Hugging Face's logo

Transformers documentation

CLIP

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v4.56.2).
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

CLIP

개요

CLIP 모델은 Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, Ilya Sutskever가 제안한 자연어 지도(supervision)를 통한 전이 가능한 시각 모델 학습라는 논문에서 소개되었습니다. CLIP(Contrastive Language-Image Pre-Training)은 다양한 이미지와 텍스트 쌍으로 훈련된 신경망 입니다. GPT-2와 3의 제로샷 능력과 유사하게, 해당 작업에 직접적으로 최적화하지 않고도 주어진 이미지에 대해 가장 관련성 있는 텍스트 스니펫을 예측하도록 자연어로 지시할 수 있습니다.

해당 논문의 초록입니다.

최신 컴퓨터 비전 시스템은 미리 정해진 고정된 객체 카테고리 집합을 예측하도록 훈련됩니다. 이러한 제한된 형태의 지도는 다른 시각적 개념을 지정하기 위해 추가적인 라벨링된 데이터가 필요하므로 그 일반성과 사용성을 제한합니다. 이미지 원시 텍스트에서 직접 학습하는 것은 훨씬 더 광범위한 지도 소스를 활용하는 아주 좋은 대안입니다. 이미지와 캡션을 맞추는 간단한 사전 학습 작업이, 인터넷에서 수집한 4억 쌍의 이미지-텍스트 데이터셋에서 SOTA 수준의 이미지 표현을 처음부터 효율적이고 확장 가능하게 학습하는 방법임을 확인할 수 있습니다. 사전 훈련 후, 자연어는 학습된 시각적 개념을 참조하거나 새로운 개념을 설명하는 데 사용되어 모델의 하위 작업으로의 제로샷 전이를 가능하게 합니다. 해당 논문에서는 OCR, 비디오 내 행동 인식, 지리적 위치 파악, 그리고 많은 종류의 세밀한 객체 분류 등 30개 이상의 다양한 기존 컴퓨터 비전 데이터셋에 대한 벤치마킹을 통해 이 접근 방식의 성능을 연구합니다. 이 모델은 대부분의 작업에 대해 의미 있게 전이되며, 종종 데이터셋별 훈련 없이도 완전 지도 학습 기준선과 경쟁력 있는 성능을 보입니다. 예를 들어, ImageNet에서 원래 ResNet-50의 정확도를 제로샷으로 일치시키는데, 이는 ResNet-50이 훈련된 128만 개의 훈련 예제를 전혀 사용할 필요가 없었습니다. 코드 및 사전 훈련된 모델 가중치는 이 https URL에서 공개합니다.

이 모델은 valhalla에 의해 기여되었습니다. 원본 코드는 이곳에서 확인할 수 있습니다.

사용 팁과 예시

CLIP은 멀티모달 비전 밒 언어 모델입니다. 이미지-텍스트 유사도 계산과 제로샷 이미지 분류에 사용될 수 있습니다. CLIP은 ViT와 유사한 트랜스포머를 사용하여 시각적 특징을 추출하고, 인과적 언어 모델을 사용하여 텍스트 특징을 추출합니다. 그 후 텍스트와 시각적 특징 모두 동일한 차원의 잠재(latent) 공간으로 투영됩니다. 투영된 이미지와 텍스트 특징 사이의 내적이 유사도 점수로 사용됩니다.

트랜스포머 인코더에 이미지를 입력하기 위해, 각 이미지는 고정 크기의 겹치지 않는 패치들의 시퀀스로 분할되고, 이후 선형 임베딩됩니다. [CLS]토큰이 전체 이미지의 표현으로 추가됩니다. 저자들은 또한 절대 위치 임베딩을 추가하고, 결과로 나온 벡터 시퀀스를 표준 트랜스포머 인토더에 입력합니다. CLIPImageProcessor는 모델을 위해 이미지를 리사이즈(또는 재스캐일링)하고 정규화하는데 사용될 수 있습니다.

CLIPTokenizer는 텍스트를 인코딩하는데 사용됩니다. CLIPProcessor는 CLIPImageProcessor와 CLIPTokenizer를 하나의 인스턴스로 감싸서 텍스트를 인코딩하고 이미지를 준비하는데 모두 사용됩니다.

다음 예시는 CLIPProcessor와 CLIPModel을 사용하여 이미지-텍스트 유사도 점수를 얻는 방법을 보여줍니다.

