Calculation of the statistics used by the FID. Params: -- gen_imgs : gen_imgs, tensor -- model : Instance of inception model

Calculation of the statistics used by the FID. Params: -- files : list of paths to image files. Images need to have same dimensions for a

Calculates the FID of two paths.

Calculates the FID of two paths :param gen_imgs: The value range of gen_imgs should be (-1, 1). Just the output of tanh. :param path: fid

Numpy implementation of the Frechet Distance. The Frechet distance between two multivariate Gaussians X_1 ~ N(mu_1, C_1) and X_2 ~ N(mu_2, C_2

Finds the python object with the given name and calls it as a function.

Checks if the path to the inception file is valid, or downloads the file if it is not present.

Creates a graph from saved GraphDef file.

Return current stage. :param epoch: current epoch. :return: current stage

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). This is the same as the DropConnect impl I created for Ef

Build pretrained Inception model for FID computation The Inception model for FID computation uses a different set of weights and has a slightl

Build pretrained Inception model for FID computation The Inception model for FID computation uses a different set of weights and has a slightl

Calculates the activations of the pool_3 layer for all images. Params: -- images : Numpy array of dimension (n_images, hi, wi, 3). The v

Calculates the activations of the pool_3 layer for all images. Params: -- files : List of image files paths -- model : Instanc

Calculates the activations of the pool_3 layer for all images. Params: -- files : list of paths to image files. Images need to have same

Get inception score. :param args: :param gen_net: :param num_img: :return: Inception score

Finds the python object with the given name.

Determine whether the given object is a top-level function, i.e., defined at module scope using 'def'.

Determine whether the given object is a valid URL string.

Convenience method for batch-loading images Params: -- files : list of paths to image files. Images need to have same dimensions for all fi

Make a grid of images. Args: tensor (Tensor or list): 4D mini-batch Tensor of shape (B x C x H x W) or a list of images a

r"""Returns the number of scalars that were accumulated for the given statistic between the last two calls to `update()`, or zero if n

r"""Class decorator that extends a given class to save its source code when pickled. Example: from torch_utils import persistence

r"""Broadcasts the given set of scalars to all interested instances of `Collector`, across device and process boundaries. This function is ex

Save a given Tensor into an image file. Args: tensor (Tensor or list): Image to be saved. If given a mini-batch tensor, s

Pytorch implementation of the Frechet Distance. Taken from https://github.com/bioinf-jku/TTUR The Frechet distance between two multivariate Ga

Estimate a covariance matrix given data. Covariance indicates the level to which two variables vary together. If we examine N-dimensional samp

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

obtain the image (read and transform) :param idx: index of the file required :return: img => image array

obtain the image (read and transform) :param idx: index of the file required :return: img => image array

r"""Convenience getter. `collector[name]` is a synonym for `collector.mean(name)`.

constructor for the class :param data_dir: path to the directory containing the data :param transform: transforms to be appli

constructor for the class :param data_dir: path to the directory containing the data :param transform: transforms to be appli