A semi-supervised dataset class for depth estimation tasks. This dataset supports both labeled and unlabeled data for semi-supervised le

Apply Gaussian Blur to the PIL image.

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor, or keep as is if already a tensor.

Residual convolution module.

Residual convolution module.

Track a series of values and provide access to smoothed values over a window or the global series average.

Feature fusion block.

Feature fusion block.

Kozachenko-Leonenko entropic loss regularizer from Sablayrolles et al. - 2018 - Spreading vectors for similarity search

Linear layer to train on top of frozen features

Normlize image by given mean and std.

Prepare sample for usage as network input.

Resize sample to given size (width, height).

A dictionary of running averages.

Computes and stores the average and current value

Gets knn of test features from all processes on a chunk of the train features Each rank gets a chunk of the train features as well as a chun

Normlize image by given mean and std.

2D image to patch embedding: (B,C,H,W) -> (B,N,D) Args: img_size: Image size. patch_size: Patch token size. in_chans

2D image to patch embedding: (B,C,H,W) -> (B,N,D) Args: img_size: Image size. patch_size: Patch token size. in_chans

Prepare sample for usage as network input.

Resize sample to given size (width, height).