>>> from PIL import Image
>>> import requests

>>> from transformers import CLIPProcessor, CLIPModel

>>> model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
>>> processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")

>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)

>>> inputs = processor(text=["a photo of a cat", "a photo of a dog"], images=image, return_tensors="pt", padding=True)

>>> outputs = model(**inputs)
>>> logits_per_image = outputs.logits_per_image  # 이미지-텍스트 유사성 점수
>>> probs = logits_per_image.softmax(dim=1)  # 확률을 레이블링 하기위해서 소프트맥스를 취합니다.

CLIP과 플래시 어텐션2 결합

먼저 최신버전의 플래시 어텐션2를 설치합니다.

pip install -U flash-attn --no-build-isolation

플래시 어텐션2와 호환되는 하드웨어를 가지고 있는지 확인하세요. 이에 대한 자세한 내용은 flash-attn 리포지토리의 공식문서에서 확인할 수 있습니다. 또한 모델을 반정밀도(torch.float16)로 로드하는 것을 잊지 마세요.

작은 배치 크기를 사용할 때, 플래시 어텐션을 사용하면 모델이 느려지는 것을 느낄 수 있습니다.아래의 플래시 어텐션과 SDPA를 사용한 예상 속도 향상 섹션을 참조하여 적절한 어텐션 구현을 선택하세요.

플래시 어텐션2를 사용해서 모델을 로드하고 구동하기 위해서 다음 스니펫을 참고하세요:

>>> import torch
>>> import requests
>>> from PIL import Image

>>> from transformers import CLIPProcessor, CLIPModel

>>> device = "cuda"
>>> dtype = torch.float16

>>> model = CLIPModel.from_pretrained(
...     "openai/clip-vit-base-patch32",
...     attn_implementation="flash_attention_2",
...     device_map=device,
...     dtype=dtype,
... )
>>> processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")

>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)

>>> inputs = processor(text=["a photo of a cat", "a photo of a dog"], images=image, return_tensors="pt", padding=True)
>>> inputs.to(device)

>>> with torch.no_grad():
...     with torch.autocast(device):
...         outputs = model(**inputs)

>>> logits_per_image = outputs.logits_per_image  # 이미지-텍스트 유사성 점수
>>> probs = logits_per_image.softmax(dim=1)  # 확률을 레이블링 하기위해서 소프트맥스를 취합니다.
>>> print(probs)
tensor([[0.9946, 0.0052]], device='cuda:0', dtype=torch.float16)

스케일된 내적 어텐션 (Scaled dot-product Attention(SDPA)) 사용하기

파이토치는 torch.nn.functional의 일부로 네이티브 스케일된 내적 어텐션(SPDA) 연산자를 포함하고 있습니다. 이 함수는 입력과 사용 중인 하드웨어에 따라 적용될 수 있는 여러 구현을 포함합니다. 자세한 정보는 공식문서나 GPU 추론 페이지를 참조하세요.

torch>=2.1.1에서는 구현이 가능할 때 SDPA가 기본적으로 사용되지만, from_pretrained() 함수에서 attn_implementation="sdpa"를 설정하여 SDPA를 명시적으로 사용하도록 요청할 수도 있습니다.

from transformers import CLIPModel

model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32", dtype=torch.float16, attn_implementation="sdpa")

최고의 속도향상을 위해서, 반정밀도로 모델을 로드하는 것을 추천합니다. (예를들면 torch.float16 또는 torch.bfloat16).

플래시 어텐션과 스케일된 내적 어텐션(SDPA)으로 인해 예상되는 속도향상

로컬 벤치마크(NVIDIA A10G, PyTorch 2.3.1+cu121)에서 float16을 사용하여 "openai/clip-vit-large-patch14" 체크포인트로 추론을 수행했을 때, 다음과 같은 속도 향상을 확인 했습니다. 코드:

CLIPTextModel

Num text labels Eager (s/iter) FA2 (s/iter) FA2 speedup SDPA (s/iter) SDPA speedup
4 0.009 0.012 0.737 0.007 1.269
16 0.009 0.014 0.659 0.008 1.187
32 0.018 0.021 0.862 0.016 1.142
64 0.034 0.034 1.001 0.03 1.163
128 0.063 0.058 1.09 0.054 1.174

clip_text_model_viz_3

CLIPVisionModel

Image batch size Eager (s/iter) FA2 (s/iter) FA2 speedup SDPA (s/iter) SDPA speedup
1 0.016 0.013 1.247 0.012 1.318
4 0.025 0.021 1.198 0.021 1.202
16 0.093 0.075 1.234 0.075 1.24
32 0.181 0.147 1.237 0.146 1.241

