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 mo

Renderer used for visualizing the SMPL model Code adapted from https://github.com/vchoutas/smplify-x

SMPL Iterative Regressor with ResNet50 backbone

This class represents a bounding box detection in a single image. Parameters ---------- tlwh : array_like Bounding box in fo

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

Outputs mesh texture

Class used for extracting frames from a video file.

Class used for loading and saving videos.

Mark this track as missed (no association at the current time step).

This is the multi-target tracker. Parameters ---------- metric : nn_matching.NearestNeighborDistanceMetric A distance metric

A nearest neighbor distance metric that, for each target, returns the closest distance to any sample that has been observed so far. Para

Class for autogenerated text clips. Creates an ImageClip originating from a script-generated text image. Requires ImageMagick. Parameter

Enumeration type for the single target track state. Newly created tracks are classified as `tentative` until enough evidence has been collect