A Deep learning program that recognizes your hand gesture and lets you play rock paper scissors with your computer
The model is a convolutional neural network with 4 convolution layers and one dense layer trained on 100 epochs. For now, This is all i have done but i am working on improving the accuracy
The data consists of 3873 images labeled for each gesture such as rock, paper and scissor. All the data was generated by me
First of all make sure you have python installed. In this project I used python 3.8 but most versions will work. However Python 3.9 will not work yet as tensorflow does not have support for it yet.
You can download the project directly from here or download it from the command line using git
>git clone https://github.com/fwizz/rock-paper-scissors
Once you have downloaded the project you will need to install the requirements
>cd rock-paper-scissors
>pip install -r requirements.txt
To run the rock paper scissors game all you will have to do is
>python main.py
If you want to test out the algorithm only, You will have to do this instead
>cd misc
>python test_video.py