clip_image_model_viz_3

CLIPModel

Image batch size Num text labels Eager (s/iter) FA2 (s/iter) FA2 speedup SDPA (s/iter) SDPA speedup
1 4 0.025 0.026 0.954 0.02 1.217
1 16 0.026 0.028 0.918 0.02 1.287
1 64 0.042 0.046 0.906 0.036 1.167
4 4 0.028 0.033 0.849 0.024 1.189
4 16 0.034 0.035 0.955 0.029 1.169
4 64 0.059 0.055 1.072 0.05 1.179
16 4 0.096 0.088 1.091 0.078 1.234
16 16 0.102 0.09 1.129 0.083 1.224
16 64 0.127 0.11 1.157 0.105 1.218
32 4 0.185 0.159 1.157 0.149 1.238
32 16 0.19 0.162 1.177 0.154 1.233
32 64 0.216 0.181 1.19 0.176 1.228

자료

CLIP을 시작하는 데 도움이 되는 Hugging Face와 community 자료 목록(🌎로 표시됨) 입니다.

​ Image-to-Text
  • 사전학습된 CLIP모델을 이미지 캡셔닝을 위한 빔서치 추론에 어떻게 활용하는지에 관한 노트북

이미지 검색

  • 사전학습된 CLIP모델과 MRR(Mean Reciprocal Rank) 점수 연산을 사용한 이미지 검색에 대한 노트북. 🌎
  • 이미지 검색과 유사성 점수에 대해 보여주는 노트북. 🌎
  • Multilingual CLIP를 사용해서 이미지와 텍스트를 어떻게 같은 벡터 공간에 매핑 시키는지에 대한 노트북. 🌎
  • Unsplash와 TMDB 데이터셋을 활용한 의미론적(semantic) 이미지 검색에서 CLIP을 구동하는 방법에 대한 노트북. 🌎

설명 가능성

  • 입력 토큰과 이미지 조각(segment) 사이의 유사성을 시각화 시키는 방법에 대한 노트북. 🌎

여기에 포함될 자료를 제출하고 싶으시다면 PR(Pull Request)를 열어주세요. 리뷰 해드리겠습니다! 자료는 기존 자료를 복제하는 대신 새로운 내용을 담고 있어야 합니다.

CLIPConfig

class transformers.CLIPConfig

< >

( text_config = None vision_config = None projection_dim = 512 logit_scale_init_value = 2.6592 **kwargs )

Parameters

  • text_config (dict, optional) — Dictionary of configuration options used to initialize CLIPTextConfig.
  • vision_config (dict, optional) — Dictionary of configuration options used to initialize CLIPVisionConfig.
  • projection_dim (int, optional, defaults to 512) — Dimensionality of text and vision projection layers.
  • logit_scale_init_value (float, optional, defaults to 2.6592) — The initial value of the logit_scale parameter. Default is used as per the original CLIP implementation.
  • kwargs (optional) — Dictionary of keyword arguments.

CLIPConfig is the configuration class to store the configuration of a CLIPModel. It is used to instantiate a CLIP model according to the specified arguments, defining the text model and vision model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the CLIP openai/clip-vit-base-patch32 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 CLIPConfig, CLIPModel

>>> # Initializing a CLIPConfig with openai/clip-vit-base-patch32 style configuration
>>> configuration = CLIPConfig()

>>> # Initializing a CLIPModel (with random weights) from the openai/clip-vit-base-patch32 style configuration
>>> model = CLIPModel(configuration)

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

>>> # We can also initialize a CLIPConfig from a CLIPTextConfig and a CLIPVisionConfig
>>> from transformers import CLIPTextConfig, CLIPVisionConfig

>>> # Initializing a CLIPText and CLIPVision configuration
>>> config_text = CLIPTextConfig()
>>> config_vision = CLIPVisionConfig()

>>> config = CLIPConfig.from_text_vision_configs(config_text, config_vision)

from_text_vision_configs

< >

( text_config vision_config **kwargs ) → PreTrainedConfig

Returns

PreTrainedConfig

An instance of a configuration object

Instantiate a model config (or a derived class) from text model configuration and vision model configuration.

