Normlize image by given mean and std.

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

Defines the Unet submodule with skip connection. X -------------------identity---------------------- |-- downsampling -- |submodule| -

Feature fusion block.

Create a Unet-based generator

Feature fusion block.

Prepare sample for usage as network input.

Resize sample to given size (width, height).

Interpolation module.

Normlize image by given mean and std.

Prepare sample for usage as network input.

Resize sample to given size (width, height).

Resnet-based generator that consists of Resnet blocks between a few downsampling/upsampling operations. We adapt Torch code and idea from Justin

Modification of https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/levit.py: ConvNorm such that ConvTranspose2

Crop sample for batch-wise training. Image is of shape CxHxW

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

Gradient loss

Allows easier transportation of massive ammount of named gradio inputs. Allows adding visibility rules quicker.

Multi-Head Convolutional Attention

Network for monocular depth estimation.

Network for monocular depth estimation.

Defines a PatchGAN discriminator

Residual convolution module.

Residual convolution module.

Residual convolution module.

Residual convolution module.

A dictionary of running averages.

SILog loss (pixel-wise)

This class includes test options. It also includes shared options defined in BaseOptions.

This class takes a dictionary and creates a core_generation_funnel inp. Non-applicable parameters are silently discarded (no error)

Wrapper class of Dataset class that performs multi-threaded data loading

Cross entropy loss

Efficient Multi-Head Self Attention

Feature fusion block.

Feature fusion block.

This HTML class allows us to save images and write texts into a single HTML file. It consists of functions such as <add_header> (add a text head

Output class for Marigold monocular depth prediction pipeline. Args: depth_np (np.ndarray): Predicted depth map, with de

Next Convolution Block

Next Transformer Block

Normlize image by given mean and std.

Normlize image by given mean and std.

This class implements the pix2pix model, for learning a mapping from input images to output images given paired data. The model training require

Defines a 1x1 PatchGAN discriminator (pixelGAN)

Prepare sample for usage as network input.