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

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

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

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

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

Evaluate Pascal VOC AP. It contains a synchronization, therefore has to be called from all ranks. Note that this is a rewrite of the off

Two linear layers for predicting Fast R-CNN outputs: (1) proposal-to-detection box regression deltas (2) classification scores

Two linear layers for predicting Fast R-CNN outputs: (1) proposal-to-detection box regression deltas (2) classification scores

A class that stores information about outputs of a Fast R-CNN head. It provides methods that are used to decode the outputs of a Fast R-CNN h

A class that stores information about outputs of a Fast R-CNN head. It provides methods that are used to decode the outputs of a Fast R-CNN h

Simple GCN layer as https://arxiv.org/abs/1609.02907

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

Deformable convolutional layer with configurable deformable groups, dilations and groups. Code is from: https://github.com/facebookr

Deformable convolutional layer with configurable deformable groups, dilations and groups. Code is from: https://github.com/facebookr

Generalized R-CNN. Any models that contains the following three components: 1. Per-image feature extraction (aka backbone) 2. Region prop

Generalized R-CNN. Any models that contains the following three components: 1. Per-image feature extraction (aka backbone) 2. Region prop

Region Proposal Network, introduced by :paper:`Faster R-CNN`.

Region Proposal Network, introduced by :paper:`Faster R-CNN`.

The ROIHeads in a typical "C4" R-CNN model, where the box and mask head share the cropping and the per-region feature computation by a Re

The ROIHeads in a typical "C4" R-CNN model, where the box and mask head share the cropping and the per-region feature computation by a Re

Intersetion Over Union (IoU) loss which supports three different IoU computations: * IoU * Linear IoU * gIoU

Intersetion Over Union (IoU) loss which supports three different IoU computations: * IoU * Linear IoU * gIoU

r"""NaiveGroupNorm implements Group Normalization with the high-level matrix operations in PyTorch. It is a temporary solution to export GN by ONN

r"""NaiveGroupNorm implements Group Normalization with the high-level matrix operations in PyTorch. It is a temporary solution to export GN by ONN

Evaluate Pascal VOC AP. It contains a synchronization, therefore has to be called from all ranks. Note that this is a rewrite of the off

Standard RPN classification and regression heads described in :paper:`Faster R-CNN`. Uses a 3x3 conv to produce a shared hidden state from wh

Standard RPN classification and regression heads described in :paper:`Faster R-CNN`. Uses a 3x3 conv to produce a shared hidden state from wh