InstructBlipVideo
Overview
Overview
The InstructBLIPVideo is an extension of the models proposed in InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning by Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, Steven Hoi. InstructBLIPVideo uses the same architecture as InstructBLIP and works with the same checkpoints as InstructBLIP. The only difference is the ability to process videos.
The abstract from the paper is the following:
General-purpose language models that can solve various language-domain tasks have emerged driven by the pre-training and instruction-tuning pipeline. However, building general-purpose vision-language models is challenging due to the increased task discrepancy introduced by the additional visual input. Although vision-language pre-training has been widely studied, vision-language instruction tuning remains relatively less explored. In this paper, we conduct a systematic and comprehensive study on vision-language instruction tuning based on the pre-trained BLIP-2 models. We gather a wide variety of 26 publicly available datasets, transform them into instruction tuning format and categorize them into two clusters for held-in instruction tuning and held-out zero-shot evaluation. Additionally, we introduce instruction-aware visual feature extraction, a crucial method that enables the model to extract informative features tailored to the given instruction. The resulting InstructBLIP models achieve state-of-the-art zero-shot performance across all 13 held-out datasets, substantially outperforming BLIP-2 and the larger Flamingo. Our models also lead to state-of-the-art performance when finetuned on individual downstream tasks (e.g., 90.7% accuracy on ScienceQA IMG). Furthermore, we qualitatively demonstrate the advantages of InstructBLIP over concurrent multimodal models.
![drawing](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/instructblip_architecture.jpg)
This model was contributed by RaushanTurganbay. The original code can be found here.
Usage tips
- The model was trained by sampling 4 frames per video, so it’s recommended to sample 4 frames
InstructBlipVideoConfig
class transformers.InstructBlipVideoConfig
< source >( vision_config = None qformer_config = None text_config = None num_query_tokens = 32 **kwargs )
Parameters
- vision_config (
dict
, optional) — Dictionary of configuration options used to initialize InstructBlipVideoVisionConfig. - qformer_config (
dict
, optional) — Dictionary of configuration options used to initialize InstructBlipVideoQFormerConfig. - text_config (
dict
, optional) — Dictionary of configuration options used to initialize any PretrainedConfig. - num_query_tokens (
int
, optional, defaults to 32) — The number of query tokens passed through the Transformer. - kwargs (optional) — Dictionary of keyword arguments.
InstructBlipVideoConfig is the configuration class to store the configuration of a InstructBlipVideoForConditionalGeneration. It is used to instantiate a Instructblipvideo model according to the specified arguments, defining the vision model, Q-Former model and language model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the Instructblipvideo Salesforce/instruct-blip-flan-t5 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 (
... InstructBlipVideoVisionConfig,
... InstructBlipVideoQFormerConfig,
... OPTConfig,
... InstructBlipVideoConfig,
... InstructBlipVideoForConditionalGeneration,
... )
>>> # Initializing a InstructBlipVideoConfig with Salesforce/instruct-blip-flan-t5 style configuration
>>> configuration = InstructBlipVideoConfig()
>>> # Initializing a InstructBlipVideoForConditionalGeneration (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration
>>> model = InstructBlipVideoForConditionalGeneration(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
>>> # We can also initialize a InstructBlipVideoConfig from a InstructBlipVideoVisionConfig, InstructBlipVideoQFormerConfig and any PretrainedConfig
>>> # Initializing Instructblipvideo vision, Instructblipvideo Q-Former and language model configurations
>>> vision_config = InstructBlipVideoVisionConfig()
>>> qformer_config = InstructBlipVideoQFormerConfig()
>>> text_config = OPTConfig()
>>> config = InstructBlipVideoConfig.from_text_vision_configs(vision_config, qformer_config, text_config)
from_vision_qformer_text_configs
< source >( vision_config: InstructBlipVideoVisionConfig qformer_config: InstructBlipVideoQFormerConfig text_config: PretrainedConfig **kwargs ) → InstructBlipVideoConfig
Instantiate a InstructBlipVideoConfig (or a derived class) from a Instructblipvideo vision model, Q-Former and language model configurations.
