pritam-n / parnet Goto Github PK

In Downsample, I think it should be torch.nn.AvgPool2d(kernel_size=(3, 3), stride=(2, 2), padding=(1, 1)), not torch.nn.AvgPool2d(kernel_size=(2,2)). otherwise x & y have wrong size, and x + y will throw exception.

Like requirement.
Please! Thank you!

Can you give an easy baseline for training ?
Please, thank you !

Hello, my friend, appreciate for your great work! I have tested your code and change the ResNet code in my model by using your ParNet , but the actual time is quite slow than the paper said. My block size is [64, 128, 256, 512, 2048], and the time of "forward()" is more than 5s average while the Resnet is 0.02s in my device. I have use the time function for every line in the forward(), find that the encode stuff is the main reason. I continue write time.perf_counter() in the encode stuff, find that the "self.stream2_fusion" and "self.stream3_fusion" is the most time user. Do you know why ?