Hugging Face's logo

Transformers documentation

PE Video (Perception Encoder Video)

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v5.3.0).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

This model was released on {release_date} and added to Hugging Face Transformers on 2025-12-16.

PE Video (Perception Encoder Video)

Overview

TODO

Usage

Basic usage

TODO

PeVideoVideoProcessor

class transformers.PeVideoVideoProcessor

< >

( **kwargs: typing_extensions.Unpack[transformers.processing_utils.VideosKwargs] )

__call__

< >

( videos **kwargs )

PeVideoProcessor

class transformers.PeVideoProcessor

< >

( *args **kwargs )

__call__

< >

( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor'], NoneType] = None text: str | list[str] | list[list[str]] | None = None videos: typing.Union[list['PIL.Image.Image'], numpy.ndarray, ForwardRef('torch.Tensor'), list[numpy.ndarray], list['torch.Tensor'], list[list['PIL.Image.Image']], list[list[numpy.ndarray]], list[list['torch.Tensor']], transformers.video_utils.URL, list[transformers.video_utils.URL], list[list[transformers.video_utils.URL]], transformers.video_utils.Path, list[transformers.video_utils.Path], list[list[transformers.video_utils.Path]], NoneType] = None audio: typing.Union[numpy.ndarray, ForwardRef('torch.Tensor'), collections.abc.Sequence[numpy.ndarray], collections.abc.Sequence['torch.Tensor'], NoneType] = None **kwargs: typing_extensions.Unpack[transformers.processing_utils.ProcessingKwargs] ) → BatchFeature

Parameters

  • images (PIL.Image.Image, np.ndarray, torch.Tensor, list[PIL.Image.Image], list[np.ndarray], list[torch.Tensor]) — The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. Both channels-first and channels-last formats are supported.
  • text (TextInput, PreTokenizedInput, list[TextInput], list[PreTokenizedInput], optional) — The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set is_split_into_words=True (to lift the ambiguity with a batch of sequences).
  • videos (np.ndarray, torch.Tensor, List[np.ndarray], List[torch.Tensor]) — The video or batch of videos to be prepared. Each video can be a 4D NumPy array or PyTorch tensor, or a nested list of 3D frames. Both channels-first and channels-last formats are supported.
  • audio (np.ndarray, torch.Tensor, list[np.ndarray], list[torch.Tensor]) — The audio or batch of audio to be prepared. Each audio can be a NumPy array or PyTorch tensor.
  • return_tensors (str or TensorType, optional) — If set, will return tensors of a particular framework. Acceptable values are:

    • 'pt': Return PyTorch torch.Tensor objects.
    • 'np': Return NumPy np.ndarray objects.

Returns

BatchFeature

A BatchFeature object with processed inputs in a dict format.

Main method to prepare for model inputs. This method forwards the each modality argument to its own processor along with kwargs. Please refer to the docstring of the each processor attributes for more information.

PeVideoEncoderConfig

class transformers.PeVideoEncoderConfig

< >

( vision_config: dict | transformers.configuration_utils.PreTrainedConfig | None = None hidden_size: int | None = 1792 intermediate_size: int | None = 4800 num_hidden_layers: int | None = 6 num_attention_heads: int | None = 14 num_key_value_heads: int | None = None head_dim: int | None = 128 hidden_act: str | None = 'silu' max_position_embeddings: int | None = 10000 initializer_range: float | None = 0.02 rms_norm_eps: float | None = 1e-05 rope_parameters: transformers.modeling_rope_utils.RopeParameters | dict | None = {'rope_theta': 20000} attention_bias: bool | None = False attention_dropout: float | None = 0.0 **kwargs )

Parameters

  • vision_config (Union[dict, ~configuration_utils.PreTrainedConfig], optional) — The config object or dictionary of the vision backbone.
  • hidden_size (int, optional, defaults to 1792) — Dimension of the hidden representations.
  • intermediate_size (int, optional, defaults to 4800) — Dimension of the MLP representations.
  • num_hidden_layers (int, optional, defaults to 6) — Number of hidden layers in the Transformer decoder.
  • num_attention_heads (int, optional, defaults to 14) — Number of attention heads for each attention layer in the Transformer decoder.
  • num_key_value_heads (int, optional) — This is the number of key_value heads that should be used to implement Grouped Query Attention. If num_key_value_heads=num_attention_heads, the model will use Multi Head Attention (MHA), if num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed by meanpooling all the original heads within that group. For more details, check out this paper. If it is not specified, will default to num_attention_heads.
  • head_dim (int, optional, defaults to 128) — The attention head dimension. If None, it will default to hidden_size // num_attention_heads
  • hidden_act (str, optional, defaults to silu) — The non-linear activation function (function or string) in the decoder. For example, "gelu", "relu", "silu", etc.
  • max_position_embeddings (int, optional, defaults to 10000) — The maximum sequence length that this model might ever be used with.
  • initializer_range (float, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
  • rms_norm_eps (float, optional, defaults to 1e-05) — The epsilon used by the rms normalization layers.
  • rope_parameters (Union[~modeling_rope_utils.RopeParameters, dict], optional, defaults to {'rope_theta' -- 20000}): Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain a value for rope_theta and optionally parameters used for scaling in case you want to use RoPE with longer max_position_embeddings.
  • attention_bias (bool, optional, defaults to False) — Whether to use a bias in the query, key, value and output projection layers during self-attention.
  • attention_dropout (float, optional, defaults to 0.0) — The dropout ratio for the attention probabilities.

This is the configuration class to store the configuration of a PeVideoModel. It is used to instantiate a Pe Video model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the facebook/pe-av-large

Configuration objects inherit from PreTrainedConfig and can be used to control the model outputs. Read the documentation from PreTrainedConfig for more information.

Example:

>>> from transformers import PeAudioEncoder, PeAudioEncoderConfig

>>> # Initializing a PeAudioEncoder style configuration
>>> configuration = PeAudioEncoderConfig()

>>> # Initializing a model from the pe-av-large style configuration
>>> model = PeAudioEncoder(configuration)

>>> # Accessing the model configuration
>>> configuration = model.config

PeVideoConfig

class transformers.PeVideoConfig

< >

( text_config = None video_config = None **kwargs )

Parameters

  • text_config (“) — The config object or dictionary of the text backbone.
  • video_config (dict or PreTrainedConfig, optional) — Configuration for the video encoder component.
  • ```python —

    from transformers import PeVideoModel, PeVideoConfig

This is the configuration class to store the configuration of a PeVideoModel. It is used to instantiate a Pe Video model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the facebook/pe-av-large

Configuration objects inherit from PreTrainedConfig and can be used to control the model outputs. Read the documentation from PreTrainedConfig for more information.

PeVideoModel

class transformers.PeVideoModel

< >

( config: PeVideoConfig )

forward

< >

( input_ids: Tensor pixel_values_videos: Tensor attention_mask: torch.Tensor | None = None padding_mask_videos: torch.Tensor | None = None return_loss: bool | None = None **kwargs )

PeVideoEncoder

class transformers.PeVideoEncoder

< >

( config: PeVideoEncoderConfig )

Parameters

  • config (PeVideoEncoderConfig) — Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

The PeVideo Encoder model.

This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

forward

< >

( pixel_values_videos: Tensor padding_mask_videos: torch.Tensor | None = None **kwargs )

Update on GitHub

←XLSR-Wav2Vec2 SAM2 Video→