This is an official pytorch implementation of Fast Non-Local Neural Networks with Spectral Residual Learning.

This repo uses Simple Baselines as the baseline method for Pose Estimation.

• Flip test is used.
• Person detector has person AP of 56.4 on COCO val2017 dataset.

The code is developed using python 3.6 on Ubuntu 16.04. NVIDIA GPUs are needed. The code is developed and tested using 8 NVIDIA P100 GPU cards. Other platforms or GPU cards are not fully tested.

1. Install pytorch >= v1.0.0 following official instruction. Note that if you use pytorch's version < v1.0.0, you should following the instruction at https://github.com/Microsoft/human-pose-estimation.pytorch to disable cudnn's implementations of BatchNorm layer. We encourage you to use higher pytorch's version(>=v1.0.0)

2. Clone this repo, and we'll call the directory that you cloned as ${POSE_ROOT}.

3. Install dependencies:

   pip install -r requirements.txt
   

4. Make libs:

   cd ${POSE_ROOT}/lib
   make
   

5. Install COCOAPI:

   # COCOAPI=/path/to/clone/cocoapi
   git clone https://github.com/cocodataset/cocoapi.git $COCOAPI
   cd $COCOAPI/PythonAPI
   # Install into global site-packages
   make install
   # Alternatively, if you do not have permissions or prefer
   # not to install the COCO API into global site-packages
   python3 setup.py install --user
   

   Note that instructions like # COCOAPI=/path/to/install/cocoapi indicate that you should pick a path where you'd like to have the software cloned and then set an environment variable (COCOAPI in this case) accordingly.

6. Init output(training model output directory) and log(tensorboard log directory) directory:

   mkdir output 
   mkdir log
   

   Your directory tree should look like this:

   ${POSE_ROOT}
   ├── data
   ├── experiments
   ├── lib
   ├── log
   ├── models
   ├── output
   ├── tools 
   ├── README.md
   └── requirements.txt
   

7. Download pytorch imagenet pretrained models from pytorch model zoo. Please download them under ${POSE_ROOT}/models/pytorch, and make them look like this:

   ${POSE_ROOT}
    `-- models
        `-- pytorch
            `-- imagenet
                |-- resnet50-19c8e357.pth
                |-- resnet101-5d3b4d8f.pth
                |-- resnet152-b121ed2d.pth
   

Please download from COCO download, 2017 Train/Val is needed for COCO keypoints training and validation. We also provide person detection result of COCO val2017 to reproduce our multi-person pose estimation results. Please download from OneDrive or GoogleDrive. Download and extract them under {POSE_ROOT}/data, and make them look like this:

${POSE_ROOT}
|-- data
`-- |-- coco
    `-- |-- annotations
        |   |-- person_keypoints_train2017.json
        |   `-- person_keypoints_val2017.json
        |-- person_detection_results
        |   |-- COCO_val2017_detections_AP_H_56_person.json
        `-- images
            |-- train2017
            |   |-- 000000000009.jpg
            |   |-- 000000000025.jpg
            |   |-- 000000000030.jpg
            |   |-- ... 
            `-- val2017
                |-- 000000000139.jpg
                |-- 000000000285.jpg
                |-- 000000000632.jpg
                |-- ... 

python pose_estimation/train.py \
    --cfg experiments/coco/resnet50/256x192_d256x3_adam_lr1e-3.yaml \
    --dec_nl 1 1 1 --nltype fft

python pose_estimation/valid.py \
    --cfg experiments/coco/resnet50/256x192_d256x3_adam_lr1e-3.yaml \
    --flip-test \
    --use-detect-bbox \
    --dec_nl 1 1 1 --nltype fft

If you use our code or models in your research, please cite with:

@inproceedings{chi2019SRL,
    author={Chi, Lu and Tian, Guiyu and Mu, Yadong and Xie, Lingxi and Tian, Qi},
    title={Fast Non-Local Neural Networks with Spectral Residual Learning},
    booktitle = {ACM International Conference on Multimedia (MM)},
    year = {2019}
}

• Simple Baselines for Human Pose Estimation and Tracking
• Compact Generalized Non-local Network
• CCNet: Criss-Cross Attention for Semantic Segmentation