sxjscience commented on issue #10035: Who can help me solve this error??batch_loss.backward() error? URL: https://github.com/apache/incubator-mxnet/issues/10035#issuecomment-371622551 The for-loop here should be the problem ```python for step in range(...): ... ``` We can revise it to be a single phrase, i.e, ```python batch_loss = nd.mean(softmax_cross_entropy(logits, one_hot_label)) ``` If you still cannot solve it, you can post the codes here (instead of images) and I will help you debug.
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services