YOLO ON SERVER

This repo comprises of the code to run a detection algoithm on a server as a service and it has live implementation of my nosave-server approach. Use it freely :)

Highly recommended to have Tensorflow-gpu up and running.

After moving inside the directory. To run the project:

1. Install virtual environment

pip install virtualenv

2. Initiate virtual environment

virtualenv venv

3. Activate virtualenv

. venv/bin/activate

4. Install the requirements

pip install -r requirements.txt

5. Download and convert the weights for yolov3 and yolov3-tiny

wget https://pjreddie.com/media/files/yolov3.weights
 ./yad2k.py yolov3.cfg yolov3.weights yolo.h5  
wget https://pjreddie.com/media/files/yolov3-tiny.weights
./yad2k.py yolov3-tiny.cfg yolov3-tiny.weights tint_yolo.h5

6. Run the server

python server.py