This is the official pytorch implementation of our ICLR 2023 paper "Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation ".
We present ED-Pose, an end-to-end framework with Explicit box Detection for multi-person Pose estimation. ED-Pose re-considers this task as two explicit box detection processes with a unified representation and regression supervision.
In general, ED-Pose is conceptually simple without post-processing and dense heatmap supervision.
- For the first time, ED-Pose, as a fully end-to-end framework with a L1 regression loss, surpasses heatmap-based Top-down methods under the same backbone by 1.2 AP on COCO.
- ED-Pose achieves the state-of-the-art with 76.6 AP on CrowdPose without test-time augmentation.
2023/08/08
: 1. We support ED-Pose on the Human-Art dataset. 2. We upload the inference script for faster virtualization.
This repo contains further modifications including:
-
Integrated into detrex.
-
Integrated into Huggingface Spaces ๐ค using Gradio.
We have put our model checkpoints here.
Model | Backbone | Lr schd | mAP | AP50 | AP75 | APM | APL | Time (ms) | Download |
---|---|---|---|---|---|---|---|---|---|
ED-Pose | R-50 | 60e | 71.7 | 89.7 | 78.8 | 66.2 | 79.7 | 51 | Google Drive |
ED-Pose | Swin-L | 60e | 74.3 | 91.5 | 81.7 | 68.5 | 82.7 | 88 | Google Drive |
ED-Pose | Swin-L-5scale | 60e | 75.8 | 92.3 | 82.9 | 70.4 | 83.5 | 142 | Google Drive |
Model | Backbone | Lr schd | mAP | AP50 | AP75 | APE | APM | APH | Download |
---|---|---|---|---|---|---|---|---|---|
ED-Pose | R-50 | 80e | 69.9 | 88.6 | 75.8 | 77.7 | 70.6 | 60.9 | Google Drive |
ED-Pose | Swin-L | 80e | 73.1 | 90.5 | 79.8 | 80.5 | 73.8 | 63.8 | Google Drive |
ED-Pose | Swin-L-5scale | 80e | 76.6 | 92.4 | 83.3 | 83.0 | 77.3 | 68.3 | Google Drive |
Model | Backbone | Loss | mAP | AP50 | AP75 | APM | APL |
---|---|---|---|---|---|---|---|
DirectPose | R-50 | Reg | 62.2 | 86.4 | 68.2 | 56.7 | 69.8 |
DirectPose | R-101 | Reg | 63.3 | 86.7 | 69.4 | 57.8 | 71.2 |
FCPose | R-50 | Reg+HM | 64.3 | 87.3 | 71.0 | 61.6 | 70.5 |
FCPose | R-101 | Reg+HM | 65.6 | 87.9 | 72.6 | 62.1 | 72.3 |
InsPose | R-50 | Reg+HM | 65.4 | 88.9 | 71.7 | 60.2 | 72.7 |
InsPose | R-101 | Reg+HM | 66.3 | 89.2 | 73.0 | 61.2 | 73.9 |
PETR | R-50 | Reg+HM | 67.6 | 89.8 | 75.3 | 61.6 | 76.0 |
PETR | Swin-L | Reg+HM | 70.5 | 91.5 | 78.7 | 65.2 | 78.0 |
ED-Pose | R-50 | Reg | 69.8 | 90.2 | 77.2 | 64.3 | 77.4 |
ED-Pose | Swin-L | Reg | 72.7 | 92.3 | 80.9 | 67.6 | 80.0 |
Results on COCO test-dev dataset
Arch | Backbone | mAP | AP50 | AP75 | AR | AR50 | Download |
---|---|---|---|---|---|---|---|
ED-Pose | ResNet-50 | 0.723 | 0.861 | 0.774 | 0.808 | 0.921 | Google Drive |
Arch | Backbone | AP | AP50 | AP75 | AR | AR50 | Download |
---|---|---|---|---|---|---|---|
ED-Pose | ResNet-50 | 0.724 | 0.898 | 0.794 | 0.799 | 0.946 | Google Drive |
- Any test-time augmentations is not used for ED-Pose.
- We use the Object365 dataset to pretrain the human detection of ED-Pose under the Swin-L-5scale setting.
Installation
We use the DN-Deformable-DETR as our codebase. We test our models under python=3.7.3,pytorch=1.9.0,cuda=11.1
. Other versions might be available as well.
- Clone this repo
git clone https://github.com/IDEA-Research/ED-Pose.git
cd ED-Pose
- Install Pytorch and torchvision
Follow the instruction on https://pytorch.org/get-started/locally/.
# an example:
conda install -c pytorch pytorch torchvision
- Install other needed packages
pip install -r requirements.txt
- Compiling CUDA operators
cd models/edpose/ops
python setup.py build install
# unit test (should see all checking is True)
python test.py
cd ../../..
