TimeSformer
개요
TimeSformer 모델은 Facebook Research에서 제안한 TimeSformer: Is Space-Time Attention All You Need for Video Understanding?에서 소개되었습니다. 이 연구는 첫 번째 비디오 Transformer로서, 행동 인식 분야에서 중요한 이정표가 되었습니다. 또한 Transformer 기반의 비디오 이해 및 분류 논문에 많은 영감을 주었습니다.
논문의 초록은 다음과 같습니다.
우리는 공간과 시간에 걸쳐 셀프 어텐션만을 사용하는 합성곱이 없는(convolution-free) 비디오 분류 방법을 제안합니다. 이 방법은 “TimeSformer”라고 불리며, 표준 Transformer 아키텍처를 비디오에 적용하여 프레임 수준 패치 시퀀스로부터 직접 시공간적 특징을 학습할 수 있게 합니다. 우리의 실험적 연구는 다양한 셀프 어텐션 방식을 비교하며, 시간적 어텐션과 공간적 어텐션을 각각의 블록 내에서 별도로 적용하는 “분할 어텐션” 방식이 고려된 설계 선택 중 가장 우수한 비디오 분류 정확도를 제공한다는 것을 시사합니다. 이 혁신적인 설계에도 불구하고, TimeSformer는 Kinetics-400 및 Kinetics-600을 포함한 여러 행동 인식 벤치마크에서 최첨단 결과를 달성했으며, 현재까지 보고된 가장 높은 정확도를 기록했습니다. 마지막으로, 3D 합성곱 네트워크와 비교했을 때, TimeSformer는 더 빠르게 학습할 수 있으며, 약간의 정확도 저하를 감수하면 테스트 효율성이 크게 향상되고, 1분 이상의 긴 비디오 클립에도 적용할 수 있습니다. 코드와 모델은 다음 링크에서 확인할 수 있습니다: https URL 링크.
이 모델은 fcakyon이 기여하였습니다. 원본 코드는 여기에서 확인할 수 있습니다.
사용 팁
다양한 사전 학습된 모델의 변형들이 있습니다. 사용하려는 데이터셋에 맞춰 사전 학습된 모델을 선택해야 합니다. 또한, 모델 크기에 따라 클립당 입력 프레임 수가 달라지므로, 사전 학습된 모델을 선택할 때 이 매개변수를 고려해야 합니다.
리소스
TimesformerConfig
class transformers.TimesformerConfig
< source >( image_size = 224 patch_size = 16 num_channels = 3 num_frames = 8 hidden_size = 768 num_hidden_layers = 12 num_attention_heads = 12 intermediate_size = 3072 hidden_act = 'gelu' hidden_dropout_prob = 0.0 attention_probs_dropout_prob = 0.0 initializer_range = 0.02 layer_norm_eps = 1e-06 qkv_bias = True attention_type = 'divided_space_time' drop_path_rate = 0 **kwargs )
Parameters
- image_size (
int, optional, defaults to 224) — The size (resolution) of each image. - patch_size (
int, optional, defaults to 16) — The size (resolution) of each patch. - num_channels (
int, optional, defaults to 3) — The number of input channels. - num_frames (
int, optional, defaults to 8) — The number of frames in each video. - hidden_size (
int, optional, defaults to 768) — Dimensionality of the encoder layers and the pooler layer. - num_hidden_layers (
int, optional, defaults to 12) — Number of hidden layers in the Transformer encoder. - num_attention_heads (
int, optional, defaults to 12) — Number of attention heads for each attention layer in the Transformer encoder. - intermediate_size (
int, optional, defaults to 3072) — Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder. - hidden_act (
strorfunction, optional, defaults to"gelu") — The non-linear activation function (function or string) in the encoder and pooler. If string,"gelu","relu","selu"and"gelu_new"are supported. - hidden_dropout_prob (
float, optional, defaults to 0.0) — The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. - attention_probs_dropout_prob (
float, optional, defaults to 0.0) — The dropout ratio for the attention probabilities. - initializer_range (
float, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices. - layer_norm_eps (
float, optional, defaults to 1e-06) — The epsilon used by the layer normalization layers. - qkv_bias (
bool, optional, defaults toTrue) — Whether to add a bias to the queries, keys and values. - attention_type (
str, optional, defaults to"divided_space_time") — The attention type to use. Must be one of"divided_space_time","space_only","joint_space_time". - drop_path_rate (
float, optional, defaults to 0) — The dropout ratio for stochastic depth.
This is the configuration class to store the configuration of a TimesformerModel. It is used to instantiate a TimeSformer 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 TimeSformer facebook/timesformer-base-finetuned-k600 architecture.
