pytorch-binary-converter

pytorch-binary-converter copied to clipboard

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...

eadstry

In float2bit, values of 0 are throwing an out of bounds bug

2

Hi, when sending a tensor from a Relu activation function to float2bit, f can take the value 0. Then, the log2 will return -inf with all the complications it ensues...

sebastienwood