Data Preparation
For COCO data, please download from COCO download. The coco_dir should look like this:
|-- EDPose
`-- |-- coco_dir
`-- |-- annotations
| |-- person_keypoints_train2017.json
| `-- person_keypoints_val2017.json
`-- images
|-- train2017
| |-- 000000000009.jpg
| |-- 000000000025.jpg
| |-- 000000000030.jpg
| |-- ...
`-- val2017
|-- 000000000139.jpg
|-- 000000000285.jpg
|-- 000000000632.jpg
|-- ...
For CrowdPose data, please download from CrowdPose download, The crowdpose_dir should look like this:
|-- ED-Pose
`-- |-- crowdpose_dir
`-- |-- json
| |-- crowdpose_train.json
| |-- crowdpose_val.json
| |-- crowdpose_trainval.json (generated by util/crowdpose_concat_train_val.py)
| `-- crowdpose_test.json
`-- images
|-- 100000.jpg
|-- 100001.jpg
|-- 100002.jpg
|-- 100003.jpg
|-- 100004.jpg
|-- 100005.jpg
|-- ...
Single GPU
#For ResNet-50:
export EDPOSE_COCO_PATH=/path/to/your/cocodir
python main.py \
--output_dir "logs/coco_r50" \
-c config/edpose.cfg.py \
--options batch_size=4 epochs=60 lr_drop=55 num_body_points=17 backbone='resnet50' \
--dataset_file="coco"
#For Swin-L:
export EDPOSE_COCO_PATH=/path/to/your/cocodir
export pretrain_model_path=/path/to/your/swin_L_384_22k
python main.py \
--output_dir "logs/coco_swinl" \
-c config/edpose.cfg.py \
--options batch_size=4 epochs=60 lr_drop=55 num_body_points=17 backbone='swin_L_384_22k' \
--dataset_file="coco"
Distributed Run
#For ResNet-50:
export EDPOSE_COCO_PATH=/path/to/your/cocodir
python -m torch.distributed.launch --nproc_per_node=4 main.py \
--output_dir "logs/coco_r50" \
-c config/edpose.cfg.py \
--options batch_size=4 epochs=60 lr_drop=55 num_body_points=17 backbone='resnet50' \
--dataset_file="coco"
#For Swin-L:
export EDPOSE_COCO_PATH=/path/to/your/cocodir
export pretrain_model_path=/path/to/your/swin_L_384_22k
python -m torch.distributed.launch --nproc_per_node=4 main.py \
--output_dir "logs/coco_swinl" \
-c config/edpose.cfg.py \
--options batch_size=4 epochs=60 lr_drop=55 num_body_points=17 backbone='swin_L_384_22k' \
--dataset_file="coco"
Single GPU
#For ResNet-50:
export EDPOSE_CrowdPose_PATH=/path/to/your/crowdpose_dir
python main.py \
--output_dir "logs/crowdpose_r50" \
-c config/edpose.cfg.py \
--options batch_size=4 epochs=80 lr_drop=75 num_body_points=14 backbone='resnet50' \
--dataset_file="crowdpose"
#For Swin-L:
export EDPOSE_CrowdPose_PATH=/path/to/your/crowdpose_dir
export pretrain_model_path=/path/to/your/swin_L_384_22k
python main.py \
--output_dir "logs/crowdpose_swinl" \
-c config/edpose.cfg.py \
--options batch_size=4 epochs=80 lr_drop=75 num_body_points=14 backbone='swin_L_384_22k' \
--dataset_file="crowdpose"
Distributed Run
#For ResNet-50:
export EDPOSE_CrowdPose_PATH=/path/to/your/crowdpose_dir
python -m torch.distributed.launch --nproc_per_node=4 main.py \
--output_dir "logs/crowdpose_r50" \
-c config/edpose.cfg.py \
--options batch_size=4 epochs=80 lr_drop=75 num_body_points=14 backbone='resnet50' \
--dataset_file="crowdpose"
#For Swin-L:
export EDPOSE_CrowdPose_PATH=/path/to/your/crowdpose_dir
export pretrain_model_path=/path/to/your/swin_L_384_22k
python -m torch.distributed.launch --nproc_per_node=4 main.py \
--output_dir "logs/crowdpose_swinl" \
-c config/edpose.cfg.py \
--options batch_size=4 epochs=80 lr_drop=75 num_body_points=14 backbone='swin_L_384_22k' \
--dataset_file="crowdpose"
We have put the Swin-L model pretrained on ImageNet-22k here.