InstructBlipVideoVisionConfig
class transformers.InstructBlipVideoVisionConfig
< source >( hidden_size = 1408 intermediate_size = 6144 num_hidden_layers = 39 num_attention_heads = 16 image_size = 224 patch_size = 14 hidden_act = 'gelu' layer_norm_eps = 1e-06 attention_dropout = 0.0 initializer_range = 1e-10 qkv_bias = True **kwargs )
Parameters
- hidden_size (
int
, optional, defaults to 1408) — Dimensionality of the encoder layers and the pooler layer. - intermediate_size (
int
, optional, defaults to 6144) — Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder. - num_hidden_layers (
int
, optional, defaults to 39) — Number of hidden layers in the Transformer encoder. - num_attention_heads (
int
, optional, defaults to 16) — Number of attention heads for each attention layer in the Transformer encoder. - image_size (
int
, optional, defaults to 224) — The size (resolution) of each image. - patch_size (
int
, optional, defaults to 14) — The size (resolution) of each patch. - hidden_act (
str
orfunction
, 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"
`"gelu"
are supported. to 1e-5): The epsilon used by the layer normalization layers. - layer_norm_eps (
float
, optional, defaults to 1e-06) — The epsilon used by the layer normalization layers. - attention_dropout (
float
, optional, defaults to 0.0) — The dropout ratio for the attention probabilities. - initializer_range (
float
, optional, defaults to 1e-10) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices. - qkv_bias (
bool
, optional, defaults toTrue
) — Whether to add a bias to the queries and values in the self-attention layers.
This is the configuration class to store the configuration of a InstructBlipVideoVisionModel. It is used to instantiate a Instructblipvideo vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration defaults will yield a similar configuration to that of the Instructblipvideo Salesforce/instruct-blip-flan-t5 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 InstructBlipVideoVisionConfig, InstructBlipVideoVisionModel
>>> # Initializing a InstructBlipVideoVisionConfig with Salesforce/instruct-blip-flan-t5 style configuration
>>> configuration = InstructBlipVideoVisionConfig()
>>> # Initializing a InstructBlipVideoVisionModel (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration
>>> model = InstructBlipVideoVisionModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
InstructBlipVideoQFormerConfig
class transformers.InstructBlipVideoQFormerConfig
< source >( vocab_size = 30522 hidden_size = 768 num_hidden_layers = 12 num_attention_heads = 12 intermediate_size = 3072 hidden_act = 'gelu' hidden_dropout_prob = 0.1 attention_probs_dropout_prob = 0.1 max_position_embeddings = 512 initializer_range = 0.02 layer_norm_eps = 1e-12 pad_token_id = 0 position_embedding_type = 'absolute' cross_attention_frequency = 2 encoder_hidden_size = 1408 **kwargs )
Parameters
- vocab_size (
int
, optional, defaults to 30522) — Vocabulary size of the Q-Former model. Defines the number of different tokens that can be represented by theinputs_ids
passed when calling the model. - 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” (often named feed-forward) layer in the Transformer encoder. - hidden_act (
str
orCallable
, optional, defaults to"gelu"
) — The non-linear activation function (function or string) in the encoder and pooler. If string,"gelu"
,"relu"
,"silu"
and"gelu_new"
are supported. - hidden_dropout_prob (
float
, optional, defaults to 0.1) — The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. - attention_probs_dropout_prob (
float
, optional, defaults to 0.1) — The dropout ratio for the attention probabilities. - max_position_embeddings (
int
, optional, defaults to 512) — The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048). - 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-12) — The epsilon used by the layer normalization layers. - pad_token_id (
int
, optional, defaults to 0) — Token id used for padding sequences. - position_embedding_type (
str
, optional, defaults to"absolute"
) — Type of position embedding. Choose one of"absolute"
,"relative_key"
,"relative_key_query"
. For positional embeddings use"absolute"
. For more information on"relative_key"
, please refer to Self-Attention with Relative Position Representations (Shaw et al.). For more information on"relative_key_query"
, please refer to Method 4 in Improve Transformer Models with Better Relative Position Embeddings (Huang et al.). - cross_attention_frequency (
int
, optional, defaults to 2) — The frequency of adding cross-attention to the Transformer layers. - encoder_hidden_size (
int
, optional, defaults to 1408) — The hidden size of the hidden states for cross-attention.
This is the configuration class to store the configuration of a InstructBlipVideoQFormerModel. It is used to instantiate a Instructblipvideo Querying Transformer (Q-Former) 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 Instructblipvideo Salesforce/instruct-blip-flan-t5 architecture. Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.
Note that InstructBlipVideoQFormerModel is very similar to BertLMHeadModel with interleaved cross-attention.
