glt999

Hello, in the training of the following mistakes, how to solve it

1

einops.EinopsError: Error while processing rearrange-reduction pattern "b h (x y) d -> b h x y d". Input tensor shape: torch.Size([2, 4, 900, 128]). Additional info: {'x': 26, 'y': 26}....

Why is gflops negative

1

 When testing mobilenet-yolov4, a negative number of gflops is displayed

AttributeError: module 'torch.distributed' has no attribute 'barrier'

2

Hello, I encountered this problem during verification. I would be very grateful if you could give me the answer.