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 TimesformerConfig, TimesformerModel
>>> # Initializing a TimeSformer timesformer-base style configuration
>>> configuration = TimesformerConfig()
>>> # Initializing a model from the configuration
>>> model = TimesformerModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.configTimesformerModel
class transformers.TimesformerModel
< source >( config )
Parameters
- config (TimesformerConfig) — 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 bare TimeSformer Model transformer outputting raw hidden-states without any specific head on top. This model is 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
< source >( pixel_values: FloatTensor output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.BaseModelOutput or tuple(torch.FloatTensor)
Parameters
- pixel_values (
torch.FloatTensorof shape(batch_size, num_frames, num_channels, height, width)) — Pixel values. Pixel values can be obtained using AutoImageProcessor. SeeVideoMAEImageProcessor.preprocess()for details. - output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.
Returns
transformers.modeling_outputs.BaseModelOutput or tuple(torch.FloatTensor)
A transformers.modeling_outputs.BaseModelOutput or a tuple of
torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various
elements depending on the configuration (TimesformerConfig) and inputs.
-
last_hidden_state (
torch.FloatTensorof shape(batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the model. -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape(batch_size, sequence_length, hidden_size).Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
-
attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, sequence_length, sequence_length).Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
The TimesformerModel forward method, overrides the __call__ special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Examples:
>>> import av
>>> import numpy as np
>>> from transformers import AutoImageProcessor, TimesformerModel
>>> from huggingface_hub import hf_hub_download
>>> np.random.seed(0)
>>> def read_video_pyav(container, indices):
... '''
... Decode the video with PyAV decoder.
... Args:
... container (`av.container.input.InputContainer`): PyAV container.
... indices (`List[int]`): List of frame indices to decode.
... Returns:
... result (np.ndarray): np array of decoded frames of shape (num_frames, height, width, 3).
... '''
... frames = []
... container.seek(0)
... start_index = indices[0]
... end_index = indices[-1]
... for i, frame in enumerate(container.decode(video=0)):
... if i > end_index:
... break
... if i >= start_index and i in indices:
... frames.append(frame)
... return np.stack([x.to_ndarray(format="rgb24") for x in frames])
>>> def sample_frame_indices(clip_len, frame_sample_rate, seg_len):
... '''
... Sample a given number of frame indices from the video.
... Args:
... clip_len (`int`): Total number of frames to sample.
... frame_sample_rate (`int`): Sample every n-th frame.
... seg_len (`int`): Maximum allowed index of sample's last frame.
... Returns:
... indices (`List[int]`): List of sampled frame indices
... '''
... converted_len = int(clip_len * frame_sample_rate)
... end_idx = np.random.randint(converted_len, seg_len)
... start_idx = end_idx - converted_len
... indices = np.linspace(start_idx, end_idx, num=clip_len)
... indices = np.clip(indices, start_idx, end_idx - 1).astype(np.int64)
... return indices
>>> # video clip consists of 300 frames (10 seconds at 30 FPS)
>>> file_path = hf_hub_download(
... repo_id="nielsr/video-demo", filename="eating_spaghetti.mp4", repo_type="dataset"
... )
>>> container = av.open(file_path)
>>> # sample 8 frames
>>> indices = sample_frame_indices(clip_len=8, frame_sample_rate=4, seg_len=container.streams.video[0].frames)
>>> video = read_video_pyav(container, indices)
>>> image_processor = AutoImageProcessor.from_pretrained("MCG-NJU/videomae-base")
>>> model = TimesformerModel.from_pretrained("facebook/timesformer-base-finetuned-k400")
>>> # prepare video for the model
>>> inputs = image_processor(list(video), return_tensors="pt")
>>> # forward pass
>>> outputs = model(**inputs)
>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 1569, 768]TimesformerForVideoClassification
class transformers.TimesformerForVideoClassification
< source >( config )
Parameters
- config (TimesformerConfig) — 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.
TimeSformer Model transformer with a video classification head on top (a linear layer on top of the final hidden state of the [CLS] token) e.g. for ImageNet. This model is 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
< source >( pixel_values: typing.Optional[torch.Tensor] = None labels: typing.Optional[torch.Tensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.ImageClassifierOutput or tuple(torch.FloatTensor)
Parameters
- pixel_values (
torch.FloatTensorof shape(batch_size, num_frames, num_channels, height, width)) — Pixel values. Pixel values can be obtained using AutoImageProcessor. SeeVideoMAEImageProcessor.preprocess()for details. - output_attentions (
bool, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentionsunder returned tensors for more detail. - output_hidden_states (
bool, optional) — Whether or not to return the hidden states of all layers. Seehidden_statesunder returned tensors for more detail. - return_dict (
bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - labels (
torch.LongTensorof shape(batch_size,), optional) — Labels for computing the image classification/regression loss. Indices should be in[0, ..., config.num_labels - 1]. Ifconfig.num_labels == 1a regression loss is computed (Mean-Square loss), Ifconfig.num_labels > 1a classification loss is computed (Cross-Entropy).
