Meaning of "ni" and "nf"

Hey folks,
Lovely course. I didn’t catch it much:
What’s “ni” or “nf”?
When I see in Conv(ni,nf), it looks like initial to final (ni to nf), and it is actually number of features (nf)?
Thanks

Hi,

Reference the PyTorch documentation
https://pytorch.org/docs/stable/generated/torch.nn.Conv2d.html

ni, nf should correspond to

  • in_channels (int) – Number of channels in the input image
  • out_channels (int) – Number of channels produced by the convolution
1 Like

Thank you! I’ll continue exploring about this from your reference.