Examples:
>>> from transformers import InstructBlipVideoQFormerConfig, InstructBlipVideoQFormerModel
>>> # Initializing a Instructblipvideo Salesforce/instruct-blip-flan-t5 style configuration
>>> configuration = InstructBlipVideoQFormerConfig()
>>> # Initializing a model (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration
>>> model = InstructBlipVideoQFormerModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
InstructBlipVideoProcessor
class transformers.InstructBlipVideoProcessor
< source >( image_processor tokenizer qformer_tokenizer = None **kwargs )
Parameters
- image_processor (
InstructBlipVideoImageProcessor
) — An instance of InstructBlipVideoImageProcessor. The image processor is a required input. - tokenizer (
AutoTokenizer
) — An instance of [‘PreTrainedTokenizer`]. The tokenizer is a required input. - qformer_tokenizer (
AutoTokenizer
, optional) — An instance of [‘PreTrainedTokenizer`]. The Q-Former tokenizer is a required input.
Constructs an InstructBLIPVideo processor which wraps a InstructBLIP image processor and a LLaMa/T5 tokenizer into a single processor.
InstructBlipVideoProcessor offers all the functionalities of InstructBlipVideoImageProcessor and AutoTokenizer. See the
docstring of __call__()
and decode() for more information.
This method forwards all its arguments to PreTrainedTokenizer’s batch_decode(). Please refer to the docstring of this method for more information.
This method forwards all its arguments to PreTrainedTokenizer’s decode(). Please refer to the docstring of this method for more information.
InstructBlipVideoImageProcessor
class transformers.InstructBlipVideoImageProcessor
< source >( do_resize: bool = True size: Dict = None resample: Resampling = <Resampling.BICUBIC: 3> do_rescale: bool = True rescale_factor: Union = 0.00392156862745098 do_normalize: bool = True image_mean: Union = None image_std: Union = None do_convert_rgb: bool = True **kwargs )
Parameters
- do_resize (
bool
, optional, defaults toTrue
) — Whether to resize the image’s (height, width) dimensions to the specifiedsize
. Can be overridden by thedo_resize
parameter in thepreprocess
method. - size (
dict
, optional, defaults to{"height" -- 384, "width": 384}
): Size of the output image after resizing. Can be overridden by thesize
parameter in thepreprocess
method. - resample (
PILImageResampling
, optional, defaults toResampling.BICUBIC
) — Resampling filter to use if resizing the image. Only has an effect ifdo_resize
is set toTrue
. Can be overridden by theresample
parameter in thepreprocess
method. - do_rescale (
bool
, optional, defaults toTrue
) — Whether to rescale the image by the specified scalerescale_factor
. Can be overridden by thedo_rescale
parameter in thepreprocess
method. - rescale_factor (
int
orfloat
, optional, defaults to1/255
) — Scale factor to use if rescaling the image. Only has an effect ifdo_rescale
is set toTrue
. Can be overridden by therescale_factor
parameter in thepreprocess
method. - do_normalize (
bool
, optional, defaults toTrue
) — Whether to normalize the image. Can be overridden by thedo_normalize
parameter in thepreprocess
method. Can be overridden by thedo_normalize
parameter in thepreprocess
method. - image_mean (
float
orList[float]
, optional, defaults toIMAGENET_STANDARD_MEAN
) — Mean to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by theimage_mean
parameter in thepreprocess
method. Can be overridden by theimage_mean
parameter in thepreprocess
method. - image_std (
float
orList[float]
, optional, defaults toIMAGENET_STANDARD_STD
) — Standard deviation to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by theimage_std
parameter in thepreprocess
method. Can be overridden by theimage_std
parameter in thepreprocess
method. - do_convert_rgb (
bool
, optional, defaults toTrue
) — Whether to convert the image to RGB.
Constructs a InstructBLIPVideo image processor.
