Firstly the model is created and trained using train.py. The model parameters are also saved at model_state.pt. visualize.py is then used to "look into the cnn". The model is loaded back in using the ...
Number of filters in convolutional layers Number of units in the fully connected layer Dropout rate Learning rate Batch size Visualization: Matplotlib is used to display some results, and TensorBoard ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback