Similar to roll but for only one dim. Args: x: A PyTorch tensor. shift: Amount to roll. dim: Which dimension to roll.

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized portio

Calculate loss given Discriminator's output and grount truth labels. Parameters: prediction (tensor) - - tpyically the prediction

(mask_len_range): given in (min, max) tuple. Specifies the range of box size in each dimension (mask_prob_range): for the cas

Extract values from a 1-D numpy array for a batch of indices. :param arr: the 1-D numpy array. :param timesteps: a tensor of indices int

Calculate the gradient penalty loss, used in WGAN-GP paper https://arxiv.org/abs/1704.00028 Arguments: netD (network) -- dis

Convert primitive modules to float16.

Convert primitive modules to float32, undoing convert_module_to_f16().

Convert the torso of the model to float16.

Convert the torso of the model to float32.

Convert the torso of the model to float32.

Generate a mask of weights penalizing values close to the boundaries

Extract patches from images and put them in the C output dimension. :param padding: :param images: [batch, channels, in_rows, in_cols]. A

FFT with shifting DC to the center of the image

Apply centered 2 dimensional Fast Fourier Transform. Args: data: Complex valued input data containing at least 3 dimensions:

Transfer flow map to image. Part of code forked from flownet.

Apply the module to `x` given `emb` timestep embeddings.