add HRNet

HRNet/.gitignore

@@ -0,0 +1,95 @@
+# IntelliJ project files
+.idea
+*.iml
+out
+gen
+
+### Vim template
+[._]*.s[a-w][a-z]
+[._]s[a-w][a-z]
+*.un~
+Session.vim
+.netrwhist
+*~
+
+### IPythonNotebook template
+# Temporary data
+.ipynb_checkpoints/
+
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+#lib/
+#lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+*.ipynb
+*.params
+*.json
+.vscode/
+
+lib/pycocotools/_mask.c
+lib/nms/cpu_nms.c
+
+output/*
+models/*
+log/*
+data/*
+external/
+
+draws/
+plot/
+

HRNet/_config.yml

@@ -0,0 +1 @@
+theme: jekyll-theme-cayman

HRNet/coco_annotations.py

@@ -0,0 +1,107 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# 转化成适合的格式便于测试mAP准确率
+import os
+import json
+import numpy as np
+import ipdb;pdb=ipdb.set_trace
+import shutil
+from argparse import ArgumentParser
+
+np.random.seed(10101)
+def find_items(images, anns):
+    lists = []
+    for img in images:
+        image_id = img['id']
+        for ann in anns:
+            if image_id == ann['image_id']:
+                lists.append(ann)
+    return lists
+
+if __name__ == '__main__':
+    parser = ArgumentParser()
+    parser.add_argument("-p", "--ants_path", help="input file path", default="./data/coco/annotations/person_keypoints_val2017.json")  # 通过-p指定路径，标注文件名
+    args = parser.parse_args()
+    ants_path = args.ants_path
+    '''
+    with open("../shape/annotations/instances_train.json", "rt") as f:
+        data = json.loads(f.read())
+    print(data.keys())
+
+    '''
+    with open(ants_path, "rt") as f:
+        data = eval(f.read())
+    print('data.keys() = ', data.keys())
+    print('info = ', data['info'])
+    print('licenses num = ', len(data['licenses']))
+    # for i in range(len(data['licenses'])):
+    #     print('licenses = ', data['licenses'][i])
+    print('images num = ', len(data['images']))
+    print('images = ', data['images'][0])
+
+    print('annotations num = ', len(data['annotations']))
+    print('annotations = ', data['annotations'][0])
+
+    print('categories num = ', len(data['categories']))
+    print('categories = ', data['categories'][0])
+
+    # data = data['annotations']
+    # anns = []
+    # id_num = 0
+    # image_id_num = 0
+    # images = []
+    # for dd in data:
+    #     for d in dd[1:]:
+    #         x1, y1, x2, y2 = d[:4]
+    #         w, h = x2-x1, y2-y1
+    #         bbox = [x1, y1, w, h]
+    #         area = w*h
+    #         image_name = dd[0]
+    #         image_id = image_id_num
+    #         id = id_num
+    #         id_num += 1
+    #         item = {"id": id, "image_id": image_id, "category_id": 1, "iscrowd": 0, 'area': area, "bbox": bbox}
+    #         anns.append(item)
+    #     img = {"id": image_id, "file_name": image_name}
+    #     images.append(img)
+    #     image_id_num += 1
+
+    # np.random.shuffle(images)
+    # len_val = int(len(images)*0.1)
+
+    # val_imgs = images[: len_val]
+    # val_anns = find_items(val_imgs, anns)
+
+    # train_imgs = images[len_val : ]
+    # train_anns = find_items(train_imgs, anns)
+
+    # images_path = "images/"
+    # train_path = "../pig/train/"
+    # if not os.path.exists(train_path):
+    #     os.makedirs(train_path)
+    # val_path = "../pig/val/"
+    # if not os.path.exists(val_path):
+    #     os.makedirs(val_path)
+    # anns_path = "../pig/annotations/"
+    # if not os.path.exists(anns_path):
+    #     os.makedirs(anns_path)
+    # for img in val_imgs:
+    #     image_name = img['file_name']
+    #     file_image = images_path + image_name
+    #     shutil.copy(file_image, val_path)
+    # for img in train_imgs:
+    #     image_name = img['file_name']
+    #     file_image = images_path + image_name
+    #     shutil.copy(file_image, train_path)
+
+    # with open(anns_path + 'instances_val.json', 'wt') as f:
+    #     val_data = {"categories": [{"id": 1, "name": "pig", "supercategory": "None"}],
+    #                 "images": val_imgs,
+    #                 "annotations": val_anns}
+    #     f.write(json.dumps(val_data))
+
+    # with open(anns_path + 'instances_train.json', 'wt') as f:
+    #     train_data = {"categories": [{"id": 1, "name": "pig", "supercategory": "None"}],
+    #                   "images": train_imgs,
+    #                   "annotations": train_anns}
+    #     f.write(json.dumps(train_data))

