代码拉取完成，页面将自动刷新
AlphaPose is an accurate multi-person pose estimator, which is the first open-source system that achieves 70+ mAP (75 mAP) on COCO dataset and 80+ mAP (82.1 mAP) on MPII dataset. To match poses that correspond to the same person across frames, we also provide an efficient online pose tracker called Pose Flow. It is the first open-source online pose tracker that achieves both 60+ mAP (66.5 mAP) and 50+ MOTA (58.3 MOTA) on PoseTrack Challenge dataset.
# install libGL
yum install mesa-libGL
# install zlib
wget http://www.zlib.net/fossils/zlib-1.2.9.tar.gz
tar xvf zlib-1.2.9.tar.gz
cd zlib-1.2.9/
./configure && make install
cd ..
rm -rf zlib-1.2.9.tar.gz zlib-1.2.9/
# install requirements
pip3 install seaborn pandas pycocotools matplotlib
pip3 install easydict tensorboardX opencv-python
Go to visit COCO official website, then select the COCO dataset you want to download.
Take coco2017 dataset as an example, specify /path/to/coco2017 to your COCO path in later training process, the unzipped dataset path structure sholud look like:
coco2017
├── annotations
│ ├── instances_train2017.json
│ ├── instances_val2017.json
│ └── ...
├── train2017
│ ├── 000000000009.jpg
│ ├── 000000000025.jpg
│ └── ...
├── val2017
│ ├── 000000000139.jpg
│ ├── 000000000285.jpg
│ └── ...
├── train2017.txt
├── val2017.txt
└── ...
# create soft link to coco
mkdir -p /home/datasets/cv/
ln -s /path/to/coco2017 /home/datasets/cv/coco
#
bash ./scripts/trainval/train.sh ./configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml 1
| GPUs | FPS | ACC |
|---|---|---|
| BI-V100 x8 | 1.71s/it | acc: 0.8429 |
此处可能存在不合适展示的内容，页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容，可点击提交进行申诉，我们将尽快为您处理。