CLIPTextConfig

class transformers.CLIPTextConfig

< >

( vocab_size = 49408 hidden_size = 512 intermediate_size = 2048 projection_dim = 512 num_hidden_layers = 12 num_attention_heads = 8 max_position_embeddings = 77 hidden_act = 'quick_gelu' layer_norm_eps = 1e-05 attention_dropout = 0.0 initializer_range = 0.02 initializer_factor = 1.0 pad_token_id = 1 bos_token_id = 49406 eos_token_id = 49407 **kwargs )

Parameters

  • vocab_size (int, optional, defaults to 49408) — Vocabulary size of the CLIP text model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling CLIPModel.
  • hidden_size (int, optional, defaults to 512) — Dimensionality of the encoder layers and the pooler layer.
  • intermediate_size (int, optional, defaults to 2048) — Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.
  • projection_dim (int, optional, defaults to 512) — Dimensionality of text and vision projection layers.
  • num_hidden_layers (int, optional, defaults to 12) — Number of hidden layers in the Transformer encoder.
  • num_attention_heads (int, optional, defaults to 8) — Number of attention heads for each attention layer in the Transformer encoder.
  • max_position_embeddings (int, optional, defaults to 77) — 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).
  • hidden_act (str or function, optional, defaults to "quick_gelu") — The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "selu" and "gelu_new" "quick_gelu" are supported.
  • layer_norm_eps (float, optional, defaults to 1e-05) — 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 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
  • initializer_factor (float, optional, defaults to 1.0) — A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing).
  • pad_token_id (int, optional, defaults to 1) — Padding token id.
  • bos_token_id (int, optional, defaults to 49406) — Beginning of stream token id.
  • eos_token_id (int, optional, defaults to 49407) — End of stream token id.

This is the configuration class to store the configuration of a CLIPTextModel. It is used to instantiate a CLIP text encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the text encoder of the CLIP openai/clip-vit-base-patch32 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 CLIPTextConfig, CLIPTextModel

>>> # Initializing a CLIPTextConfig with openai/clip-vit-base-patch32 style configuration
>>> configuration = CLIPTextConfig()

>>> # Initializing a CLIPTextModel (with random weights) from the openai/clip-vit-base-patch32 style configuration
>>> model = CLIPTextModel(configuration)

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

CLIPVisionConfig

class transformers.CLIPVisionConfig

< >

( hidden_size = 768 intermediate_size = 3072 projection_dim = 512 num_hidden_layers = 12 num_attention_heads = 12 num_channels = 3 image_size = 224 patch_size = 32 hidden_act = 'quick_gelu' layer_norm_eps = 1e-05 attention_dropout = 0.0 initializer_range = 0.02 initializer_factor = 1.0 **kwargs )

Parameters

  • hidden_size (int, optional, defaults to 768) — Dimensionality of the encoder layers and the pooler layer.
  • intermediate_size (int, optional, defaults to 3072) — Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.
  • projection_dim (int, optional, defaults to 512) — Dimensionality of text and vision projection layers.
  • 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.
  • num_channels (int, optional, defaults to 3) — The number of input channels.
  • image_size (int, optional, defaults to 224) — The size (resolution) of each image.
  • patch_size (int, optional, defaults to 32) — The size (resolution) of each patch.
  • hidden_act (str or function, optional, defaults to "quick_gelu") — The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "selu" and "gelu_new" "quick_gelu" are supported.
  • layer_norm_eps (float, optional, defaults to 1e-05) — 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 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
  • initializer_factor (float, optional, defaults to 1.0) — A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing).

This is the configuration class to store the configuration of a CLIPVisionModel. It is used to instantiate a CLIP vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the vision encoder of the CLIP openai/clip-vit-base-patch32 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 CLIPVisionConfig, CLIPVisionModel

>>> # Initializing a CLIPVisionConfig with openai/clip-vit-base-patch32 style configuration
>>> configuration = CLIPVisionConfig()

>>> # Initializing a CLIPVisionModel (with random weights) from the openai/clip-vit-base-patch32 style configuration
>>> model = CLIPVisionModel(configuration)

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

CLIPTokenizer

class transformers.CLIPTokenizer

< >

( vocab_file merges_file errors = 'replace' unk_token = '<|endoftext|>' bos_token = '<|startoftext|>' eos_token = '<|endoftext|>' pad_token = '<|endoftext|>' **kwargs )

Parameters

  • vocab_file (str) — Path to the vocabulary file.
  • merges_file (str) — Path to the merges file.
  • errors (str, optional, defaults to "replace") — Paradigm to follow when decoding bytes to UTF-8. See bytes.decode for more information.
  • unk_token (str, optional, defaults to "<|endoftext|>") — The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.
  • bos_token (str, optional, defaults to "<|startoftext|>") — The beginning of sequence token.
  • eos_token (str, optional, defaults to "<|endoftext|>") — The end of sequence token.
  • pad_token (str, optional, defaults to "<|endoftext|>") — The token used for padding, for example when batching sequences of different lengths.