preprocess
< source >( images: Union = None do_resize: Optional = None size: Optional = None resample: Resampling = None do_rescale: Optional = None rescale_factor: Optional = None do_normalize: Optional = None image_mean: Union = None image_std: Union = None return_tensors: Union = None do_convert_rgb: bool = None data_format: ChannelDimension = <ChannelDimension.FIRST: 'channels_first'> input_data_format: Union = None )
Parameters
- videos (
VideoInput
) — Video frames to preprocess. Expects a single or batch of videos as a list of frames with pixel values ranging from 0 to 255. If passing in video with pixel values between 0 and 1, setdo_rescale=False
. - do_resize (
bool
, optional, defaults toself.do_resize
) — Whether to resize the video. - size (
Dict[str, int]
, optional, defaults toself.size
) — Controls the size of the video afterresize
. The shortest edge of the image is resized tosize["shortest_edge"]
whilst preserving the aspect ratio. If the longest edge of this resized image is >int(size["shortest_edge"] * (1333 / 800))
, then the image is resized again to make the longest edge equal toint(size["shortest_edge"] * (1333 / 800))
. - resample (
PILImageResampling
, optional, defaults toself.resample
) — Resampling filter to use if resizing the video. Only has an effect ifdo_resize
is set toTrue
. - do_rescale (
bool
, optional, defaults toself.do_rescale
) — Whether to rescale the video values between [0 - 1]. - rescale_factor (
float
, optional, defaults toself.rescale_factor
) — Rescale factor to rescale the video by ifdo_rescale
is set toTrue
. - do_normalize (
bool
, optional, defaults toself.do_normalize
) — Whether to normalize the video. - image_mean (
float
orList[float]
, optional, defaults toself.image_mean
) — Image mean to normalize the video by ifdo_normalize
is set toTrue
. - image_std (
float
orList[float]
, optional, defaults toself.image_std
) — Image standard deviation to normalize the video by ifdo_normalize
is set toTrue
. - do_convert_rgb (
bool
, optional, defaults toself.do_convert_rgb
) — Whether to convert the image to RGB. - return_tensors (
str
orTensorType
, optional) — The type of tensors to return. Can be one of:- Unset: Return a list of
np.ndarray
. TensorType.TENSORFLOW
or'tf'
: Return a batch of typetf.Tensor
.TensorType.PYTORCH
or'pt'
: Return a batch of typetorch.Tensor
.TensorType.NUMPY
or'np'
: Return a batch of typenp.ndarray
.TensorType.JAX
or'jax'
: Return a batch of typejax.numpy.ndarray
.
- Unset: Return a list of
- data_format (
ChannelDimension
orstr
, optional, defaults toChannelDimension.FIRST
) — The channel dimension format for the output image. Can be one of:"channels_first"
orChannelDimension.FIRST
: image in (num_channels, height, width) format."channels_last"
orChannelDimension.LAST
: image in (height, width, num_channels) format.- Unset: Use the channel dimension format of the input image.
- input_data_format (
ChannelDimension
orstr
, optional) — The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of:"channels_first"
orChannelDimension.FIRST
: image in (num_channels, height, width) format."channels_last"
orChannelDimension.LAST
: image in (height, width, num_channels) format."none"
orChannelDimension.NONE
: image in (height, width) format.
Preprocess a video or batch of images/videos.
InstructBlipVideoVisionModel
class transformers.InstructBlipVideoVisionModel
< source >( config: InstructBlipVideoVisionConfig )
forward
< source >( pixel_values: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None return_dict: Optional = None interpolate_pos_encoding: bool = False ) → transformers.modeling_outputs.BaseModelOutputWithPooling or tuple(torch.FloatTensor)
Parameters
- pixel_values (
torch.FloatTensor
of shape(batch_size, num_channels, height, width)
) — Pixel values. Pixel values can be obtained using InstructBlipVideoProcessor. SeeInstructBlipVideoProcessor.__call__()
for details. - output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. - return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - interpolate_pos_encoding (
bool
, optional, defaults toFalse
) — Whether to interpolate the pre-trained position encodings.
Returns
transformers.modeling_outputs.BaseModelOutputWithPooling or tuple(torch.FloatTensor)
A transformers.modeling_outputs.BaseModelOutputWithPooling 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 (<class 'transformers.models.instructblipvideo.configuration_instructblipvideo.InstructBlipVideoVisionConfig'>
) and inputs.
-
last_hidden_state (
torch.FloatTensor
of shape(batch_size, sequence_length, hidden_size)
) — Sequence of hidden-states at the output of the last layer of the model. -
pooler_output (
torch.FloatTensor
of shape(batch_size, hidden_size)
) — Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining. -
hidden_states (
tuple(torch.FloatTensor)
, optional, returned whenoutput_hidden_states=True
is 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=True
is 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 InstructBlipVideoVisionModel 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.
