pytorch_compact_bilinear_pooling
pytorch_compact_bilinear_pooling copied to clipboard
gdlg
Compact Bilinear Pooling for PyTorch
Dear gdlg, Wishing you all the best lately. Thank you very much for sharing the CBP codes. The time I was trying to test them, I found an interesting result....
Hi, I have run the same code, but got this error in this [line](https://github.com/gdlg/pytorch_compact_bilinear_pooling/blob/master/compact_bilinear_pooling/__init__.py#L154). For input: ``` from compact_bilinear_pooling import CountSketch, CompactBilinearPooling input_size = 2048 output_size = 16000 mcb =...
I am running this code for compact bilinear pooling. I have 18000 data points but for some values I am getting zero output vector. My inputs are of shape 1024,...
merge
What if I want to merge two feature maps? The shape of the feature map is (batch_size, channel, w, h) ,,,, Thank you ！
Fix torch.rfft and torch.irfft import problems. Support both origin torch version and version 1.1.0
Source code： x = self.features(x) #[4,512,28,28] batch_size = x.size(0) x = (torch.bmm(x, torch.transpose(x, 1, 2)) / 28 ** 2).view(batch_size, -1) x = torch.nn.functional.normalize(torch.sign(x) * torch.sqrt(torch.abs(x) + 1e-10)) x = self.classifiers(x)...
