Create a 1D, 2D, or 3D convolution module.

Make a standard normalization layer. :param channels: number of input channels. :return: an nn.Module for normalization.

Zero out the parameters of a module and return it.

Convert flow into middlebury color code image :param flow: optical flow map :return: optical flow image in middlebury color

This function disables printing when not in master process

Computation of error metrics between predicted and ground truth depths

A counter for the `thop` package to count the operations in an attention operation. Meant to be used like: macs, params = thop.pr

Used for tensorboard visualization

Perform evaluation on the FlyingChairs (test) split

Peform validation using the KITTI-2015 (train) split

Peform validation using the Sintel (train) split

Peform validation using the Things (test) split

feature1: [B, C, H, W] intrinsics: [B, 3, 3] pose: [B, 4, 4] depth: [B, D, H, W]

Initialize slurm distributed training environment. If argument ``port`` is not specified, then the master port will be system environment va

Return disparity read from filename.

Create a 1D, 2D, or 3D average pooling module.

Wrapper for grid_sample, uses pixel coordinates

Evaluate a function without caching intermediate activations, allowing for reduced memory at the expense of extra compute in the backward pas

Photometric augmentation

compute optical flow color map :param u: optical flow horizontal map :param v: optical flow vertical map :return: optical flow in col