Construct a CLIP tokenizer. Based on byte-level Byte-Pair-Encoding.

This tokenizer inherits from PreTrainedTokenizer which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.

build_inputs_with_special_tokens

< >

( token_ids_0: list token_ids_1: typing.Optional[list[int]] = None ) → list[int]

Parameters

  • token_ids_0 (list[int]) — List of IDs to which the special tokens will be added.
  • token_ids_1 (list[int], optional) — Optional second list of IDs for sequence pairs.

Returns

list[int]

List of input IDs with the appropriate special tokens.

Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. A CLIP sequence has the following format:

  • single sequence: <|startoftext|> X <|endoftext|>

Pairs of sequences are not the expected use case, but they will be handled without a separator.

get_special_tokens_mask

< >

( token_ids_0: list token_ids_1: typing.Optional[list[int]] = None already_has_special_tokens: bool = False ) → list[int]

Parameters

  • token_ids_0 (list[int]) — List of IDs.
  • token_ids_1 (list[int], optional) — Optional second list of IDs for sequence pairs.
  • already_has_special_tokens (bool, optional, defaults to False) — Whether or not the token list is already formatted with special tokens for the model.

Returns

list[int]

A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.

Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding special tokens using the tokenizer prepare_for_model method.

create_token_type_ids_from_sequences

< >

( token_ids_0: list token_ids_1: typing.Optional[list[int]] = None ) → list[int]

Parameters

  • token_ids_0 (list[int]) — List of IDs.
  • token_ids_1 (list[int], optional) — Optional second list of IDs for sequence pairs.

Returns

list[int]

List of zeros.

Create a mask from the two sequences passed. CLIP does not make use of token type ids, therefore a list of zeros is returned.

save_vocabulary

< >

( save_directory: str filename_prefix: typing.Optional[str] = None )

CLIPTokenizerFast

class transformers.CLIPTokenizerFast

< >

( vocab_file = None merges_file = None tokenizer_file = None unk_token = '<|endoftext|>' bos_token = '<|startoftext|>' eos_token = '<|endoftext|>' pad_token = '<|endoftext|>' **kwargs )

Parameters

  • vocab_file (str, optional) — Path to the vocabulary file.
  • merges_file (str, optional) — Path to the merges file.
  • tokenizer_file (str, optional) — The path to a tokenizer file to use instead of the vocab file.
  • unk_token (str, optional, defaults to "<|endoftext|>") — The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.
  • bos_token (str, optional, defaults to "<|startoftext|>") — The beginning of sequence token.
  • eos_token (str, optional, defaults to "<|endoftext|>") — The end of sequence token.
  • pad_token (str, optional, defaults to "<|endoftext|>") — The token used for padding, for example when batching sequences of different lengths.

Construct a “fast” CLIP tokenizer (backed by HuggingFace’s tokenizers library). Based on byte-level Byte-Pair-Encoding.

This tokenizer inherits from PreTrainedTokenizerFast which contains most of the main methods. Users should refer to this superclass for more information regarding those methods.

build_inputs_with_special_tokens

< >

( token_ids_0: list token_ids_1: typing.Optional[list[int]] = None ) → list[int]

Parameters

  • token_ids_0 (list[int]) — List of IDs to which the special tokens will be added.
  • token_ids_1 (list[int], optional) — Optional second list of IDs for sequence pairs.

Returns

list[int]

List of input IDs with the appropriate special tokens.

Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. A CLIP sequence has the following format:

  • single sequence: <|startoftext|> X <|endoftext|>

Pairs of sequences are not the expected use case, but they will be handled without a separator.

create_token_type_ids_from_sequences

< >

( token_ids_0: list token_ids_1: typing.Optional[list[int]] = None ) → list[int]

Parameters

  • token_ids_0 (list[int]) — List of IDs.
  • token_ids_1 (list[int], optional) — Optional second list of IDs for sequence pairs.

Returns

list[int]

List of zeros.

Create a mask from the two sequences passed. CLIP does not make use of token type ids, therefore a list of zeros is returned.

