Conv3d error on dimensions of a 5d tensor

#1

I have a tensor shaped ([5, 1, 3, 126, 126]), which represents a video (5 frames each 126x126 rgb).
I need to forward it into a

self.resnet = nn.Sequential(
        nn.Conv3d(5,5,1), 
        nn.UpsamplingBilinear2d(size=None, scale_factor=0.5)  
    )

but i get

RuntimeError: Given groups=1, weight of size [5, 5, 1, 1, 1], expected input[5, 1, 3, 126, 126] to have 5 channels, but got 1 channels instead

I think that I have probably misunderstood how the conv3d works but I can’t really understand why the expected dimensions are so different from the ones that my 5d tensor has at that moment

#2

Hi,

A 5D tensor is like [batch, channel, depth, height, width] and nn.Conv3d(in_channel, out_channel, kernel_size) expects to have in_channel = channel(in your 5d tensor) but you have set in_channel=5 while your 5D tensor has 1 channel.

You need to use nn.Conv3d(1, 5, 1)

Bests