:param name: A string. The name of the new variable :param shape: A list of dimensions :param initializer: User Xavier as default. :p

Defines a residual block in ResNet :param input_layer: 4D tensor :param output_channel: int. return_tensor.get_shape().as_list()[-1] = ou

Helper function to do batch normalziation :param input_layer: 4D tensor :param dimension: input_layer.get_shape().as_list()[-1]. The dept

A helper function to batch normalize, relu and conv the input layer sequentially :param input_layer: 4D tensor :param filter_shape: list.

Given a set of examples (x_nat, y), returns a set of adversarial examples within epsilon of x_nat in l_infinity norm.

A helper function to conv, batch normalize and relu the input tensor sequentially :param input_layer: 4D tensor :param filter_shape: list

:param input_layer: 2D tensor :param num_labels: int. How many output labels in total? (10 for cifar10 and 100 for cifar100) :return: out

Attack parameter initialization. The attack performs k steps of size a, while always staying within epsilon from the initial point.

:param x: A Tensor :return: Add histogram summary and scalar summary of the sparsity of the tensor