InstructBlipVideoQFormerModel
class transformers.InstructBlipVideoQFormerModel
< source >( config: InstructBlipVideoQFormerConfig )
Querying Transformer (Q-Former), used in Instructblipvideo. Slightly modified from BLIP-2 as it also takes the instruction as input.
forward
< source >( input_ids: LongTensor attention_mask: Optional = None position_ids: Optional = None query_embeds: Optional = None head_mask: Optional = None encoder_hidden_states: Optional = None encoder_attention_mask: Optional = None past_key_values: Optional = None use_cache: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None return_dict: Optional = None )
encoder_hidden_states (torch.FloatTensor
of shape (batch_size, sequence_length, hidden_size)
, optional):
Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if
the model is configured as a decoder.
encoder_attention_mask (torch.FloatTensor
of shape (batch_size, sequence_length)
, optional):
Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
the cross-attention if the model is configured as a decoder. Mask values selected in [0, 1]
:
- 1 for tokens that are not masked,
- 0 for tokens that are masked.
past_key_values (
tuple(tuple(torch.FloatTensor))
of lengthconfig.n_layers
with each tuple having 4 tensors of: shape(batch_size, num_heads, sequence_length - 1, embed_size_per_head)
): Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding. Ifpast_key_values
are used, the user can optionally input only the lastdecoder_input_ids
(those that don’t have their past key value states given to this model) of shape(batch_size, 1)
instead of alldecoder_input_ids
of shape(batch_size, sequence_length)
. use_cache (bool
, optional): If set toTrue
,past_key_values
key value states are returned and can be used to speed up decoding (seepast_key_values
).
InstructBlipVideoForConditionalGeneration
class transformers.InstructBlipVideoForConditionalGeneration
< source >( config: InstructBlipVideoConfig )
Parameters
- config (InstructBlipVideoConfig) — 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.
Instructblipvideo Model for generating text given an image and an optional text prompt. The model consists of a vision encoder, Querying Transformer (Q-Former) and a language model.
One can optionally pass input_ids
to the model, which serve as a text prompt, to make the language model continue
the prompt. Otherwise, the language model starts generating text from the [BOS] (beginning-of-sequence) token.
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
< source >( pixel_values: FloatTensor qformer_input_ids: FloatTensor qformer_attention_mask: Optional = None input_ids: Optional = None attention_mask: Optional = None decoder_input_ids: Optional = None decoder_attention_mask: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None labels: Optional = None return_dict: Optional = None interpolate_pos_encoding: bool = False ) → transformers.models.instructblipvideo.modeling_instructblipvideo.InstructBlipVideoForConditionalGenerationModelOutput
or tuple(torch.FloatTensor)
Parameters
- pixel_values (
torch.FloatTensor
of shape(batch_size, num_channels, height, width)
) — Pixel values. Pixel values can be obtained using InstructBlipVideoProcessor. SeeInstructBlipVideoProcessor.__call__()
for details. - qformer_input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Indices of input sequence tokens in the vocabulary of the Q-Former. Input tokens can optionally be provided to serve as text prompt, which the Q-Former model will encode.Indices can be obtained using InstructBlipVideoProcessor. See
InstructBlipVideoProcessor.__call__()
for details. - qformer_attention_mask (
torch.Tensor
of shape(batch_size, sequence_length)
, optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]
:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
- input_ids (
torch.LongTensor
of shape(batch_size, sequence_length)
, optional) — Indices of input sequence tokens in the vocabulary of the language model. Input tokens can optionally be provided to serve as text prompt, which the language model can continue.Indices can be obtained using InstructBlipVideoProcessor. See
InstructBlipVideoProcessor.__call__()
for details. - attention_mask (
torch.Tensor
of shape(batch_size, sequence_length)
, optional) — Mask to avoid performing attention on padding token indices. Mask values selected in[0, 1]
:- 1 for tokens that are not masked,
- 0 for tokens that are masked.
- decoder_input_ids (
torch.LongTensor
of shape(batch_size, target_sequence_length)
, optional) — Indices of decoder input sequence tokens in the vocabulary of the language model. Only relevant in case an encoder-decoder language model (like T5) is used.Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details. What are decoder input IDs?
- decoder_attention_mask (
torch.BoolTensor
of shape(batch_size, target_sequence_length)
, optional) — Default behavior: generate a tensor that ignores pad tokens indecoder_input_ids
. Causal mask will also be used by default.Only relevant in case an encoder-decoder language model (like T5) is used.