HRNet/demo/.gitignore

@@ -0,0 +1,3 @@
+output
+models
+videos

HRNet/demo/Dockerfile

@@ -0,0 +1,112 @@
+FROM nvidia/cuda:10.2-cudnn7-devel-ubuntu16.04
+
+ENV OPENCV_VERSION="3.4.6"
+
+# Basic toolchain
+RUN apt-get update && apt-get install -y \
+        apt-utils \
+        build-essential \
+        git \
+        wget \
+        unzip \
+        yasm \
+        pkg-config \
+        libcurl4-openssl-dev \
+        zlib1g-dev \
+        htop \
+        cmake \
+        nano \
+        python3-pip \
+        python3-dev \
+        python3-tk \
+        libx264-dev \
+    && cd /usr/local/bin \
+    && ln -s /usr/bin/python3 python \
+    && pip3 install --upgrade pip \
+    && apt-get autoremove -y
+
+# Getting OpenCV dependencies available with apt
+RUN apt-get update && apt-get install -y \
+        libeigen3-dev \
+        libjpeg-dev \
+        libpng-dev \
+        libtiff-dev \
+        libjasper-dev \
+        libswscale-dev \
+        libavcodec-dev \
+        libavformat-dev && \
+    apt-get autoremove -y
+
+# Getting other dependencies
+RUN apt-get update && apt-get install -y \
+        cppcheck \
+        graphviz \
+        doxygen \
+        p7zip-full \
+        libdlib18 \
+        libdlib-dev && \
+    apt-get autoremove -y
+
+
+# Install OpenCV + OpenCV contrib (takes forever)
+RUN mkdir -p /tmp && \
+    cd /tmp && \
+    wget --no-check-certificate -O opencv.zip https://github.com/opencv/opencv/archive/${OPENCV_VERSION}.zip && \
+    wget --no-check-certificate -O opencv_contrib.zip https://github.com/opencv/opencv_contrib/archive/${OPENCV_VERSION}.zip && \
+    unzip opencv.zip && \
+    unzip opencv_contrib.zip && \
+    mkdir opencv-${OPENCV_VERSION}/build && \
+    cd opencv-${OPENCV_VERSION}/build && \
+    cmake -D CMAKE_BUILD_TYPE=RELEASE \
+        -D CMAKE_INSTALL_PREFIX=/usr/local \
+        -D WITH_CUDA=ON \
+        -D CUDA_FAST_MATH=1 \
+        -D WITH_CUBLAS=1 \
+        -D WITH_FFMPEG=ON \
+        -D WITH_OPENCL=ON \
+        -D WITH_V4L=ON \
+        -D WITH_OPENGL=ON \
+        -D OPENCV_EXTRA_MODULES_PATH=/tmp/opencv_contrib-${OPENCV_VERSION}/modules \
+        .. && \
+    make -j$(nproc) && \
+    make install && \
+    echo "/usr/local/lib" > /etc/ld.so.conf.d/opencv.conf && \
+    ldconfig && \
+    cd /tmp && \
+    rm -rf opencv-${OPENCV_VERSION} opencv.zip opencv_contrib-${OPENCV_VERSION} opencv_contrib.zip && \
+    cd /
+
+# Compile and install ffmpeg from source
+RUN git clone https://github.com/FFmpeg/FFmpeg /root/ffmpeg && \
+    cd /root/ffmpeg && \
+    ./configure --enable-gpl --enable-libx264 --enable-nonfree --disable-shared --extra-cflags=-I/usr/local/include && \
+    make -j8 && make install -j8
+
+# clone deep-high-resolution-net
+ARG POSE_ROOT=/pose_root
+RUN git clone https://github.com/leoxiaobin/deep-high-resolution-net.pytorch.git $POSE_ROOT
+WORKDIR $POSE_ROOT
+RUN mkdir output && mkdir log
+
+RUN pip3 install -r requirements.txt && \
+    pip3 install torch==1.1.0 \
+    torchvision==0.3.0 \
+    opencv-python \
+    pillow==6.2.1
+
+# build deep-high-resolution-net lib
+WORKDIR $POSE_ROOT/lib
+RUN make
+
+# install COCO API
+ARG COCOAPI=/cocoapi
+RUN git clone https://github.com/cocodataset/cocoapi.git $COCOAPI
+WORKDIR $COCOAPI/PythonAPI
+# Install into global site-packages
+RUN make install
+
+# download fastrrnn pretrained model for person detection
+RUN python -c "import torchvision; model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True); model.eval()"
+
+COPY inference.py $POSE_ROOT/tools
+COPY inference-config.yaml $POSE_ROOT/

HRNet/demo/README.md

@@ -0,0 +1,37 @@
+# Inference hrnet
+
+Inferencing the deep-high-resolution-net.pytoch without using Docker. 
+
+## Prep
+1. Download the researchers' pretrained pose estimator from [google drive](https://drive.google.com/drive/folders/1hOTihvbyIxsm5ygDpbUuJ7O_tzv4oXjC?usp=sharing) to this directory under `models/`
+2. Put the video file you'd like to infer on in this directory under `videos`
+3. build the docker container in this directory with `./build-docker.sh` (this can take time because it involves compiling opencv)
+4. update the `inference-config.yaml` file to reflect the number of GPUs you have available
+
+## Running the Model
+```
+python inference.py --cfg inference-config.yaml \
+    --videoFile ../../multi_people.mp4 \
+    --writeBoxFrames \
+    --outputDir output \
+    TEST.MODEL_FILE ../models/pytorch/pose_coco/pose_hrnet_w32_256x192.pth 
+
+```
+
+The above command will create a video under *output* directory and a lot of pose image under *output/pose* directory. 
+Even with usage of GPU (GTX1080 in my case), the person detection will take nearly **0.06 sec**, the person pose match will
+ take nearly **0.07 sec**. In total. inference time per frame will be **0.13 sec**, nearly 10fps. So if you prefer a real-time (fps >= 20) 
+ pose estimation then you should try other approach.
+
+## Result
+
+Some output image is as:
+
+![1 person](inference_1.jpg)
+Fig: 1 person inference
+
+![3 person](inference_3.jpg)
+Fig: 3 person inference
+
+![3 person](inference_5.jpg)
+Fig: 3 person inference

HRNet/demo/build-docker.sh

@@ -0,0 +1 @@
+docker build -t hrnet_demo_inference .