Calculation of the statistics used by the FID. Params: -- images : Numpy array of dimension (n_images, hi, wi, 3). The values

Calculates the FID of two paths.

function to built button groups for one feature

create keras model with convolution layers of MobileNet and added fully connected layers on to top :param size_output: number of nodes in the

make feature_axis_target orthogonal to feature_axis_base :param feature_axis_target: features axes to decorrerelate, shape = (num_dim, num_f

tool funciton to generate image from latent variables :param latents: latent variables :return:

tool function

function to get names of images files and and pandas data-frame containing face attributes :param path_celeba_img: path to image files direc

function to load one image and the corresponding attributes, either using idx_img or img_name :param img_idx: index of image :param i

get a list of features from images :param x: generated images, of shape [num_images, height, width, rgb] :return: feature table, of shap

load data and preprocess before feeding it to Keras model :param num_images_total: :return:

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

function to normalize the slope of features axis so that they have the same length :param feature_slope: array of feature axis, shape = (num

save the images as hdf5 format