Compute learning rate using chainable form of the scheduler.

Returns parameters that we want to optimize over. :param opt_over: comma separated list, e.g. "net,input" or "net" :param net: network

Linear warmup for warmup_steps, optionally with cosine annealing or linear decay to 0 at total_steps.

assumes C x W x H [0..1] :param img_np_list: :return:

Converts image in numpy.array to torch.Tensor. From C x W x H [0..1] to C x W x H [0..1] :param img_np: :return:

Draws images in a grid Args: images_np: list of images, each image is np.array of size 3xHxW or 1xHxW nrow: how many images

loads makes it divisible :param file_name: :return: the numpy representation of the image

same as matlab rgb2ycbcr only_y: only return Y channel Input: uint8, [0, 255] float, [0, 1]

:param name: :param dict graph_dict: a dict from the name of the list to the list itself. :return:

Scan a directory to find the interested files. Args: dir_path (str): Path of the directory. suffix (str | tuple(str), optional):

Converts an image in torch.Tensor format to np.array. From 1 x C x W x H [0..1] to C x W x H [0..1] :param img_var: :return:

same as matlab ycbcr2rgb Input: uint8, [0, 255] float, [0, 1]

same as matlab ycbcr2rgb Input: uint8, [0, 255] float, [0, 1]