C3D-TensorFlow2

This was forked from https://github.com/toddnguyen/c3d-tensorflow, but debugged/modified significantly to work with existing UCF-101 data set and in dextro environment. It's a WIP for end-to-end training for 8-conv layer C3D network.

Training

Steps to start raining:

Download UCF-101 dataset from UCF-101 website.
Unzip the dataset: e.g. unrar x UCF101.rar
Extract frames from UCF-101 videos by revising and running a helper script, bash tools/extract_frames.sh.
Download pre-trained weights and mean cube files: bash models/get_weights_and_mean.sh
Add facebook/C3D python path (requirement for the subsequent steps): export PYTHONPATH=$PYTHONPATH:/path/to/facebook-c3d/python
Convert weights: python convert_weights.py
Convert a mean cube: python convert_mean.py

Name		Name	Last commit message	Last commit date
Latest commit History 25 Commits
architectures		architectures
lists		lists
models		models
tools		tools
utils		utils
.gitignore		.gitignore
README.md		README.md
configure.py		configure.py
convert_mean.py		convert_mean.py
convert_weights.py		convert_weights.py
gen_lists.sh		gen_lists.sh
preprocess.py		preprocess.py
test.py		test.py
trainer_c3d.py		trainer_c3d.py