pytorch-binary-converter icon indicating copy to clipboard operation
pytorch-binary-converter copied to clipboard

Published 20 hours ago • verified publisher icon KarenUllrich

The model gradient becomes 0 after adding

Open eadstry opened this issue 3 years ago • 0 comments

After I add float2bit and bit2float to the network, the weight of the convolution model is always 0 when back propagating，I checked that the variables in the code are in cuda and required_grid=true, but the gradient seems to disappear.Can anyone tell me why this problem is happening?

eadstry avatar Oct 21 '22 15:10 eadstry