Save the date! Google I/O returns May 18-20 Register now


Calculates adversarial loss from generated adversarial samples.

adv_neighbors dense float32 tensor, with two possible shapes: (a) [batch_size, feat_len] for pointwise samples, or (b) [batch_size, seq_len, feat_len] for sequence samples.
target_scores target tensor used to compute loss.
model_fn a method that has input tensor (same shape as adv_neighbors), is_train and reuse as inputs, and returns predicted logits.
loss_fn a loss function that has target and prediction as inputs, and returns a float32 scalar.

adv_loss a float32 denoting the adversarial loss.