Interpolation module.

A structure for storing masks and their related data in batched format. Implements basic filtering and concatenation.

An attention layer that allows for downscaling the size of the embedding after projection to queries, keys, and values.

Multi-size Segmentation Eavluator

Feature fusion block.

Residual convolution module.

Residual convolution module.

Residual convolution module.

Residual convolution module.

Resizes images to the longest side 'target_length', as well as provides methods for resizing coordinates and boxes. Provides methods for

! Input adapter for a (caching) istream. Ignores a UFT Byte Order Mark at beginning of input. Does not support changing the underlying std::streambuf

! @brief exception indicating access out of the defined range This exception is thrown in case a library function is called on an input parameter tha

Multi-head Attention block with relative position embeddings.

Transformer blocks with support of window attention and residual propagation blocks

r"""Creates a criterion that measures Learned Perceptual Image Patch Similarity (LPIPS). Arguments: net_type (str): the network type

Network for semantic segmentation.

Network for semantic segmentation.

Network for semantic segmentation.

Image to Patch Embedding.

Positional encoding using random spatial frequencies.

This model should not be called directly, but is used in ONNX export. It combines the prompt encoder, mask decoder, and mask postprocessing o