@@soroushmehraban yes abs thx so much, although I Have a Quick Question More Related to PyTorch actually which is in min 12:49 in line 239 in the code 1st what does -1 here means and what does it do exactly with the tensor 2nd from where we get [4,16] the 4 here from where we got it cuz its not mentioned in the reshaping. Thanks in advance.
2:43 C would be equal to the number of filters not the number of kernels. In the torch.nn.conv2d operation being performed we have 3 kernels for each input channel and then C number of filters. Each filter having 3 kernels not C number of kernels.
Because we downsample the width by 2 and height by 2. That means we have 4x downsampling in spatial resolution that we give it to the channel dimension. It's just a simple tensor reshaping. For example 10x10x2 = 200. After merging it's 5x5x8 = 200.
By far one of the best + complete, SWIN transformer explanations on the entire Internet.
Thanks!
@@soroushmehraban Hi sir, could you also explain the FasterViT and GCViT paper...
Really informative, helped me lot to understand many concepts here. Keep up the good work
Thanks! I’ll try my best.
Thorough! Very comprehensible, thank you.
That's The Most Illustrative Video Of Swin-Transformers on The Internet!
Glad you enjoyed it 😃
@@soroushmehraban yes abs thx so much, although I Have a Quick Question More Related to PyTorch actually which is in min 12:49 in line 239 in the code 1st what does -1 here means and what does it do exactly with the tensor 2nd from where we get [4,16] the 4 here from where we got it cuz its not mentioned in the reshaping. Thanks in advance.
Very well explained, thank you Soroush.
Glad you liked it
You deserve more likes and subscribers
Thanks man🙂 appreciated
Thanks for the good explanation!
perfect description.
Glad it was helpful 🙂
Amazing video !
Thanks!
Great video! Thanks
Thanks for the feedback 🙂
2:43 C would be equal to the number of filters not the number of kernels. In the torch.nn.conv2d operation being performed we have 3 kernels for each input channel and then C number of filters. Each filter having 3 kernels not C number of kernels.
I enjoy very much
Why channel increasees c to 4c after merging
Because we downsample the width by 2 and height by 2. That means we have 4x downsampling in spatial resolution that we give it to the channel dimension. It's just a simple tensor reshaping.
For example 10x10x2 = 200.
After merging it's 5x5x8 = 200.
very nicely explained thank you! likes are at 314 so didnt hit like it😁subbed instead