fastvideo.v1.dataset.utils

Module Contents

Functions

collate_latents_embs_masks
get_torch_tensors_from_row_dict	Get the latents and prompts from a row dictionary.
pad	Pad or crop an embedding [L, D] to exactly padding_length tokens. Return:

API

fastvideo.v1.dataset.utils.collate_latents_embs_masks(batch_to_process, text_padding_length, keys) → tuple[torch.Tensor, torch.Tensor, torch.Tensor, List[str]]

fastvideo.v1.dataset.utils.get_torch_tensors_from_row_dict(row_dict, keys) → Dict[str, Any]

Get the latents and prompts from a row dictionary.

fastvideo.v1.dataset.utils.pad(t: torch.Tensor, padding_length: int) → torch.Tensor

Pad or crop an embedding [L, D] to exactly padding_length tokens. Return:

• [L, D] tensor in pinned CPU memory

• [L] attention mask in pinned CPU memory