Construct a Unet generator Parameters: input_nc (int) -- the number of channels in input images output_nc (int) -- th

Construct a Unet submodule with skip connections. Parameters: outer_nc (int) -- the number of filters in the outer conv layer

Construct a PatchGAN discriminator Parameters: input_nc (int) -- the number of channels in input images ndf (int)

:param base_dir: path to VOC dataset directory :param split: train/val :param transform: transform to apply

Reduce the sum and square-sum, compute the statistics, and broadcast it.

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

Create a discriminator Parameters: input_nc (int) -- the number of channels in input images ndf (int) -- the number

Create a generator Parameters: input_nc (int) -- the number of channels in input images output_nc (int) -- the number of channels

This definition generalize to real valued pred and target vector. This should be differentiable. pred: tensor with first dimension as batch

Draw the mask probability for each img and save them to the save path :param prediction: [2, h, w] numpy :param save_path: string including

Draw the entropy information for each img and save them to the save path :param prediction: [2, h, w] numpy :param save_path: string incl

Draw the mask probability for each img and save them to the save path :param prediction: [2, h, w] numpy :param save_path: string including

Standard forward

Standard forward.

Return a learning rate scheduler Parameters: optimizer -- the optimizer of the network opt (option class) -- stores all