CLIPImageProcessor

class transformers.CLIPImageProcessor

< >

( do_resize: bool = True size: typing.Optional[dict[str, int]] = None resample: Resampling = <Resampling.BICUBIC: 3> do_center_crop: bool = True crop_size: typing.Optional[dict[str, int]] = None do_rescale: bool = True rescale_factor: typing.Union[int, float] = 0.00392156862745098 do_normalize: bool = True image_mean: typing.Union[float, list[float], NoneType] = None image_std: typing.Union[float, list[float], NoneType] = None do_convert_rgb: bool = True **kwargs )

Parameters

  • do_resize (bool, optional, defaults to True) — Whether to resize the image’s (height, width) dimensions to the specified size. Can be overridden by do_resize in the preprocess method.
  • size (dict[str, int] optional, defaults to {"shortest_edge" -- 224}): Size of the image after resizing. The shortest edge of the image is resized to size[“shortest_edge”], with the longest edge resized to keep the input aspect ratio. Can be overridden by size in the preprocess method.
  • resample (PILImageResampling, optional, defaults to Resampling.BICUBIC) — Resampling filter to use if resizing the image. Can be overridden by resample in the preprocess method.
  • do_center_crop (bool, optional, defaults to True) — Whether to center crop the image to the specified crop_size. Can be overridden by do_center_crop in the preprocess method.
  • crop_size (dict[str, int] optional, defaults to 224) — Size of the output image after applying center_crop. Can be overridden by crop_size in the preprocess method.
  • do_rescale (bool, optional, defaults to True) — Whether to rescale the image by the specified scale rescale_factor. Can be overridden by do_rescale in the preprocess method.
  • rescale_factor (int or float, optional, defaults to 1/255) — Scale factor to use if rescaling the image. Can be overridden by rescale_factor in the preprocess method.
  • do_normalize (bool, optional, defaults to True) — Whether to normalize the image. Can be overridden by do_normalize in the preprocess method.
  • image_mean (float or list[float], optional, defaults to [0.48145466, 0.4578275, 0.40821073]) — 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 the image_mean parameter in the preprocess method.
  • image_std (float or list[float], optional, defaults to [0.26862954, 0.26130258, 0.27577711]) — 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 the image_std parameter in the preprocess method. Can be overridden by the image_std parameter in the preprocess method.
  • do_convert_rgb (bool, optional, defaults to True) — Whether to convert the image to RGB.

Constructs a CLIP image processor.

preprocess

< >

( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']] do_resize: typing.Optional[bool] = None size: typing.Optional[dict[str, int]] = None resample: typing.Optional[PIL.Image.Resampling] = None do_center_crop: typing.Optional[bool] = None crop_size: typing.Optional[int] = None do_rescale: typing.Optional[bool] = None rescale_factor: typing.Optional[float] = None do_normalize: typing.Optional[bool] = None image_mean: typing.Union[float, list[float], NoneType] = None image_std: typing.Union[float, list[float], NoneType] = None do_convert_rgb: typing.Optional[bool] = None return_tensors: typing.Union[str, transformers.utils.generic.TensorType, NoneType] = None data_format: typing.Optional[transformers.image_utils.ChannelDimension] = <ChannelDimension.FIRST: 'channels_first'> input_data_format: typing.Union[str, transformers.image_utils.ChannelDimension, NoneType] = None **kwargs )

Parameters

  • images (ImageInput) — Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set do_rescale=False.
  • do_resize (bool, optional, defaults to self.do_resize) — Whether to resize the image.
  • size (dict[str, int], optional, defaults to self.size) — Size of the image after resizing. Shortest edge of the image is resized to size[“shortest_edge”], with the longest edge resized to keep the input aspect ratio.
  • resample (int, optional, defaults to self.resample) — Resampling filter to use if resizing the image. This can be one of the enum PILImageResampling. Only has an effect if do_resize is set to True.
  • do_center_crop (bool, optional, defaults to self.do_center_crop) — Whether to center crop the image.
  • crop_size (dict[str, int], optional, defaults to self.crop_size) — Size of the center crop. Only has an effect if do_center_crop is set to True.
  • do_rescale (bool, optional, defaults to self.do_rescale) — Whether to rescale the image.
  • rescale_factor (float, optional, defaults to self.rescale_factor) — Rescale factor to rescale the image by if do_rescale is set to True.
  • do_normalize (bool, optional, defaults to self.do_normalize) — Whether to normalize the image.
  • image_mean (float or list[float], optional, defaults to self.image_mean) — Image mean to use for normalization. Only has an effect if do_normalize is set to True.
  • image_std (float or list[float], optional, defaults to self.image_std) — Image standard deviation to use for normalization. Only has an effect if do_normalize is set to True.
  • do_convert_rgb (bool, optional, defaults to self.do_convert_rgb) — Whether to convert the image to RGB.
  • return_tensors (str or TensorType, optional) — The type of tensors to return. Can be one of:
    • Unset: Return a list of np.ndarray.
    • TensorType.PYTORCH or 'pt': Return a batch of type torch.Tensor.
    • TensorType.NUMPY or 'np': Return a batch of type np.ndarray.
  • data_format (ChannelDimension or str, optional, defaults to ChannelDimension.FIRST) — The channel dimension format for the output image. Can be one of:
    • "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
    • "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format.
    • Unset: Use the channel dimension format of the input image.
  • input_data_format (ChannelDimension or str, 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" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
    • "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format.
    • "none" or ChannelDimension.NONE: image in (height, width) format.