- output_attentions (
bool
, optional) — Whether or not to return the attentions tensors of all attention layers. Seeattentions
under returned tensors for more detail. - output_hidden_states (
bool
, optional) — Whether or not to return the hidden states of all layers. Seehidden_states
under returned tensors for more detail. - return_dict (
bool
, optional) — Whether or not to return a ModelOutput instead of a plain tuple. - interpolate_pos_encoding (
bool
, optional, defaults toFalse
) — Whether to interpolate the pre-trained position encodings. - labels (
torch.LongTensor
of shape(batch_size,)
, optional) — Labels for computing the language modeling loss. Indices should be in[-100, 0, ..., config.vocab_size - 1]
. All labels set to-100
are ignored (masked), the loss is only computed for labels in[0, ..., config.vocab_size]
Returns
transformers.models.instructblipvideo.modeling_instructblipvideo.InstructBlipVideoForConditionalGenerationModelOutput
or tuple(torch.FloatTensor)
A transformers.models.instructblipvideo.modeling_instructblipvideo.InstructBlipVideoForConditionalGenerationModelOutput
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 (<class 'transformers.models.instructblipvideo.configuration_instructblipvideo.InstructBlipVideoVisionConfig'>
) and inputs.
- loss (
torch.FloatTensor
, optional, returned whenlabels
is provided,torch.FloatTensor
of shape(1,)
) — Language modeling loss from the language model. - logits (
torch.FloatTensor
of shape(batch_size, sequence_length, config.vocab_size)
) — Prediction scores of the language modeling head of the language model. - vision_outputs (
BaseModelOutputWithPooling
) — Outputs of the vision encoder. - qformer_outputs (
BaseModelOutputWithPoolingAndCrossAttentions
) — Outputs of the Q-Former (Querying Transformer). - language_model_outputs (
CausalLMOutputWithPast
orSeq2SeqLMOutput
) — Outputs of the language model.
The InstructBlipVideoForConditionalGeneration 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:
>>> from transformers import InstructBlipVideoProcessor, InstructBlipVideoForConditionalGeneration
>>> import torch
>>> from huggingface_hub import hf_hub_download
>>> import av
>>> import numpy as np
>>> 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])
>>> model = InstructBlipVideoForConditionalGeneration.from_pretrained("Salesforce/instructblip-vicuna-7b", device_map="auto")
>>> processor = InstructBlipVideoProcessor.from_pretrained("Salesforce/instructblip-vicuna-7b")
>>> file_path = hf_hub_download(
... repo_id="nielsr/video-demo", filename="eating_spaghetti.mp4", repo_type="dataset"
... )
>>> container = av.open(file_path)
>>> # sample uniformly 4 frames from the videWhy is this video funny?o
>>> total_frames = container.streams.video[0].frames
>>> indices = np.arange(0, total_frames, total_frames / 4).astype(int)
>>> clip = read_video_pyav(container, indices)
>>> prompt = "What is happening in the video?"
>>> inputs = processor(text=prompt, images=clip, return_tensors="pt").to(model.device)
>>> outputs = model.generate(
... **inputs,
... do_sample=False,
... num_beams=5,
... max_length=256,
... repetition_penalty=1.5,
... length_penalty=1.0,
... )
>>> generated_text = processor.batch_decode(outputs, skip_special_tokens=True)[0].strip()
>>> print(generated_text)
"A person is eating a bowl of pasta, and they are using a fork to eat it. The person is sitting at a table, and the plate of pasta is on the table in front"
generate
< source >( pixel_values: FloatTensor qformer_input_ids: Optional = None qformer_attention_mask: Optional = None input_ids: Optional = None attention_mask: Optional = None interpolate_pos_encoding: bool = False **generate_kwargs ) → captions (list)
Parameters
- pixel_values (
torch.FloatTensor
of shape (batch_size, num_channels, height, width) or — (batch_size, num_frames, num_channels, height, width)): Input images or videos to be processed. qformer_input_ids (torch.LongTensor
of shape (batch_size, sequence_length), optional): The sequence used as a prompt to be fed to the Q-Former module. qformer_attention_mask (torch.LongTensor
of shape (batch_size, sequence_length), optional): Mask to avoid performing attention on padding token indices. input_ids (torch.LongTensor
of shape (batch_size, sequence_length), optional): The sequence used as a prompt for the generation. attention_mask (torch.LongTensor
of shape (batch_size, sequence_length), optional): Mask to avoid performing attention on padding token indices. interpolate_pos_encoding (bool
, optional, defaults toFalse
): Whether to interpolate the positional encoding of the image embeddings.
Returns
captions (list)
A list of strings of length batch_size * num_captions.
Overrides generate
function to be able to use the model as a conditional generator.