This module implements Vision Transformer (ViT) backbone in :paper:`vitdet`. "Exploring Plain Vision Transformer Backbones for Object Detecti

Multi-head Attention block with relative position embeddings.

r""" :class:`~pytorch_transformers.BertConfig` is the configuration class to store the configuration of a `BertModel`. Argum

Transformer blocks with support of window attention and residual propagation blocks

Scale the shorter edge to the given size, with a limit of `max_size` on the longer edge. If `max_size` is reached, then downscale so that the

Image to Patch Embedding.

The standard bottleneck residual block without the last activation layer. It contains 3 conv layers with kernels 1x1, 3x3, 1x1.

Base class for all configuration classes. Handle a few common parameters and methods for loading/downloading/saving configurations.