ResNet-50
export EDPOSE_COCO_PATH=/path/to/your/cocodir
python -m torch.distributed.launch --nproc_per_node=4 main.py \
--output_dir "logs/coco_r50" \
-c config/edpose.cfg.py \
--options batch_size=4 epochs=60 lr_drop=55 num_body_points=17 backbone='resnet50' \
--dataset_file="coco" \
--pretrain_model_path "./models/edpose_r50_coco.pth" \
--eval
Swin-L
export EDPOSE_COCO_PATH=/path/to/your/cocodir
export pretrain_model_path=/path/to/your/swin_L_384_22k
python -m torch.distributed.launch --nproc_per_node=4 main.py \
--output_dir "logs/coco_swinl" \
-c config/edpose.cfg.py \
--options batch_size=4 epochs=60 lr_drop=55 num_body_points=17 backbone='swin_L_384_22k' \
--dataset_file="coco" \
--pretrain_model_path "./models/edpose_swinl_coco.pth" \
--eval
Swin-L-5scale
export EDPOSE_COCO_PATH=/path/to/your/cocodir
export pretrain_model_path=/path/to/your/swin_L_384_22k
python -m torch.distributed.launch --nproc_per_node=4 main.py \
--output_dir "logs/coco_swinl" \
-c config/edpose.cfg.py \
--options batch_size=4 epochs=60 lr_drop=55 num_body_points=17 backbone='swin_L_384_22k' \
return_interm_indices=0,1,2,3 num_feature_levels=5 \
--dataset_file="coco" \
--pretrain_model_path "./models/edpose_swinl_5scale_coco.pth" \
--eval
ResNet-50
export EDPOSE_CrowdPose_PATH=/path/to/your/crowdpose_dir
python main.py \
--output_dir "logs/crowdpose_r50" \
-c config/edpose.cfg.py \
--options batch_size=4 epochs=80 lr_drop=75 num_body_points=14 backbone='resnet50' \
--dataset_file="crowdpose"\
--pretrain_model_path "./models/edpose_r50_crowdpose.pth" \
--eval
Swin-L
export EDPOSE_CrowdPose_PATH=/path/to/your/crowdpose_dir
export pretrain_model_path=/path/to/your/swin_L_384_22k
python main.py \
--output_dir "logs/crowdpose_swinl" \
-c config/edpose.cfg.py \
--options batch_size=4 epochs=80 lr_drop=75 num_body_points=14 backbone='swin_L_384_22k' \
--dataset_file="crowdpose" \
--pretrain_model_path "./models/edpose_swinl_crowdpose.pth" \
--eval
Swin-L-5scale
export EDPOSE_CrowdPose_PATH=/path/to/your/crowdpose_dir
export pretrain_model_path=/path/to/your/swin_L_384_22k
python -m torch.distributed.launch --nproc_per_node=4 main.py \
--output_dir "logs/crowdpose_swinl" \
-c config/edpose.cfg.py \
--options batch_size=4 epochs=80 lr_drop=75 num_body_points=14 backbone='swin_L_384_22k' \
return_interm_indices=0,1,2,3 num_feature_levels=5 \
-- dataset_file="crowdpose" \
--pretrain_model_path "./models/edpose_swinl_5scale_crowdpose.pth" \
--eval
ResNet-50
export EDPOSE_COCO_PATH=/path/to/your/cocodir
export Inference_Path=/path/to/your/inference_dir
python -m torch.distributed.launch --nproc_per_node=1 main.py \
--output_dir "logs/coco_r50" \
-c config/edpose.cfg.py \
--options batch_size=1 epochs=60 lr_drop=55 num_body_points=17 backbone='resnet50' \
--dataset_file="coco" \
--pretrain_model_path "./models/edpose_r50_coco.pth" \
--eval
Swin-L
export EDPOSE_COCO_PATH=/path/to/your/cocodir
export Inference_Path=/path/to/your/inference_dir
python -m torch.distributed.launch --nproc_per_node=1 main.py \
--output_dir "logs/coco_swinl" \
-c config/edpose.cfg.py \
--options batch_size=1 epochs=60 lr_drop=55 num_body_points=17 backbone='swin_L_384_22k' \
--dataset_file="coco" \
--pretrain_model_path "./models/edpose_swinl_coco.pth" \
--eval
Swin-L-5scale
export EDPOSE_COCO_PATH=/path/to/your/cocodir
export Inference_Path=/path/to/your/inference_dir
python -m torch.distributed.launch --nproc_per_node=1 main.py \
--output_dir "logs/coco_swinl" \
-c config/edpose.cfg.py \
--options batch_size=1 epochs=60 lr_drop=55 num_body_points=17 backbone='swin_L_384_22k' \
return_interm_indices=0,1,2,3 num_feature_levels=5 \
--dataset_file="coco" \
--pretrain_model_path "./models/edpose_swinl_5scale_coco.pth" \
--eval
@inproceedings{
yang2023explicit,
title={Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation},
author={Jie Yang and Ailing Zeng and Shilong Liu and Feng Li and Ruimao Zhang and Lei Zhang},
booktitle={International Conference on Learning Representations},
year={2023},
url={https://openreview.net/forum?id=s4WVupnJjmX}
}