vis4d.model.detect.yolox¶

YOLOX model implementation and runtime.

Classes

YOLOX(num_classes[, basemodel, fpn, ...])

YOLOX detector.

class YOLOX(num_classes, basemodel=None, fpn=None, yolox_head=None, postprocessor=None, weights=None)[source]¶

YOLOX detector.

Creates an instance of the class.

Parameters:

num_classes (int) – Number of classes.
basemodel (BaseModel, optional) – Base model. Defaults to None. If None, will use CSPDarknet.
fpn (FeaturePyramidProcessing, optional) – Feature Pyramid Processing. Defaults to None. If None, will use YOLOXPAFPN.
yolox_head (YOLOXHead, optional) – YOLOX head. Defaults to None. If None, will use YOLOXHead.
postprocessor (YOLOXPostprocess, optional) – Post processor. Defaults to None. If None, will use YOLOXPostprocess.
weights (None | str, optional) – Weights to load for model. If set to “mmdet”, will load MMDetection pre-trained weights. Defaults to None.

forward(images, input_hw=None, original_hw=None)[source]¶

Forward pass.

Parameters:

images (torch.Tensor) – Input images.
input_hw (None | list[tuple[int, int]], optional) – Input image resolutions. Defaults to None.
original_hw (None | list[tuple[int, int]], optional) – Original image resolutions (before padding and resizing). Required for testing. Defaults to None.

Returns:

Either raw model outputs (for training) or: predicted outputs (for testing).

Return type:

YOLOXOut | DetOut

forward_test(images, images_hw, original_hw)[source]¶

Forward testing stage.

Parameters:

images (torch.Tensor) – Input images.
images_hw (list[tuple[int, int]]) – Input image resolutions.
original_hw (list[tuple[int, int]]) – Original image resolutions (before padding and resizing).

Returns:

Predicted outputs.

Return type:

DetOut

forward_train(images)[source]¶

Forward training stage.