Closed varghesealex90 closed 7 years ago
In the autoencoder example, the values printed i.e. print('epoch [{}/{}], loss:{:.4f}' .format(epoch + 1, num_epochs, loss.data[0])) this is the error associated with the final batch of the data right ?
yes, you can compute the average loss by storing all the loss.
In the autoencoder example, the values printed i.e. print('epoch [{}/{}], loss:{:.4f}' .format(epoch + 1, num_epochs, loss.data[0])) this is the error associated with the final batch of the data right ?