softmax issue

[HenryZ5734]

My implementation of softmax.backward is below: def backward(self, label): self.delta = self.softmax.copy()

start your code

    self.delta -= label
    ## end your code
    return self.delta / self.input_batch

[xianggkl]

Thank you for pointing out my problem. In order to treat a batch of data as one, the cross-entropy function needs to take the average of the batches of data, so it also needs to divide by batchsize when back-propagating.