Error with 3D convolution on custom Kernels

[Elmiar0642]

I wanted to add my own 3D kernel on every layer. I tried using this,

` def conv3(in_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=True, planar=False, dim=3): """Returns an appropriate spatial convolution layer, depending on args.

• dim=2: Conv2d with 3x3 kernel
• dim=3 and planar=False: Conv3d with 3x3x3 kernel

• dim=3 and planar=True: Conv3d with 1x3x3 kernel """ if planar: stride = planar_kernel(stride) padding = planar_pad(padding) kernel_size = planar_kernel(kernel_size)

  weights = torch.tensor([[[4., 1., 4.], [1., 1., 1.], [4., 1., 4.]], [[1., 1., 1.], [1., 10., 1.], [1., 1., 1.]], [[4., 1., 4.], [1., 1., 1.], [4., 1., 4.]]])

  weights

  weightsu = weights.view(3, 3, 3).repeat(1, 1, 1, 1, 1)

  weightsu

  kernel = get_conv(dim)( in_channels, out_channels, kernel_size=kernel_size, stride=stride, padding=padding, bias=bias ) print(kernel.weight.shape) with torch.no_grad(): kernel.weight = nn.Parameter(weightsu)

  return kernel

`

But I got an error like this,

Testing 3D U-Net with n_blocks = 1, planar_blocks = ()... torch.Size([32, 1, 3, 3, 3]) torch.Size([32, 32, 3, 3, 3])

RuntimeError: Given weight of size [1, 1, 3, 3, 3], expected bias to be 1-dimensional with 1 elements, but got bias of size [32] instead

I kindly request you to Help me fix this!!!

@Optiligence @my-tien @xeray @mdraw @jmrk84

[Elmiar0642]

With Random kernels and planar setting, I get output as

Testing 3D U-Net with n_blocks = 1, planar_blocks = ()...

torch.Size([32, 1, 3, 3, 3])

torch.Size([32, 32, 3, 3, 3])

Testing 3D U-Net with n_blocks = 1, planar_blocks = (0,)...

torch.Size([32, 1, 1, 3, 3])

torch.Size([32, 32, 1, 3, 3])

...

...

...

All tests sucessful!

[mdraw]

This issue is not really related to elektronn3. If I understand correctly you want to change the initialization of your weights. Note that the get_conv(dim) call here evaluates to torch.nn.Conv3d Please refer to the PyTorch docs and https://discuss.pytorch.org/ if you need help with changing weights of torch.nn.Conv3d modules.