mirrors
/
EasyCV
mirror of https://github.com/alibaba/EasyCV.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
EasyCV/docs/source/model_zoo_det.md

50 lines
14 KiB
Markdown
Raw Normal View History

initial commit
2022-04-02 20:01:06 +08:00
# Detection Model Zoo
support DINO algo (#144) dino_4sc_r50_12e：48.71 dino_4sc_r50_24e：50.53 dino_4sc_r50_36e：50.69 dino_4sc_swinl_12e: 56.86 dino_4sc_swinl_36e: 58.04 dino_5sc_swinl_36e: 58.47
2022-08-31 15:18:11 +08:00
Inference default use V100 16G.
add github config path for yolox-pai (#166) * add github config path
2022-08-26 13:50:48 +08:00
## YOLOX-PAI
initial commit
2022-04-02 20:01:06 +08:00
Fix YOLOX-Edge problem and update yolox-pai turtorial (#182) * complete yolox introduction * fix env problem with nni2.6.1 * fix yolox-edge problem * add docker turtorial * add blade test * support old export yolox model Co-authored-by: wuziheng <zhoulou.wzh@alibaba-inc.com>
2022-09-06 17:11:12 +08:00
Pretrained on COCO2017 dataset. (The result has been optimized with PAI-Blade, and only computes the model inference time. To learn about end2end inference time, you can refer to [export.md](./tutorials/export.md).)
initial commit
2022-04-02 20:01:06 +08:00
add train memory (#178) * add train memory
2022-09-19 18:00:34 +08:00
| Algorithm | Config | Params | Speed<sup>V100<br/><sub>fp16 b32 </sub> | mAP<sup>val<br/><sub>0.5:0.95</sub> | AP<sup>val<br/><sub>50</sub> | Download |
| --------------------- | ------------------------------------------------------------ | ------ | --------------------------------------- | ----------------------------------- | ---------------------------- | ------------------------------------------------------------ |
| YOLOX-s | [yolox_s_8xb16_300e_coco](https://github.com/alibaba/EasyCV/tree/master/configs/detection/yolox/yolox_s_8xb16_300e_coco.py) | 9M | 0.68ms | 40.0 | 58.9 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox_s_bs16_lr002/epoch_300.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox_s_bs16_lr002/log.txt) |
| PAI-YOLOXs | [yoloxs_pai_8xb16_300e_coco](https://github.com/alibaba/EasyCV/tree/master/configs/detection/yolox/pai_yoloxs_8xb16_300e_coco.py) | 16M | 0.71ms | 41.4 | 60.0 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox-pai/model/pai_yoloxs.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox-pai/log/pai_yoloxs.json) |
| PAI-YOLOXs-ASFF | [yoloxs_pai_asff_8xb16_300e_coco](https://github.com/alibaba/EasyCV/tree/master/configs/detection/yolox/pai_yoloxs_asff_8xb16_300e_coco.py) | 21M | 0.87ms | 42.8 | 61.8 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox-pai/model/pai_yoloxs_asff.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox-pai/log/pai_yoloxs_asff.json) |
add github config path for yolox-pai (#166) * add github config path
2022-08-26 13:50:48 +08:00
| PAI-YOLOXs-ASFF-TOOD3 | [yoloxs_pai_asff_tood3_8xb16_300e_coco](https://github.com/alibaba/EasyCV/tree/master/configs/detection/yolox/pai_yoloxs_asff_tood3_8xb16_300e_coco.py) | 24M | 1.15ms | 43.9 | 62.1 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox-pai/model/pai_yoloxs_asff_tood3.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox-pai/log/pai_yoloxs_asff_tood3.json) |
add train memory (#178) * add train memory
2022-09-19 18:00:34 +08:00
| YOLOX-m | [yolox_m_8xb16_300e_coco](https://github.com/alibaba/EasyCV/tree/master/configs/detection/yolox/yolox_m_8xb16_300e_coco.py) | 25M | 1.52ms | 46.3 | 64.9 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox_m_bs16_lr002/epoch_300.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox_m_bs16_lr002/log.txt) |
| YOLOX-l | [yolox_l_8xb8_300e_coco](https://github.com/alibaba/EasyCV/tree/master/configs/detection/yolox/yolox_m_8xb8_300e_coco.py) | 54M | 2.47ms | 48.9 | 67.5 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox_l_bs8_lr001/epoch_290.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox_l_bs8_lr001/log.txt) |
| YOLOX-x | [yolox_x_8xb8_300e_coco](https://github.com/alibaba/EasyCV/tree/master/configs/detection/yolox/yolox_x_8xb8_300e_coco.py) | 99M | 4.74ms | 50.9 | 69.2 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox_x_bs8_lr001/epoch_290.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox_x_bs8_lr001/log.txt) |
| YOLOX-tiny | [yolox_tiny_8xb16_300e_coco](https://github.com/alibaba/EasyCV/tree/master/configs/detection/yolox/yolox_tiny_8xb16_300e_coco.py) | 5M | 0.28ms | 31.5 | 49.2 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox_tiny_bs16_lr002/epoch_300.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox_tiny_bs16_lr002/log.txt) |
| YOLOX-nano | [yolox_nano_8xb16_300e_coco](https://github.com/alibaba/EasyCV/tree/master/configs/detection/yolox/yolox_tiny_8xb16_300e_coco.py) | 2.2M | 0.19ms | 26.5 | 42.6 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox_nano_bs16_lr002/epoch_300.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/yolox/yolox_nano_bs16_lr002/log.txt) |
Support ViTDet algo (#35) * adapt mmlab modules * add vitdet * support conv aggregation * modify vitdet load pretrained * support fp16 * modify defaultformatbundle * modify aug * bugfix sampler * bugfix mmresize * bugfix fp16&nonetype * bugfix filterannotation * support dlc * bugfix dist * bugfix detsourcecoco * smodify mmdet_parse_losses * bugfix nan * bugfix eval * bugfix data=nonetype * modify resize_embed * support vitdet_conv * add vitdet_conv init_weight * add test_vitdet * uniform rand_another * uniform use fp16 method * add test_fp16 Co-authored-by: jiangnana.jnn <jiangnana.jnn@alibaba-inc.com>
2022-06-10 21:49:32 +08:00
## ViTDet
add train memory (#178) * add train memory
2022-09-19 18:00:34 +08:00
| Algorithm | Config | Params<br/>(backbone/total) | Train memory<br/>(GB) | inference time(V100)<br/>(ms/img) | bbox_mAP<sup>val<br/><sub>0.5:0.95</sub> | mask_mAP<sup>val<br/><sub>0.5:0.95</sub> | Download |
| ---------- | ------------------------------------------------------------ | ------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
| ViTDet_MaskRCNN | [vitdet_maskrcnn](https://github.com/alibaba/EasyCV/tree/master/configs/detection/vitdet/vitdet_mask_rcnn_100e.py) | 86M/111M | 13.3 (fp16) | 138ms | 50.65 | 45.41 | [model](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/vitdet/vit_base/epoch_100.pth) - [log](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/vitdet/vit_base/20220901_135827.log.json) |
refactor detection, support detr and dab-detr (#104) refactor detection, support detr and dab-detr
2022-07-11 14:52:49 +08:00
support fcos (#100) support fcos(38.57)
2022-07-12 18:07:02 +08:00
## FCOS
add train memory (#178) * add train memory
2022-09-19 18:00:34 +08:00
| Algorithm | Config | Params<br/>(backbone/total) | Train memory<br/>(GB) | inference time(V100)<br/>(ms/img) | mAP<sup>val<br/><sub>0.5:0.95</sub> | AP<sup>val<br/><sub>50</sub> | Download |
| ---------- | ------------------------------------------------------------ | ------------------------ | --------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
| FCOS-r50(caffe) | [fcos-r50](https://github.com/alibaba/EasyCV/tree/master/configs/detection/fcos/fcos_r50_caffe_1x_coco.py) | 23M/32M | 5.0 | 85.8ms | 38.58 | 57.18 | [model](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/fcos/epoch_12.pth) - [log](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/fcos/20220621_121315.log.json) |
| FCOS-r50(torch) | [fcos-r50](https://github.com/alibaba/EasyCV/tree/master/configs/detection/fcos/fcos_r50_torch_1x_coco.py) | 23M/32M | 4.0 (fp16) | 105.3ms | 38.88 | 58.01 | [model](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/fcos/fcos_epoch_12.pth) - [log](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/fcos/20220826_182628.log.json) |
add dn_detr algo (#119) support dn-detr-r50: 44.39 refactor set_criterion
2022-07-27 15:06:06 +08:00
refactor detection, support detr and dab-detr (#104) refactor detection, support detr and dab-detr
2022-07-11 14:52:49 +08:00
## DETR
add train memory (#178) * add train memory
2022-09-19 18:00:34 +08:00
| Algorithm | Config | Params<br/>(backbone/total) | Train memory<br/>(GB) | inference time(V100)<br/>(ms/img) | bbox_mAP<sup>val<br/><sub>0.5:0.95</sub> | AP<sup>val<br/><sub>50</sub> | Download |
| ---------- | ------------------------------------------------------------ | ------------------------ | --------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
| DETR-r50 | [detr-r50](https://github.com/alibaba/EasyCV/tree/master/configs/detection/detr/detr_r50_8x2_150e_coco.py) | 23M/41M | 8.5 | 48.5ms | 39.92 | 60.52 | [model](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/detr/epoch_150.pth) - [log](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/detr/20220609_101243.log.json) |
| DAB-DETR-r50 | [dab-detr-r50](https://github.com/alibaba/EasyCV/tree/master/configs/detection/dab_detr/dab_detr_r50_8x2_50e_coco.py) | 23M/43M | 2.6 | 58.5ms | 42.52 | 63.03 | [model](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/dab_detr/dab_detr_epoch_50.pth) - [log](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/dab_detr/20220610_122811.log.json) |
| DN-DETR-r50 | [dab-detr-r50](https://github.com/alibaba/EasyCV/tree/master/configs/detection/dab_detr/dn_detr_r50_8x2_50e_coco.py) | 23M/43M | 7.8 | 58.5ms | 44.39 | 64.66 | [model](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/dn_detr/dn_detr_epoch_50.pth) - [log](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/dn_detr/20220713_105127.log.json) |
support DINO algo (#144) dino_4sc_r50_12e：48.71 dino_4sc_r50_24e：50.53 dino_4sc_r50_36e：50.69 dino_4sc_swinl_12e: 56.86 dino_4sc_swinl_36e: 58.04 dino_5sc_swinl_36e: 58.47
2022-08-31 15:18:11 +08:00
## DINO
| Algorithm | Config | Params<br/>(backbone/total) | inference time(V100)<br/>(ms/img) | bbox_mAP<sup>val<br/><sub>0.5:0.95</sub> | AP<sup>val<br/><sub>50</sub> | Download | Comment |
| ---------- | ------------------------------------------------------------ | ------------------------ | --------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | --------------------------------------------- |
| DINO_4sc_r50_12e | [DINO_4sc_r50_12e](https://github.com/alibaba/EasyCV/tree/master/configs/detection/dino/dino_4sc_r50_12e_coco.py) | 23M/47M | 184ms | 48.71 | 66.27 | [model](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/dino/dino_4sc_r50_12e/epoch_12.pth) - [log](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/dino/dino_4sc_r50_12e/20220815_141403.log.json) |Inference use V100 32G|
| DINO_4sc_r50_36e | [DINO_4sc_r50_36e](https://github.com/alibaba/EasyCV/tree/master/configs/detection/dino/dino_4sc_r50_36e_coco.py) | 23M/47M | 184ms | 50.69 | 68.60 | [model](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/dino/dino_4sc_r50_36e/epoch_29.pth) - [log](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/dino/dino_4sc_r50_36e/20220817_101549.log.json) |Inference use V100 32G|
| DINO_4sc_swinl_12e | [DINO_4sc_swinl_12e](https://github.com/alibaba/EasyCV/tree/master/configs/detection/dino/dino_4sc_swinl_12e_coco.py) | 195M/217M | 155ms | 56.86 | 75.61 | [model](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/dino/dino_4sc_swinl_12e/epoch_12.pth) - [log](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/dino/dino_4sc_swinl_12e/20220815_211633.log.json) |Inference use V100 32G|
| DINO_4sc_swinl_36e | [DINO_4sc_swinl_36e](https://github.com/alibaba/EasyCV/tree/master/configs/detection/dino/dino_4sc_swinl_36e_coco.py) | 195M/217M | 155ms | 58.04 | 76.76 | [model](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/dino/dino_4sc_swinl_36e/epoch_34.pth) - [log](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/dino/dino_4sc_swinl_36e/20220817_101416.log.json) |Inference use V100 32G|
| DINO_5sc_swinl_36e | [DINO_5sc_swinl_36e](https://github.com/alibaba/EasyCV/tree/master/configs/detection/dino/dino_5sc_swinl_36e_coco.py) | 195M/217M | 235ms | 58.47 | 77.10 | [model](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/dino/dino_5sc_swinl_36e/epoch_35.pth) - [log](https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/detection/dino/dino_5sc_swinl_36e/20220820_215711.log.json) |Inference use V100 32G|