This is the implementation of tf.nn.softmax_cross_entropy_with_logits, a function in tensoflow to compute the Cross_entropy loss with softmax classifier. Official Documentation for tf.nn.softmax_cross ...

Training result show between CapsNet (Orange) and CNN baseline (Blue). The cost of CapsNet is marginal loss plus l2 regularization. The cost of CNN baseline is the sum of cross entropy and l2 loss.

Implementation. You can use the loss function by simply calling tf.keras.loss as shown in the below command, and we are also importing NumPy additionally for our upcoming sample usage of loss ...