Jinfu Liu

I compile and install in a docker image. [pytorch docker image](https://hub.docker.com/r/pytorch/pytorch/tags) My installation process log: ''' docker pull pytorch/pytorch:1.11.0-cuda11.3-cudnn8-devel conda create -n torch python=3.8 conda activate torch conda install pytorch...

In centos8, it work for me. Remove the following from yaml: ``body-visualizer==1.1.0`` ``configer==1.4.1`` ``psbody-mesh==0.4`` Replace by: ``pip install git+https://github.com/nghorbani/body_visualizer.git`` ``pip install git+https://github.com/MPI-IS/configer`` ``sudo yum -y install boost-devel`` ``pip install git+https://github.com/MPI-IS/mesh.git``

same too. Solution: Please check the corresponding log.txt. Generally it is because of code or environment errors that need to be configured and updated. So please check the error printed...

# Step 1: ``` git clone https://github.com/liujf69/TD-GCN-Gesture.git ``` # Step2: ```python import sys import torch import traceback def import_class(import_str): mod_str, _sep, class_str = import_str.rpartition('.') __import__(mod_str) try: return getattr(sys.modules[mod_str], class_str) except...

Generally, the model can be used for 2D Pose obtained by HR-Net. You need to modify the following key modules: 1. Define the adjacency matrix of skeleton graph. ```python #...

你是使用了我提供的fbx文件嘛？我这边运行是正常的

In fact, the input for both Mix_GCN and Mix_Former follow the dimensions of [N, C, T, V, M], so you only need to reconstruct the ```dataloader``` in the usual way...

In fact, you need to train each modality separately and save their classification scores. Then, use the ensemble code to combine the classification scores in order to obtain the ensemble...