Demonstrate layer dimension in ‘visualcross’

As a deep learning specialist or student, you must work with documentation. Your document must show your models in detail. When you search Google for “how to demonstrate our violate deep learning model details,” you’ll find the ‘visual cross’ library.

Paul Gavrikov developed the ‘visual cross.’

What’s the visual cross?

Visualkeras is a Python package to help visualize Keras (either standalone or included in Tensorflow) neural network architectures. It allows easy styling to fit most needs. This module supports layered-style architecture generation, which is excellent for CNNs (Convolutional Neural Networks), and graph-style architecture, which works great for most models, including plain feed-forward networks.

 

Demonstrate layer dimension in ‘visual cross.’

If you installed this library, you probably asked, “how do you show layer dimensions detail?”. To solve this issue, I forked this repository and added new lines inside the source code for this library.

While I submitted a pull request to merge my contribution into the main code, the repository owner still needs to approve it.

If you want to use my code, you can download, install, and use it manually.

If you need to show layer dimension you must set legend=True and show_dimantion=True in layered_view:

visualkeras.layered_view(model, legend=True, show_dimantion=True)