Skip to content

Latest commit

 

History

History
19 lines (15 loc) · 844 Bytes

README.md

File metadata and controls

19 lines (15 loc) · 844 Bytes

MLP Digit recognition

The example codes above are related to a 5-layer MLP NN (Input layer - 3 hidden layer - Output layer) classification for the problem of recognizing numbers from 0 to 9.

For this issue, the dataset available in the link below has been used. https://www.kaggle.com/competitions/digit-recognizer/data (Also available in Dataset folder)

Run the main.py file to run the code. After running the code, you will need to specify the following.

  • The dataset path
  • If you want to use a previously saved model, the path to the saved model must be specified
  • The number of iteration steps (Epochs)
  • Data validation percentage
  • Test set percentage
  • Learning rate
  • Batch size
  • Optimizer model
  • The number of neurons in the first layer
  • The number of neurons in the second layer
  • The number of neurons in the third layer