ValueError: Shape mismatch: The shape of labels (received (19200,)) should equal the shape of log...

ValueError: Shape mismatch: The shape of labels (received (19200,)) should equal the shape of logits except for the last dimension (received (6144, 50)).

解决:use of sparse_softmax_cross_entropy. feed it one hot encoded labels which it doesn't want.

Switch to just normal softmax_cross_entropy and see if that works.

https://stackoverflow.com/a/37317322/7431458

你可能感兴趣的:(ValueError: Shape mismatch: The shape of labels (received (19200,)) should equal the shape of log...)