Hot 3D 人体姿态估计 HPE Demo复现过程

视频讲解

Hot 3D 人体姿态估计 HPE Demo复现过程

• 标题：Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation
• 论文地址：https://arxiv.org/abs/2311.12028
• 代码地址：https://github.com/NationalGAILab/HoT

使用conda进行环境准备

conda create -n hot python=3.9
conda activate hot
pip3 install -r requirements.txt -i https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple

下载human3.6M dataset

https://drive.google.com/file/d/1FMgAf_I04GlweHMfgUKzB0CMwglxuwPe/view

解压后把npz放进./data文件夹下

下载pretrained-model

https://drive.google.com/drive/folders/1Mr00vyPXMnAX2lA4r1r2L3nR1bR4wvoN

下载YOLOv3 and HRNet pretrained models

https://drive.google.com/drive/folders/1_ENAMOsPM7FXmdYRbkwbFHgzQq_B_NQA

放到./demo/lib/checkpoint

三个地方的文件下载完成后，如下图的目录

跑一下demo

python demo/vis.py --video sample_video.mp4

报错

- 标题：Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation
- 论文地址：https://arxiv.org/abs/2311.12028
- 代码地址：https://github.com/NationalGAILab/HoT
使用conda进行环境准备
conda create -n hot python=3.9
conda activate hot
pip3 install -r requirements.txt -i https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
下载human3.6M dataset  
https://drive.google.com/file/d/1FMgAf_I04GlweHMfgUKzB0CMwglxuwPe/view
解压后把npz放进./data文件夹下下载pretrained-model
https://drive.google.com/drive/folders/1Mr00vyPXMnAX2lA4r1r2L3nR1bR4wvoN下载YOLOv3 and HRNet pretrained models
https://drive.google.com/drive/folders/1_ENAMOsPM7FXmdYRbkwbFHgzQq_B_NQA
./demo/lib/checkpoint三个地方的文件下载完成后，如下图的目录跑一下demo
python demo/vis.py --video sample_video.mp4
报错
python demo/vis.py --video sample_video.mp4
A module that was compiled using NumPy 1.x cannot be run in
NumPy 2.0.2 as it may crash. To support both 1.x and 2.x
versions of NumPy, modules must be compiled with NumPy 2.0.
Some module may need to rebuild instead e.g. with 'pybind11>=2.12'.
If you are a user of the module, the easiest solution will be to
downgrade to 'numpy<2' or try to upgrade the affected module.
We expect that some modules will need time to support NumPy 2.
Traceback (most recent call last):  File "/home/dar/model/HoT/demo/vis.py", line 15, in <module>
import matplotlib
File "/home/dar/miniconda3/envs/hot/lib/python3.9/site-packages/matplotlib/__init__.py", line 131, in <module>
from . import _api, _version, cbook, _docstring, rcsetup
File "/home/dar/miniconda3/envs/hot/lib/python3.9/site-packages/matplotlib/rcsetup.py", line 27, in <module>
from matplotlib.colors import Colormap, is_color_like
File "/home/dar/miniconda3/envs/hot/lib/python3.9/site-packages/matplotlib/colors.py", line 56, in <module>
from matplotlib import _api, _cm, cbook, scale
File "/home/dar/miniconda3/envs/hot/lib/python3.9/site-packages/matplotlib/scale.py", line 22, in <module>
from matplotlib.ticker import (
File "/home/dar/miniconda3/envs/hot/lib/python3.9/site-packages/matplotlib/ticker.py", line 138, in <module>
from matplotlib import transforms as mtransforms
File "/home/dar/miniconda3/envs/hot/lib/python3.9/site-packages/matplotlib/transforms.py", line 49, in <module>
from matplotlib._path import (
AttributeError: _ARRAY_API not found
Traceback (most recent call last):
File "/home/dar/model/HoT/demo/vis.py", line 15, in <module>
import matplotlib
File "/home/dar/miniconda3/envs/hot/lib/python3.9/site-packages/matplotlib/__init__.py", line 131, in <module>
from . import _api, _version, cbook, _docstring, rcsetup
File "/home/dar/miniconda3/envs/hot/lib/python3.9/site-packages/matplotlib/rcsetup.py", line 27, in <module>
from matplotlib.colors import Colormap, is_color_like
File "/home/dar/miniconda3/envs/hot/lib/python3.9/site-packages/matplotlib/colors.py", line 56, in <module>
from matplotlib import _api, _cm, cbook, scale
File "/home/dar/miniconda3/envs/hot/lib/python3.9/site-packages/matplotlib/scale.py", line 22, in <module>
from matplotlib.ticker import (
File "/home/dar/miniconda3/envs/hot/lib/python3.9/site-packages/matplotlib/ticker.py", line 138, in <module>
from matplotlib import transforms as mtransforms
File "/home/dar/miniconda3/envs/hot/lib/python3.9/site-packages/matplotlib/transforms.py", line 49, in <module>
from matplotlib._path import (
ImportError: numpy.core.multiarray failed to import

使用  conda update matplotlib 解决

再运行一次，生成的视频，3d pose 2d pose都在output目录下