yolov4-deepsort

This repository is a fork from "https://github.com/theAIGuysCode/yolov4-deepsort" which was modified to simply aims to perform object detection using Tensorflow 2.x and YOlOv4 ignoring the object tracking

Getting Started

To get started, install the proper dependencies either via Anaconda or Pip. I recommend Anaconda route for people using a GPU as it configures CUDA toolkit version for you.

Conda (Recommended)

# 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

Pip

(TensorFlow 2 packages require a pip version >19.0.)

# TensorFlow CPU
pip install -r requirements.txt

# TensorFlow GPU
pip install -r requirements-gpu.txt

Nvidia Driver (For GPU, if you are not using Conda Environment and haven't set up CUDA yet)

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

Downloading Official YOLOv4 Pre-trained Weights

Our object tracker uses YOLOv4 to make the object detections, which deep sort then uses to track. There exists an official pre-trained YOLOv4 object detector model that is able to detect 80 classes. For easy demo purposes we will use the pre-trained weights for our tracker. Download pre-trained yolov4.weights file: https://drive.google.com/open?id=1cewMfusmPjYWbrnuJRuKhPMwRe_b9PaT

Copy and paste yolov4.weights from your downloads folder into the 'data' folder of this repository.

If you want to use yolov4-tiny.weights, a smaller model that is faster at running detections but less accurate, download file here: https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v4_pre/yolov4-tiny.weights

Save the YOLOv4 wegiths as a TensorFlow model

To perform object detection with YOLOv4, first we convert the .weights into the corresponding TensorFlow model which will be saved to a checkpoints folder.

# Convert darknet weights to tensorflow model
python save_model.py --weights ./data/yolov4-tiny.weights --output ./checkpoints/yolov4-tiny-416 --model yolov4 --tiny

    or

python save_model.py --model yolov4

If you want to run yolov3 set the model flag to --model yolov3, upload the yolov3.weights to the 'data' folder and adjust the weights flag in above commands. (see all the available command line flags and descriptions of them in a below section)

Running the detections with YOLOv4-Tiny

The following commands will allow you to run yolov4-tiny model. Yolov4-tiny allows you to obtain a higher speed (FPS) for the tracker at a slight cost to accuracy. Make sure that you have downloaded the tiny weights file and added it to the 'data' folder in order for commands to work!

# save yolov4-tiny model
python save_model.py --weights ./data/yolov4-tiny.weights --output ./checkpoints/yolov4-tiny-416 --model yolov4 --tiny

# Run yolov4-tiny detection with
python process_image_withTensorFlow.py

References

Huge shoutout goes to hunglc007 and nwojke for creating the backbones of this repository:

DimasVeliz/yolov4-deepsort