https://drive.google.com/file/d/19eICWXLr0zc4ea4vm1kx9Nyk64e42B00/view?usp=sharing
# Tensorflow CPU
conda env create -f conda-cpu.yml
conda activate yolov4-cpu
# Tensorflow GPU
conda env create -f conda-gpu.yml
conda activate yolov4-gpu
(TensorFlow 2 packages require a pip version >19.0.)
pip install opencv-python
# TensorFlow CPU
pip install -r requirements.txt
# TensorFlow GPU
pip install -r requirements-gpu.txt
Make sure to use CUDA Toolkit version 10.1 as it is the proper version for the TensorFlow version used in this repository. https://developer.nvidia.com/cuda-10.1-download-archive-update2
python guii.py
After that you will see tkinker window app
- pick a video file to process
- run the program
- open modified video file and logs to see results