dgs.models.embedding_generator.pose_based.LinearPBEG.forward

LinearPBEG.forward(ds: State) → tuple[torch.Tensor, torch.Tensor]

Forward pass of the linear pose-based embedding generator.

Params:

ds: Either an already flattened tensor, containing the values of the key-point coordinates and the

bounding box as a single tensor of shape [B x self.J * self.j_dim + 4], or the key-point coordinates and bounding boxes as tensors of shapes [B x self.J] and [B x 4].

Returns:

This modules’ prediction. embeddings is describing the key-points and bounding boxes as a tensor of shape [B x E]. ids is the probability to predict a class. The ids are given as a tensor of shape [B x num_classes] with values in range [0, 1].