Hi!
I am reading your paper and code recently, they're really good. But I have some difficulties understanding the following code in get_adv2() in nn.py:
adv_list = [] loss = layer_list[-2][1].output[:, f] grads = K.gradients(loss, model.input)[0] iterate = K.function([model.input], [loss, grads])
What does the 'loss' mean here? Does it means the specific loss of the f^th output_neuron?
Hi!
I am reading your paper and code recently, they're really good. But I have some difficulties understanding the following code in get_adv2() in nn.py:
adv_list = [] loss = layer_list[-2][1].output[:, f] grads = K.gradients(loss, model.input)[0] iterate = K.function([model.input], [loss, grads])What does the 'loss' mean here? Does it means the specific loss of the f^th output_neuron?