Evaluate point interactive IoU metrics.

Very simple multi-layer perceptron (also called FFN)

Attribute: polygons (list[ndarray]): list[ndarray]: polygons for this mask. Each ndarray has format [x, y, x, y, ...]

Evaluate AR for object proposals, AP for instance detection/segmentation, AP for keypoint detection outputs using COCO's metrics. See htt

Very simple multi-layer perceptron (also called FFN)

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

Evaluate semantic segmentation metrics.

The same as `fvcore.common.config.CfgNode`, but different in: 1. Use unsafe yaml loading by default. Note that this may lead to arbit

A callable which takes a dataset dict in Detectron2 Dataset format, and map it into a format used by MaskFormer for instance segmentation.

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

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

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

Visualizer that draws data about detection/segmentation on images. It contains methods like `draw_{text,box,circle,line,binary_mask,polygon}

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

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

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

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

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

Evaluate Panoptic Quality metrics on COCO using PanopticAPI. It saves panoptic segmentation prediction in `output_dir` It contains a syn

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 the model. This is the default call

Focal Modulation Args: dim (int): Number of input channels. proj_drop (float, optional): Dropout ratio of output. Default: 0.0

Focal Modulation Args: dim (int): Number of input channels. proj_drop (float, optional): Dropout ratio of output. Default: 0.0

Focal Modulation Block. Args: dim (int): Number of input channels. mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.

Focal Modulation Block. Args: dim (int): Number of input channels. mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.

Main class for mask classification semantic segmentation architectures.

Sets: source="canvas", tool="sketch"

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

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 is the multi-scale encoder in detection models, also named as pixel decoder in segmentation models.

A callable which takes a dataset dict in Detectron2 Dataset format, and map it into a format used by MaskFormer for panoptic segmentation.

A callable which takes a dataset dict in Detectron2 Dataset format, and map it into a format used by MaskFormer for panoptic segmentation.

A callable which takes a dataset dict in Detectron2 Dataset format, and map it into a format used by MaskFormer for semantic segmentation.

Multilayer perceptron.

Multilayer perceptron.

Multilayer perceptron.

Multilayer perceptron.

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

PASCALPARTEvaluator on open_vocabulary

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

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

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 Args: patch_size (int): Patch token size. Default: 4. in_chans (int): Number of input image channels. D

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

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

This class computes the loss for DETR. The process happens in two steps: 1) we compute one to one assignment (max iou score) between groun

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

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.

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

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

Unify different panoptic annotation/prediction formats

Computes and stores the average and current value.

Abstract base class for network backbones.

Enum of different color modes to use for instance visualizations.

FocalNet backbone. Args: pretrain_img_size (int): Input image size for training the pretrained model, used in absolute posti

FocalNet backbone. Args: pretrain_img_size (int): Input image size for training the pretrained model, used in absolute posti

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