# Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose
This repository contains training code for the paper [Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose](https://arxiv.org/pdf/1811.12004.pdf). This work heavily optimizes the [OpenPose](https://github.com/CMU-Perceptual-Computing-Lab/openpose) approach to reach real-time inference on CPU with negliable accuracy drop. It detects a skeleton (which consists of keypoints and connections between them) to identify human poses for every person inside the image. The pose may contain up to 18 keypoints: ears, eyes, nose, neck, shoulders, elbows, wrists, hips, knees, and ankles. On COCO 2017 Keypoint Detection validation set this code achives 40% AP for the single scale inference (no flip or any post-processing done). The result can be reproduced using this repository. *This repo significantly overlaps with https://github.com/opencv/openvino_training_extensions, however contains just the necessary code for human pose estimation.*
<p align="center">
<img src="data/preview.jpg" />
</p>
:fire: Check out our [new work](https://github.com/Daniil-Osokin/gccpm-look-into-person-cvpr19.pytorch) on accurate (and still fast) single-person pose estimation, which ranked 10<sup>th</sup> on CVPR'19 [Look-Into-Person](http://47.100.21.47:9999/index.php) challenge.
:fire::fire: Check out our lightweight [3D pose estimation](https://github.com/Daniil-Osokin/lightweight-human-pose-estimation-3d-demo.pytorch), which is based on [Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB](https://arxiv.org/pdf/1712.03453.pdf) paper and this work.
## Table of Contents
* [Requirements](#requirements)
* [Prerequisites](#prerequisites)
* [Training](#training)
* [Validation](#validation)
* [Pre-trained model](#pre-trained-model)
* [C++ demo](#cpp-demo)
* [Python demo](#python-demo)
* [Citation](#citation)
### Other Implementations
* TensorFlow by [murdockhou](https://github.com/murdockhou/lightweight_openpose).
* OpenVINO by [Pavel Druzhkov](https://github.com/openvinotoolkit/open_model_zoo/pull/1718/).
## Requirements
* Ubuntu 16.04
* Python 3.6
* PyTorch 0.4.1 (should also work with 1.0, but not tested)
## Prerequisites
1. Download COCO 2017 dataset: [http://cocodataset.org/#download](http://cocodataset.org/#download) (train, val, annotations) and unpack it to `<COCO_HOME>` folder.
2. Install requirements `pip install -r requirements.txt`
## Training
Training consists of 3 steps (given AP values for full validation dataset):
* Training from MobileNet weights. Expected AP after this step is ~38%.
* Training from weights, obtained from previous step. Expected AP after this step is ~39%.
* Training from weights, obtained from previous step and increased number of refinement stages to 3 in network. Expected AP after this step is ~40% (for the network with 1 refinement stage, two next are discarded).
1. Download pre-trained MobileNet v1 weights `mobilenet_sgd_68.848.pth.tar` from: [https://github.com/marvis/pytorch-mobilenet](https://github.com/marvis/pytorch-mobilenet) (sgd option). If this doesn't work, download from [GoogleDrive](https://drive.google.com/file/d/18Ya27IAhILvBHqV_tDp0QjDFvsNNy-hv/view?usp=sharing).
2. Convert train annotations in internal format. Run `python scripts/prepare_train_labels.py --labels <COCO_HOME>/annotations/person_keypoints_train2017.json`. It will produce `prepared_train_annotation.pkl` with converted in internal format annotations.
[OPTIONAL] For fast validation it is recommended to make *subset* of validation dataset. Run `python scripts/make_val_subset.py --labels <COCO_HOME>/annotations/person_keypoints_val2017.json`. It will produce `val_subset.json` with annotations just for 250 random images (out of 5000).
3. To train from MobileNet weights, run `python train.py --train-images-folder <COCO_HOME>/train2017/ --prepared-train-labels prepared_train_annotation.pkl --val-labels val_subset.json --val-images-folder <COCO_HOME>/val2017/ --checkpoint-path <path_to>/mobilenet_sgd_68.848.pth.tar --from-mobilenet`
4. Next, to train from checkpoint from previous step, run `python train.py --train-images-folder <COCO_HOME>/train2017/ --prepared-train-labels prepared_train_annotation.pkl --val-labels val_subset.json --val-images-folder <COCO_HOME>/val2017/ --checkpoint-path <path_to>/checkpoint_iter_420000.pth --weights-only`
5. Finally, to train from checkpoint from previous step and 3 refinement stages in network, run `python train.py --train-images-folder <COCO_HOME>/train2017/ --prepared-train-labels prepared_train_annotation.pkl --val-labels val_subset.json --val-images-folder <COCO_HOME>/val2017/ --checkpoint-path <path_to>/checkpoint_iter_280000.pth --weights-only --num-refinement-stages 3`. We took checkpoint after 370000 iterations as the final one.
We did not perform the best checkpoint selection at any step, so similar result may be achieved after less number of iterations.
