CODEWITHSUNDEEP
pythonconv-neural-networkpytorchtorch
markroxor
markroxor

Reputation: 6476

Setting custom kernel for CNN in pytorch

Is there a way to specify our own custom kernel values for a convolution neural network in pytorch? Something like kernel_initialiser in tensorflow? Eg. I want a 3x3 kernel in nn.Conv2d with initialization so that it acts as a identity kernel -

0 0 0
0 1 0
0 0 0

(this will effectively return the same output as my input in the very first iteration)

My non-exhaustive research on the subject -

I could use nn.init but it only has some pre-defined kernel initialisaition values.

I tried to follow the discussion on their official thread but it doesn't suit my needs.

I might have missed something in my research please feel free to point out.

Upvotes: 4

Views: 5837

Answers (2)

William
William

Reputation: 31

I think an easier solution is to :

    deconv = nn.ConvTranspose2d(
        in_channels=channel_dim, out_channels=channel_dim,
        kernel_size=kernel_size, stride=stride,
        bias=False, padding=1, output_padding=1
    )
    deconv.weight.data.copy_(
        get_upsampling_weight(channel_dim, channel_dim, kernel_size)
    )

in other words use copy_

Upvotes: 1

markroxor
markroxor

Reputation: 6476

Thanks to ptrblck I was able to solve it. I can define a new convolution layer as conv and as per the example I can set the identity kernel using - 

weights = ch.Tensor([[0, 0, 0], [0, 1, 0], [0, 0, 0]]).unsqueeze(0).unsqueeze(0)
weights.requires_grad = True


conv = nn.Conv2d(1, 1, kernel_size=3, stride=1, padding=1, bias=False)

with ch.no_grad():
    conv.weight = nn.Parameter(weights)

I can then continue to use conv as my regular nn.Conv2d layer.

Upvotes: 1

Related Questions