Less parameters will improve the training time. FC layers are costly and we can avoid it if needed.
-
Updated
Aug 1, 2021 - Jupyter Notebook
#
mnist-less-trainable-parameters
Here is 1 public repository matching this topic...
Improve this page
Add a description, image, and links to the mnist-less-trainable-parameters topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the mnist-less-trainable-parameters topic, visit your repo's landing page and select "manage topics."