Action recognition UCF101

This code was inspired in: https://github.com/harvitronix/five-video-classification-methods

Requirements

This code requires you have Keras 2 and TensorFlow 2 or greater installed. Please see the requirements.txt file. To ensure you're up to date, run:

pip install -r requirements.txt

You must also have ffmpeg installed in order to extract the video files.

Getting the data

First, download the dataset from UCF into the data folder:

cd data && wget http://crcv.ucf.edu/data/UCF101/UCF101.rar

Then extract it with unrar e UCF101.rar.

Next, create folders (still in the data folder) with mkdir train && mkdir test && mkdir sequences && mkdir checkpoints.

Now you can run the scripts in the data folder to move the videos to the appropriate place, extract their frames and make the CSV file the rest of the code references. You need to run these in order. Example:

python 1_move_files.py

python 2_extract_files.py

Training models

The CNN-only method is run from train_cnn.py.

The rest of the models are run from train.py. There are configuration options you can set in that file to choose which model you want to run.

The models are all defined in models.py. Reference that file to see which models you are able to run in train.py.

UCF101 Citation

Khurram Soomro, Amir Roshan Zamir and Mubarak Shah, UCF101: A Dataset of 101 Human Action Classes From Videos in The Wild., CRCV-TR-12-01, November, 2012.