Most parts are copied from torch.nn.modules.batchnorm._BatchNorm.

Add optimizer-specific arguments to the parser.

Add arguments to the parser for this LR scheduler.

Add optimizer-specific arguments to the parser.

Add optimizer-specific arguments to the parser.

Add arguments to the parser for this LR scheduler.

shrink learning rate for pytorch

r"""AlexNet model architecture from the `"One weird trick..." <https://arxiv.org/abs/1404.5997>`_ paper.

Converts a one-channel grayscale image to a color heatmap image

Constructs a ResNet model.

Args: input_: A (batch, input_size) tensor containing input features. hx: A tuple (h_0, c_0), which c

Compute the mean and std value of dataset.

Initialize embedding

Initialize linear transformation

Initialize lstm

Init layer parameters.

Return a kwarg dictionary that will be used to override optimizer args stored in checkpoints. This allows us to load a checkpoint and

Return a kwarg dictionary that will be used to override optimizer args stored in checkpoints. This allows us to load a checkpoint and

Return a kwarg dictionary that will be used to override optimizer args stored in checkpoints. This allows us to load a checkpoint and

Constructs a ResNet model.

Wraps hidden states in new Variables, to detach them from their history.

Constructs a ResNet model.

Constructs a ResNeXt.

Construct ResNeXt-101.

Construct ResNeXt-152.

Construct ResNeXt-50.