Open ojmakke opened 5 years ago
Hello,
The last layer for MNIST is Linear, not BinarizeLinear, this will cause the weights to not necessarily be binary, correct?
Also, for the batch normalization layer, its parameters are not binary. Correct?
Hello,
The last layer for MNIST is Linear, not BinarizeLinear, this will cause the weights to not necessarily be binary, correct?
Also, for the batch normalization layer, its parameters are not binary. Correct?