Let's try to recognize the handwritten digits online with our single hidden layer Fully Connected Neural Network (aka. FCNet), which is powered by the MNIST dataset 😄.
It will be nice if you can play with the project. Below are some basic guidelines for you to have a good start!
You can run run_Train_Model.py and run_Evaluate_Model.py to train and evaluate the model respectively.
Currently, we use a single hidden layer Fully Connected Network and make it be trained with MNIST dataset. Feel free to rdesign your own network architecture and replace the file FCNet.py in the server/Training folder.
We prepared some helpful tools for you in the server/toos. You can do some work for the MNIST dataset with the help of these tools.
This project is open source under the MIT license.