Open helblazer811 opened 1 year ago
The max pooling visualization can work as follows:
Moved max pooling to its own issue: https://github.com/helblazer811/ManimML/issues/16
For padding I probably want to add a dotted rectangle surrounding each of the feature maps. I will then need to make sure that when I do the convolution animation that I align with the corner there.
[ ] Change the parameters of the Convolutional3D to be more ergonomic.
I want to make the parameters more similar to: https://pytorch.org/docs/stable/generated/torch.nn.Conv2d.html?highlight=conv2d#torch.nn.Conv2d
Your suggestion "Add a FlattenLayer that flattens a preceding convolutional layer." is a duplicate of issue #24 .
I want to add the following features: