How does Conv2d sees the input data?

  (conv): Sequential(
    (0): Conv2d(1, 64, kernel_size=(4, 4), stride=(1, 1))
    (1): ReLU()
    (2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)

Imagine the input shape looks like 1x7x7
How does the input data gets transformed/scaled into the In/Out channels of Conv2d?

I’m sure I sound silly but all explanations came with the perspective of images where the input was larger than the channels. My case is Connect4 (with 6x7 + 1x7 action space). I am trying to get a pattern recognition.

Are you interested in the general method how conv layers are working?
If so, I think CS231n - Conv is providing a good explanation how each filter is used in the layer.

after checking the resource that @ptrblck provided,you can check this as well : SIIM-ISIC Melanoma Classification | Kaggle

Thanks guys, I dive further