Preprocess an image or batch of images.

CLIPFeatureExtractor

class transformers.CLIPFeatureExtractor

< >

( *args **kwargs )

CLIPProcessor

class transformers.CLIPProcessor

< >

( image_processor = None tokenizer = None **kwargs )

Parameters

  • image_processor (CLIPImageProcessor, optional) — The image processor is a required input.
  • tokenizer (AutoTokenizer, optional) — The tokenizer is a required input.

Constructs a CLIP processor which wraps a CLIP image processor and a CLIP tokenizer into a single processor.

CLIPProcessor offers all the functionalities of CLIPImageProcessor and CLIPTokenizerFast. See the call() and decode() for more information.

CLIPModel

class transformers.CLIPModel

< >

( config: CLIPConfig )

Parameters

  • config (CLIPConfig) — 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 Clip Model outputting raw hidden-states without any specific head on top.

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

< >

( input_ids: typing.Optional[torch.LongTensor] = None pixel_values: typing.Optional[torch.FloatTensor] = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.LongTensor] = None return_loss: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None interpolate_pos_encoding: bool = False ) → transformers.models.clip.modeling_clip.CLIPOutput or tuple(torch.FloatTensor)

Parameters

  • input_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

    Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are input IDs?

  • pixel_values (torch.FloatTensor of shape (batch_size, num_channels, image_size, image_size), optional) — The tensors corresponding to the input images. Pixel values can be obtained using CLIPImageProcessor. See CLIPImageProcessor.call() for details (CLIPProcessor uses CLIPImageProcessor for processing images).
  • 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.

    What are attention masks?

  • position_ids (torch.LongTensor of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.n_positions - 1].

    What are position IDs?

  • return_loss (bool, optional) — Whether or not to return the contrastive loss.
  • output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
  • output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
  • interpolate_pos_encoding (bool, defaults to False) — Whether to interpolate the pre-trained position encodings.

Returns

transformers.models.clip.modeling_clip.CLIPOutput or tuple(torch.FloatTensor)

A transformers.models.clip.modeling_clip.CLIPOutput 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 (CLIPConfig) and inputs.

  • loss (torch.FloatTensor of shape (1,), optional, returned when return_loss is True) — Contrastive loss for image-text similarity.
  • logits_per_image (torch.FloatTensor of shape (image_batch_size, text_batch_size)) — The scaled dot product scores between image_embeds and text_embeds. This represents the image-text similarity scores.
  • logits_per_text (torch.FloatTensor of shape (text_batch_size, image_batch_size)) — The scaled dot product scores between text_embeds and image_embeds. This represents the text-image similarity scores.
  • text_embeds (torch.FloatTensor of shape (batch_size, output_dim) — The text embeddings obtained by applying the projection layer to the pooled output of CLIPTextModel.
  • image_embeds (torch.FloatTensor of shape (batch_size, output_dim) — The image embeddings obtained by applying the projection layer to the pooled output of CLIPVisionModel.
  • text_model_output (<class '~modeling_outputs.BaseModelOutputWithPooling'>.text_model_output, defaults to None) — The output of the CLIPTextModel.
  • vision_model_output (<class '~modeling_outputs.BaseModelOutputWithPooling'>.vision_model_output, defaults to None) — The output of the CLIPVisionModel.

The CLIPModel 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 torch
>>> from transformers import AutoProcessor, CLIPModel
>>> from transformers.image_utils import load_image

>>> model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
>>> processor = AutoProcessor.from_pretrained("openai/clip-vit-base-patch32")

>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = load_image(url)

>>> inputs = processor(
...     text=["a photo of a cat", "a photo of a dog"], images=image, return_tensors="pt", padding=True
... )

>>> with torch.inference_mode():
...     outputs = model(**inputs)
>>> logits_per_image = outputs.logits_per_image  # this is the image-text similarity score
>>> probs = logits_per_image.softmax(dim=1)  # we can take the softmax to get the label probabilities

get_text_features

< >

( input_ids: Tensor attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.Tensor] = None ) → text_features (torch.FloatTensor of shape (batch_size, output_dim)

Parameters

  • input_ids (torch.Tensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

    Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are input IDs?

