Update statistics

Make dimensions divisible by d :param pil img: :param d: :return:

Load an image and resize to a cpecific size. Args: path: path to image imsize: tuple or scalar with dimensions; -1 for `no resize

Converts image in PIL format to np.array. From W x H x C [0...255] to C x W x H [0..1]

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

Return an activation function given a string

Add JPG compression artifacts. Args: img (Numpy array): Input image, shape (h, w, c), range [0, 1], float32. quality (float): JPG

bgr version of rgb2ycbcr only_y: only return Y channel Input: uint8, [0, 255] float, [0, 1]

Flip testing with X4 self ensemble, i.e., normal, flip H, flip W, flip H and W Args: model (PyTorch model) inp (Tensor): inputs de

Get the position from a period list. It will return the index of the right-closest number in the period list. For example, the cumulative_per

Converts image in np.array format to PIL image. From C x W x H [0..1] to W x H x C [0...255] :param img_np: :return:

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]

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:

Make dimensions divisible by d image is [1, 3, W, H] or [3, W, H] :param pil img: :param d: :return:

Creates a grid from a list of images by concatenating them. :param images_np: :param nrow: :return:

Load PIL image.

Converts image in np.array format to PIL image. From C x W x H [0..1] to W x H x C [0...255] :param img_np: :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:

Reset all statistics

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