Flatten

neuralpy.layers.other.Faltten(start_dim=1, end_dim=-1, name=None)

info

Flatten is mostly stable and can be used for any project. In the future, any chance of breaking changes is very low.

Flattens a contiguous range of dims into a tensor. For use with Sequential.

For more information, check this page

Supported Arguments

• start_dim=1: (Integer) First dim to flatten
• end_dim=-1: (Integer) Last dim to flatten
• name=None: (String) Name of the layer, if not provided then automatically calculates a unique name for the layer

Example Code

from neuralpy.models import Sequential

from neuralpy.layers.other import Flatten

# Initializing the Sequential models

model = Sequential()

...

...

...

model.add(Flatten(start_dim=1, end_dim=-1, name="Flatten layer"))