: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

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

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

Return the MS-SSIM score between `img1` and `img2`. This function implements Multi-Scale Structural Similarity (MS-SSIM) Image Quality Asses

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

Function to mimic the 'fspecial' gaussian MATLAB function.

Return the Structural Similarity Map between `img1` and `img2`. This function attempts to match the functionality of ssim_index_new.m by Zho

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

The main function that defines the ResNet. total layers = 1 + 2n + 2n + 2n +1 = 6n + 2 :param input_tensor_batch: 4D tensor :param n: num

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

Builds the analysis transform.

Builds the synthesis transform.

Builds the analysis transform.

Builds the synthesis transform.

Run this function to look at the graph structure on tensorboard. A fast way! :param train_dir: