Testing and Training of the CMU Dataset - Samleo8/learnable-triangulation-pytorch GitHub Wiki

Overview

The primary purpose of this repository is to extend the capabilities of the algorithm to the CMU dataset, as well as other general datasets. After much work, I have been able to successfully test the dataset based on pre-trained weights from Human3.6M, and the volumetric triangulation algorithm. More discussion and details can be found here and results here.

You can now download pretrained labels and data from my Google drive here, with supplementary data and weights from the original author's Google drive here.

Evaluating (H36M pretrained weights)

  1. Download and preprocess the dataset by following the instructions in mvn/datasets/cmu_preprocessing/README.md.
  2. The config files can be found at $THIS_REPOSITORY/experiements/[train|eval]/cmupanoptic
  3. You can also do a quick evaluation using the provided ./eval_cmu script
  4. You can view preliminary results here

IMPORTANT NOTE: There is a bug with the old Python version where multiprocessing connections are unable to send more than 2 Gb of data. This is fixed in a pull request for new Python versions here.

Therefore, you may possible run into MemoryErrors if running on Linux machines with Python versions < 3.8. The fix to this is to modify the multiprocessing library's connection.py file with the updated file here, which is from the aforementioned pull request.

It is advised that you create a backup of the old connection.py file in case something goes wrong.

Example of where to find the file:

  • If using virtual environment: ~/.pyenv/versions/<your_python_version>/lib/python<python_version>/connection.py
  • Otherwise: /usr/lib/python<python_version>/multiprocessing*

Model Zoo

Model Train config Eval config Weights Precalculated results MPJPE (relative to pelvis), mm
Algebraic train/cmu_alg.yaml eval/cmu_alg.yaml - - ??
Volumetric (softmax) train/cmu_vol_softmax.yaml eval/cmu_vol_softmax.yaml - — ??