Hi, I stumbled upon this question because I am trying to have control over how my convolutional weights are initialized.
The API for both of those however seems different.
For the former:
torch.nn.functional.conv2d(input, weight, bias=None, stride=1, padding=0, dilation=1, groups=1)
For the latter:
class torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True)
So, my questions are the following:
- Why should I use one over the other?
- I am trying to initialize my convolutional weights with what I want, so is that possible using nn.Conv2D? I guess one way is to copy over the proper weights that I want, so is that basically it?