Returns
transformers.modeling_outputs.ImageClassifierOutput or tuple(torch.FloatTensor)
A transformers.modeling_outputs.ImageClassifierOutput or a tuple of
torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various
elements depending on the configuration (TimesformerConfig) and inputs.
-
loss (
torch.FloatTensorof shape(1,), optional, returned whenlabelsis provided) — Classification (or regression if config.num_labels==1) loss. -
logits (
torch.FloatTensorof shape(batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax). -
hidden_states (
tuple(torch.FloatTensor), optional, returned whenoutput_hidden_states=Trueis passed or whenconfig.output_hidden_states=True) — Tuple oftorch.FloatTensor(one for the output of the embeddings, if the model has an embedding layer, + one for the output of each stage) of shape(batch_size, sequence_length, hidden_size). Hidden-states (also called feature maps) of the model at the output of each stage. -
attentions (
tuple(torch.FloatTensor), optional, returned whenoutput_attentions=Trueis passed or whenconfig.output_attentions=True) — Tuple oftorch.FloatTensor(one for each layer) of shape(batch_size, num_heads, patch_size, sequence_length).Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.
The TimesformerForVideoClassification forward method, overrides the __call__ special method.
Although the recipe for forward pass needs to be defined within this function, one should call the Module
instance afterwards instead of this since the former takes care of running the pre and post processing steps while
the latter silently ignores them.
Examples:
>>> import av
>>> import torch
>>> import numpy as np
>>> from transformers import AutoImageProcessor, TimesformerForVideoClassification
>>> from huggingface_hub import hf_hub_download
>>> np.random.seed(0)
>>> def read_video_pyav(container, indices):
... '''
... Decode the video with PyAV decoder.
... Args:
... container (`av.container.input.InputContainer`): PyAV container.
... indices (`List[int]`): List of frame indices to decode.
... Returns:
... result (np.ndarray): np array of decoded frames of shape (num_frames, height, width, 3).
... '''
... frames = []
... container.seek(0)
... start_index = indices[0]
... end_index = indices[-1]
... for i, frame in enumerate(container.decode(video=0)):
... if i > end_index:
... break
... if i >= start_index and i in indices:
... frames.append(frame)
... return np.stack([x.to_ndarray(format="rgb24") for x in frames])
>>> def sample_frame_indices(clip_len, frame_sample_rate, seg_len):
... '''
... Sample a given number of frame indices from the video.
... Args:
... clip_len (`int`): Total number of frames to sample.
... frame_sample_rate (`int`): Sample every n-th frame.
... seg_len (`int`): Maximum allowed index of sample's last frame.
... Returns:
... indices (`List[int]`): List of sampled frame indices
... '''
... converted_len = int(clip_len * frame_sample_rate)
... end_idx = np.random.randint(converted_len, seg_len)
... start_idx = end_idx - converted_len
... indices = np.linspace(start_idx, end_idx, num=clip_len)
... indices = np.clip(indices, start_idx, end_idx - 1).astype(np.int64)
... return indices
>>> # video clip consists of 300 frames (10 seconds at 30 FPS)
>>> file_path = hf_hub_download(
... repo_id="nielsr/video-demo", filename="eating_spaghetti.mp4", repo_type="dataset"
... )
>>> container = av.open(file_path)
>>> # sample 8 frames
>>> indices = sample_frame_indices(clip_len=8, frame_sample_rate=1, seg_len=container.streams.video[0].frames)
>>> video = read_video_pyav(container, indices)
>>> image_processor = AutoImageProcessor.from_pretrained("MCG-NJU/videomae-base-finetuned-kinetics")
>>> model = TimesformerForVideoClassification.from_pretrained("facebook/timesformer-base-finetuned-k400")
>>> inputs = image_processor(list(video), return_tensors="pt")
>>> with torch.no_grad():
... outputs = model(**inputs)
... logits = outputs.logits
>>> # model predicts one of the 400 Kinetics-400 classes
>>> predicted_label = logits.argmax(-1).item()
>>> print(model.config.id2label[predicted_label])
eating spaghetti