Very simple multi-layer perceptron (also called FFN)

This is a more standard version of the position embedding, very similar to the one used by the Attention is all you need paper, generalized t

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

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

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

This class computes an assignment between the targets and the predictions of the network For efficiency reasons, the targets don't include the no

This class computes the loss for DETR. The process happens in two steps: 1) we compute hungarian assignment between ground truth boxes and

Randomly apply an augmentation with a given probability.

Randomly crop a rectangle region out of an image.

Flip the image horizontally or vertically with the given probability.

This method returns a copy of this image, rotated the given number of degrees counter clockwise around the given center.

Only match in the first frame where the object appears in the GT.

Create a simple end-to-end predictor with the given config that runs on single device for a single input image. Compared to using the mod

This class stores the segmentation masks for all objects in one video, in the form of bitmaps. Attributes: tensor: bool Tensor o

A predictor that runs the model asynchronously, possibly on >1 GPUs. Because rendering the visualization takes considerably amount of time,

Multi-head Attention block with relative position embeddings.

A basic Swin Transformer layer for one stage. Args: dim (int): Number of feature channels depth (int): Depths of this stage.

Transformer blocks with support of window attention and residual propagation blocks

Combines data loaders using the provided sampling ratios

If `crop_size` is smaller than the input image size, then it uses a random crop of the crop size. If `crop_size` is larger than the input ima

This class computes an assignment between the targets and the predictions of the network For efficiency reasons, the targets don't include the no

Very simple multi-layer perceptron (also called FFN)

Very simple multi-layer perceptron (also called FFN)

Multilayer perceptron.

Params for coco evaluation api

Params for coco evaluation api

Image to Patch Embedding Args: patch_size (int): Patch token size. Default: 4. in_chans (int): Number of input image channels. Def

Image to Patch Embedding.

Positional encoding using random spatial frequencies.

This is a more standard version of the position embedding, very similar to the one used by the Attention is all you need paper, generalized t

Flip the image horizontally or vertically with the given probability.

Takes target size as input and randomly scales the given target size between `min_scale` and `max_scale`. It then scales the input image such

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

This class computes the loss for DETR. The process happens in two steps: 1) we compute hungarian assignment between ground truth boxes and

Swin Transformer Block. Args: dim (int): Number of input channels. num_heads (int): Number of attention heads. window_size

Extension of the Trainer class adapted to MaskFormer.

This class computes the loss for DETR. The process happens in two steps: 1) we compute hungarian assignment between ground truth boxes and

This class computes the loss for DETR. The process happens in two steps: 1) we compute hungarian assignment between ground truth boxes and

Window based multi-head self attention (W-MSA) module with relative position bias. It supports both of shifted and non-shifted window. Args:

A callable which takes a dataset dict in Detectron2 Dataset format, and map it into a format used by MaskFormer. This dataset mapper app

A callable which takes a dataset dict in Detectron2 Dataset format, and map it into a format used by MaskFormer. This dataset mapper app