Closed MordehayM closed 6 months ago
Hi, The paper states that the output shape of the sampler is H^2 x H^2, but it appears that is not the case in the code here:
Thanks
This is a calculated result rather than something in the code. For a convolutional layer with a kernel size of H, the range of its convolution at each step covers a square area of H^2. As you can see, our code includes two convolutional layers, so the overall range of convolution would be H^2 * H^2. The output shape here refers to the representation, rather than the intermediate result.
So if I understood you correctly, the output shape of the sampler is not H^2 x H^2? I am confused because the paper states that this is the output shape of the sampler 🤔
So if I understood you correctly, the output shape of the sampler is not H^2 x H^2? I am confused because the paper states that this is the output shape of the sampler 🤔
Yes, you're right. The expression in the paper does indeed have a bit of ambiguity.
So if I understood you correctly, the output shape of the sampler is not H^2 x H^2? I am confused because the paper states that this is the output shape of the sampler 🤔
A more accurate expression would be that it should be equivalent to the shape that can be processed with each sampling.
Since your convolution layers are without padding and with unit stride, the output shape for tensor with shape [F, L] should be [F-H+1, L-H+1]. Then, you chose only K bins and passed them through the linear layers.
Hi, The paper states that the output shape of the sampler is H^2 x H^2, but it appears that is not the case in the code here: https://github.com/TzuchengChang/NASS/blob/ab98c434a5b51ff0ebfd7d3a97a9876135fa52dd/speechbrain/speechbrain/lobes/models/networks.py#L36
Thanks