#### Known issue
We observe this error with maximum number of open files (`ulimit -n`) equals to 1024:
```
File "train.py", line 164, in <module>
args.log_after, args.val_labels, args.val_images_folder, args.val_output_name, args.checkpoint_after, args.val_after)
File "train.py", line 77, in train
for _, batch_data in enumerate(train_loader):
File "/<path>/python3.6/site-packages/torch/utils/data/dataloader.py", line 330, in __next__
idx, batch = self._get_batch()
File "/<path>/python3.6/site-packages/torch/utils/data/dataloader.py", line 309, in _get_batch
return self.data_queue.get()
File "/<path>/python3.6/multiprocessing/queues.py", line 337, in get
return _ForkingPickler.loads(res)
File "/<path>/python3.6/site-packages/torch/multiprocessing/reductions.py", line 151, in rebuild_storage_fd
fd = df.detach()
File "/<path>/python3.6/multiprocessing/resource_sharer.py", line 58, in detach
return reduction.recv_handle(conn)
File "/<path>/python3.6/multiprocessing/reduction.py", line 182, in recv_handle
return recvfds(s, 1)[0]
File "/<path>/python3.6/multiprocessing/reduction.py", line 161, in recvfds
len(ancdata))
RuntimeError: received 0 items of ancdata
```
To get rid of it, increase the limit to bigger number, e.g. 65536, run in the terminal: `ulimit -n 65536`
## Validation
1. Run `python val.py --labels <COCO_HOME>/annotations/person_keypoints_val2017.json --images-folder <COCO_HOME>/val2017 --checkpoint-path <CHECKPOINT>`
## Pre-trained model <a name="pre-trained-model"/>
The model expects normalized image (mean=[128, 128, 128], scale=[1/256, 1/256, 1/256]) in planar BGR format.
Pre-trained on COCO model is available at: https://download.01.org/opencv/openvino_training_extensions/models/human_pose_estimation/checkpoint_iter_370000.pth, it has 40% of AP on COCO validation set (38.6% of AP on the val *subset*).
#### Conversion to OpenVINO format
1. Convert PyTorch model to ONNX format: run script in terminal `python scripts/convert_to_onnx.py --checkpoint-path <CHECKPOINT>`. It produces `human-pose-estimation.onnx`.
2. Convert ONNX model to OpenVINO format with Model Optimizer: run in terminal `python <OpenVINO_INSTALL_DIR>/deployment_tools/model_optimizer/mo.py --input_model human-pose-estimation.onnx --input data --mean_values data[128.0,128.0,128.0] --scale_values data[256] --output stage_1_output_0_pafs,stage_1_output_1_heatmaps`. This produces model `human-pose-estimation.xml` and weights `human-pose-estimation.bin` in single-precision floating-point format (FP32).
## C++ Demo <a name="cpp-demo"/>
To run the demo download Intel® OpenVINO™ Toolkit [https://software.intel.com/en-us/openvino-toolkit/choose-download](https://software.intel.com/en-us/openvino-toolkit/choose-download), install it and [build the samples](https://software.intel.com/en-us/articles/OpenVINO-InferEngine) (*Inferring Your Model with the Inference Engine Samples* part). Then run `<SAMPLES_BIN_FOLDER>/human_po
没有合适的资源?快使用搜索试试~ 我知道了~
资源详情
资源评论
资源推荐
收起资源包目录
lightweight-human-pose-estimation.rar (39个子文件)
lightweight-human-pose-estimation
.gitignore 24B
requirements.txt 89B
data
shake_it_off.jpg 69KB
preview.jpg 106KB
datasets
transformations.py 10KB
__init__.py 0B
__pycache__
coco.cpython-37.pyc 6KB
__init__.cpython-37.pyc 174B
coco.py 7KB
models
__init__.py 0B
__pycache__
__init__.cpython-37.pyc 172B
with_mobilenet.cpython-37.pyc 4KB
with_mobilenet.py 5KB
LICENSE 11KB
checkpoint_iter_370000.pth 83.89MB
scripts
prepare_train_labels.py 6KB
convert_to_onnx.py 1KB
make_val_subset.py 2KB
demo1.py 7KB
README.md 8KB
TRAIN-ON-CUSTOM-DATASET.md 11KB
__pycache__
val.cpython-37.pyc 6KB
demo.py 9KB
val.py 7KB
modules
__init__.py 0B
load_state.py 1KB
keypoints.py 8KB
get_parameters.py 843B
conv.py 1KB
__pycache__
pose.cpython-37.pyc 4KB
keypoints.cpython-37.pyc 5KB
one_euro_filter.cpython-37.pyc 2KB
conv.cpython-37.pyc 1KB
__init__.cpython-37.pyc 173B
load_state.cpython-37.pyc 1KB
loss.py 146B
one_euro_filter.py 1KB
pose.py 5KB
train.py 9KB
共 39 条
- 1
一只计算机幻觉划水员
- 粉丝: 0
- 资源: 7
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论0