xichunling / image-classification-rnn Goto Github PK

• This is a multi-class image classification problem.
• The purpose of this project is to classify MNIST image dataset into 10 classes.
• The model was built with Recurrent Neural Network (RNN: LSTM) on Tensorflow.

• The MNIST image dataset was saved in the ./data/ directory.

• Command: python3 train.py parameters.json
• Example: python3 train.py ./parameters.json

A directory will be created during training, and the model will be saved in this directory.

Provide the model directory (created when running train.py) to predict.py.

• Command: python3 predict.py ./trained_model_directory/
• Example: python3 predict.py ./trained_model_1481170507/

• Recurrent Neural Network