/VisuCNN

Primary LanguageJupyter NotebookGNU Affero General Public License v3.0AGPL-3.0

VisuCNN

This repo contains VisuCNN.ipynb which is a good template for many useful tools that can help in understanding CNNs.

  1. Visualise the filters, the transition of the image as it passes through different convolutions. This is very useful in understanding how and what the CNN learns.
  2. Data added to tensorboard along with histograms of weights and biases, learning rates, batch accuracies, etc.
  3. Since the filter and image transitions are added after every epoch, it allows us to visualise the gradual transition of the model across epochs.
  4. The facility to properly catalogue different tensorbaord files in directories.
  5. Adding model checkpoints after every epoch, and saving model state after all epochs have been completed.
  6. The whole file can be modified to run with any model, even pre-trained.

Install the dependecies and check it out!