Y | Y | Y | Y | $MMSEG_DIR/configs/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes.py |
| DeepLabV3+ | MMSegmentation | Y | Y | Y | Y | Y | $MMSEG_DIR/configs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes.py |
| Fast-SCNN | MMSegmentation | Y | Y | N | Y | Y | ${MMSEG_DIR}/configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py |
| SRCNN | MMEditing | Y | Y | N | Y | N | $MMSEG_DIR/configs/restorers/srcnn/srcnn_x4k915_g1_1000k_div2k.py |
| ESRGAN | MMEditing | Y | Y | N | Y | N | $MMSEG_DIR/configs/restorers/esrgan/esrgan_psnr_x4c64b23g32_g1_1000k_div2k.py |
| DBNet | MMOCR | Y | Y | Y | Y | Y | $MMOCR_DIR/configs/textdet/dbnet/dbnet_r18_fpnc_1200e_icdar2015.py |
| CRNN | MMOCR | Y | Y | Y | Y | N | $MMOCR_DIR/configs/textrecog/crnn/crnn_academic_dataset.py |
| Model | codebase | OnnxRuntime | TensorRT | NCNN | PPLNN | OpenVINO | model config file(example) |
| ------------------ | ---------------- | :---------: | :------: | :---: | :---: | :------: | :------------------------------------------------------------------------------------ |
| RetinaNet | MMDetection | Y | Y | Y | Y | Y | $MMDET_DIR/configs/retinanet/retinanet_r50_fpn_1x_coco.py |
| Faster R-CNN | MMDetection | Y | Y | Y | Y | Y | $MMDET_DIR/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py |
| YOLOv3 | MMDetection | Y | Y | Y | Y | Y | $MMDET_DIR/configs/yolo/yolov3_d53_mstrain-608_273e_coco.py |
| YOLOX | MMDetection | Y | Y | ? | ? | Y | $MMDET_DIR/configs/yolox/yolox_tiny_8x8_300e_coco.py |
| FCOS | MMDetection | Y | Y | Y | N | Y | $MMDET_DIR/configs/fcos/fcos_r50_caffe_fpn_gn-head_4x4_1x_coco. |
| FSAF | MMDetection | Y | Y | Y | Y | Y | $MMDET_DIR/configs/fsaf/fsaf_r50_fpn_1x_coco.py |
| Mask R-CNN | MMDetection | Y | Y | N | Y | Y | $MMDET_DIR/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py |
| SSD | MMDetection | Y | Y | Y | Y | Y | $MMDET_DIR/configs/ssd/ssd300_coco.py |
| FoveaBox | MMDetection | Y | ? | ? | ? | Y | $MMDET_DIR/configs/foveabox/fovea_r50_fpn_4x4_1x_coco.py |
| ATSS | MMDetection | Y | Y | ? | ? | Y | $MMDET_DIR/configs/atss/atss_r50_fpn_1x_coco.py |
| Cascade R-CNN | MMDetection | Y | ? | ? | Y | Y | $MMDET_DIR/configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.py |
| Cascade Mask R-CNN | MMDetection | Y | ? | ? | Y | Y | $MMDET_DIR/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.py |
| VFNet | MMDetection | N | ? | ? | ? | Y | $MMDET_DIR/configs/vfnet/vfnet_r50_fpn_1x_coco.py |
| ResNet | MMClassification | Y | Y | Y | Y | Y | $MMCLS_DIR/configs/resnet/resnet18_b32x8_imagenet.py |
| ResNeXt | MMClassification | Y | Y | Y | Y | Y | $MMCLS_DIR/configs/resnext/resnext50_32x4d_b32x8_imagenet.py |
| SE-ResNet | MMClassification | Y | Y | Y | Y | Y | $MMCLS_DIR/configs/seresnet/seresnet50_b32x8_imagenet.py |
| MobileNetV2 | MMClassification | Y | Y | Y | Y | Y | $MMCLS_DIR/configs/mobilenet_v2/mobilenet_v2_b32x8_imagenet.py |
| ShuffleNetV1 | MMClassification | Y | Y | Y | Y | Y | $MMCLS_DIR/configs/shufflenet_v1/shufflenet_v1_1x_b64x16_linearlr_bn_nowd_imagenet.py |
| ShuffleNetV2 | MMClassification | Y | Y | Y | Y | Y | $MMCLS_DIR/configs/shufflenet_v2/shufflenet_v2_1x_b64x16_linearlr_bn_nowd_imagenet.py |
| FCN | MMSegmentation | Y | Y | Y | Y | Y | $MMSEG_DIR/configs/fcn/fcn_r50-d8_512x1024_40k_cityscapes.py |
| PSPNet | MMSegmentation | Y | Y | N | Y | Y | $MMSEG_DIR/configs/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes.py |
| DeepLabV3 | MMSegmentation | Y | Y | Y | Y | Y | $MMSEG_DIR/configs/deeplabv3/deeplabv3_r50-d8_512x1024_40k_cityscapes.py |
| DeepLabV3+ | MMSegmentation | Y | Y | Y | Y | Y | $MMSEG_DIR/configs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_40k_cityscapes.py |
| Fast-SCNN | MMSegmentation | Y | Y | N | Y | Y | ${MMSEG_DIR}/configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py |
| SRCNN | MMEditing | Y | Y | Y | Y | Y | $MMSEG_DIR/configs/restorers/srcnn/srcnn_x4k915_g1_1000k_div2k.py |
| ESRGAN | MMEditing | Y | Y | Y | Y | Y | $MMSEG_DIR/configs/restorers/esrgan/esrgan_psnr_x4c64b23g32_g1_1000k_div2k.py |
| DBNet | MMOCR | Y | Y | Y | Y | Y | $MMOCR_DIR/configs/textdet/dbnet/dbnet_r18_fpnc_1200e_icdar2015.py |
| CRNN | MMOCR | Y | Y | Y | Y | N | $MMOCR_DIR/configs/textrecog/crnn/crnn_academic_dataset.py |
### Reminders

14
mmdeploy/codebase/mmcls/deploy/classification.py
View File

@ -230,7 +230,7 @@ class Classification(BaseTask):
if metrics:
results = dataset.evaluate(outputs, metrics, metric_options)
for k, v in results.items():
logging.info(f'\n{k} : {v:.2f}')
print(f'\n{k} : {v:.2f}')
else:
warnings.warn('Evaluation metrics are not specified.')
scores = np.vstack(outputs)
@ -243,13 +243,13 @@ class Classification(BaseTask):
'pred_class': pred_class
}
if not out:
logging.info('\nthe predicted result for the first element is '
f'pred_score = {pred_score[0]:.2f}, '
f'pred_label = {pred_label[0]} '
f'and pred_class = {pred_class[0]}. '
'Specify --out to save all results to files.')
print('\nthe predicted result for the first element is '
f'pred_score = {pred_score[0]:.2f}, '
f'pred_label = {pred_label[0]} '
f'and pred_class = {pred_class[0]}. '
'Specify --out to save all results to files.')
if out:
logging.info(f'\nwriting results to {out}')
print(f'\nwriting results to {out}')
mmcv.dump(results, out)
def get_preprocess(self) -> Dict: