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_seg.md

44 lines
7.4 KiB
Markdown
Raw Normal View History

[feature] add segmentation modules (#71) * add segmentation module & add ResNetV1c & ResNetV1d & add benchmark
2022-05-31 20:19:17 +08:00
# Segmentation Model Zoo
## FCN
Pretrained on **Pascal VOC 2012 + Aug**.
add analyse tools (#133) * add analyse tools and model performance
2022-07-27 10:52:05 +08:00
| Algorithm | Config | Params<br/>(backbone/total) | inference time(V100)<br/>(ms/img) | mIoU | Download |
| ---------- | ------------------------------------------------------------ | ------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
| fcn_r50_d8 | [fcn_r50-d8_512x512_8xb4_60e_voc12aug](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/fcn/fcn_r50-d8_512x512_8xb4_60e_voc12aug.py) | 23M/49M | 166ms | 69.01 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/segmentation/fcn_r50/epoch_60.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/segmentation/fcn_r50/20220525_203606.log.json) |
add upernet algo (#118) * add upernet algo * fix import onnx bug
2022-07-12 11:14:09 +08:00
## UperNet
Pretrained on **Pascal VOC 2012 + Aug**.
add segformer algo * 将COCO_Stuff_164k数据集增加到了data_hub.md, prepared_data.md, 以及将其对应脚本加到了prepare_data文件夹下面 * 增加了segformer对应的predictor * 完善docs/source/model_zoo_seg.md中关于segformer的信息
2022-08-18 10:40:18 +08:00
add analyse tools (#133) * add analyse tools and model performance
2022-07-27 10:52:05 +08:00
| Algorithm | Config | Params<br/>(backbone/total) | inference time(V100)<br/>(ms/img) | mIoU | Download |
| ---------- | ------------------------------------------------------------ | ------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
| upernet_r50 | [upernet_r50_512x512_8xb4_60e_voc12aug](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/upernet/upernet_r50_512x512_8xb4_60e_voc12aug.py) | 23M/66M | 282.9ms | 76.59 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/segmentation/upernet_r50/epoch_60.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/segmentation/upernet_r50/20220706_114712.log.json) |
add mask2former algo (#115) add mask2former algo support panopitc pipeline add segment predictor
2022-08-08 18:17:01 +08:00
## Mask2former
### Instance Segmentation on COCO
| Algorithm | Config | box MAP | Mask mAP | Download |
| ---------- | ------------------------------------------------------------ | ------------------------ |----------|---------------------------------------------------------------------------- |
| mask2former_r50 | [mask2former_r50_8xb2_e50_instance](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/mask2former/mask2former_r50_8xb2_e50_instance.py) | 46.09 | 43.26 |[model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/segmentation/mask2former_r50_instance/epoch_50.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/segmentation/mask2former_r50_instance/20220620_113639.log.json) |
### Panoptic Segmentation on COCO
| Algorithm | Config | PQ | box MAP | Mask mAP | Download |
| ---------- | ---------- | ------------------------------------------------------------ | ------------------------ |----------|---------------------------------------------------------------------------- |
| mask2former_r50 | [mask2former_r50_8xb2_e50_panopatic](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/mask2former/mask2former_r50_8xb2_e50_panopatic.py) | 51.64 | 44.81 | 41.88 |[model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/segmentation/mask2former_r50_panoptic/epoch_50.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/modelzoo/segmentation/mask2former_r50_panoptic/20220629_170721.log.json) |
add segformer algo * 将COCO_Stuff_164k数据集增加到了data_hub.md, prepared_data.md, 以及将其对应脚本加到了prepare_data文件夹下面 * 增加了segformer对应的predictor * 完善docs/source/model_zoo_seg.md中关于segformer的信息
2022-08-18 10:40:18 +08:00
## SegFormer
Semantic segmentation models trained on **CoCo_stuff164k**.
| Algorithm | Config | Params<br/>(backbone/total) | inference time(V100)<br/>(ms/img) |mIoU | Download |
| ---------- | ------------------------------------------------------------ | ------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
| SegFormer_B0 | [segformer_b0_coco.py](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/segformer/segformer_b0_coco.py) | 3.3M/3.8M | 47.2ms | 34.79 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b0/SegmentationEvaluator_mIoU_best.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b0/20220810_102335.log.json) |
add segformer algo . 增加了segformer的b1, b2, b3, b4几个配置文件。 . 预训练模型，log文件等均已经更新 . 已经从master合并结果 Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/9931529
2022-08-30 19:15:15 +08:00
| SegFormer_B1 | [segformer_b1_coco.py](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/segformer/segformer_b1_coco.py) | 13.2M/13.7M | 46.8ms | 39.27 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b1/SegmentationEvaluator_mIoU_best.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b1/20220819_142214.log.json) |
| SegFormer_B2 | [segformer_b2_coco.py](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/segformer/segformer_b2_coco.py) | 24.2M/27.5M | 49.1ms | 44.01 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b2/SegmentationEvaluator_mIoU_best.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b2/20220822_100513.log.json) |
| SegFormer_B3 | [segformer_b3_coco.py](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/segformer/segformer_b3_coco.py) | 44.1M/47.4M | 52.3ms | 45.31 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b3/SegmentationEvaluator_mIoU_best.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b3/20220823_100744.log.json) |
| SegFormer_B4 | [segformer_b4_coco.py](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/segformer/segformer_b4_coco.py) | 60.8M/64.1M | 58.5ms | 46.00 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b4/SegmentationEvaluator_mIoU_best.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b4/20220824_102735.log.json) |
| SegFormer_B5 | [segformer_b5_coco.py](https://github.com/alibaba/EasyCV/tree/master/configs/segmentation/segformer/segformer_b5_coco.py) | 81.4M/85.7M | 99.2ms | 46.75 | [model](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b5/SegmentationEvaluator_mIoU_best.pth) - [log](http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/EasyCV/damo/modelzoo/segmentation/segformer/segformer_b5/20220812_144336.log.json) |