  • 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.

    What are attention masks?

  • position_ids (torch.Tensor of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.n_positions - 1].

    What are position IDs?

Returns

text_features (torch.FloatTensor of shape (batch_size, output_dim)

The text embeddings obtained by applying the projection layer to the pooled output of CLIPTextModel.

Examples:

>>> import torch
>>> from transformers import AutoTokenizer, CLIPModel

>>> model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
>>> tokenizer = AutoTokenizer.from_pretrained("openai/clip-vit-base-patch32")

>>> inputs = tokenizer(["a photo of a cat", "a photo of a dog"], padding=True, return_tensors="pt")

>>> with torch.inference_mode():
...     text_features = model.get_text_features(**inputs)

get_image_features

< >

( pixel_values: FloatTensor interpolate_pos_encoding: bool = False ) → image_features (torch.FloatTensor of shape (batch_size, output_dim)

Parameters

  • pixel_values (torch.FloatTensor of shape (batch_size, num_channels, image_size, image_size)) — The tensors corresponding to the input images. Pixel values can be obtained using CLIPImageProcessor. See CLIPImageProcessor.call() for details (CLIPProcessor uses CLIPImageProcessor for processing images).
  • interpolate_pos_encoding (bool, defaults to False) — Whether to interpolate the pre-trained position encodings.

Returns

image_features (torch.FloatTensor of shape (batch_size, output_dim)

The image embeddings obtained by applying the projection layer to the pooled output of CLIPVisionModel.

Examples:

>>> import torch
>>> from transformers import AutoProcessor, CLIPModel
>>> from transformers.image_utils import load_image

>>> model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
>>> processor = AutoProcessor.from_pretrained("openai/clip-vit-base-patch32")

>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = load_image(url)

>>> inputs = processor(images=image, return_tensors="pt")

>>> with torch.inference_mode():
...     image_features = model.get_image_features(**inputs)

CLIPTextModel

class transformers.CLIPTextModel

< >

( config: CLIPTextConfig )

Parameters

  • config (CLIPTextConfig) — 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 text model from CLIP without any head or projection on top.

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

< >

( input_ids: typing.Optional[torch.Tensor] = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.Tensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None ) → transformers.modeling_outputs.BaseModelOutputWithPooling or tuple(torch.FloatTensor)

Parameters

  • input_ids (torch.Tensor of shape (batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

    Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are input IDs?

  • 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.

    What are attention masks?

  • position_ids (torch.Tensor of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.n_positions - 1].

    What are position IDs?

  • output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
  • output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.

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 (CLIPConfig) 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 when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.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 when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.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 CLIPTextModel 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 AutoTokenizer, CLIPTextModel

>>> model = CLIPTextModel.from_pretrained("openai/clip-vit-base-patch32")
>>> tokenizer = AutoTokenizer.from_pretrained("openai/clip-vit-base-patch32")

>>> inputs = tokenizer(["a photo of a cat", "a photo of a dog"], padding=True, return_tensors="pt")

>>> outputs = model(**inputs)
>>> last_hidden_state = outputs.last_hidden_state
>>> pooled_output = outputs.pooler_output  # pooled (EOS token) states

CLIPTextModelWithProjection

class transformers.CLIPTextModelWithProjection

< >

( config: CLIPTextConfig )

Parameters

  • config (CLIPTextConfig) — 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 Clip Model with a projection layer on top (a linear layer on top of the pooled output).

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

< >

( input_ids: typing.Optional[torch.Tensor] = None attention_mask: typing.Optional[torch.Tensor] = None position_ids: typing.Optional[torch.Tensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None ) → transformers.models.clip.modeling_clip.CLIPTextModelOutput or tuple(torch.FloatTensor)

Parameters

  • input_ids (torch.Tensor of shape (batch_size, sequence_length), optional) — Indices of input sequence tokens in the vocabulary. Padding will be ignored by default.

    Indices can be obtained using AutoTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details.

    What are input IDs?

  • 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.

    What are attention masks?

  • position_ids (torch.Tensor of shape (batch_size, sequence_length), optional) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range [0, config.n_positions - 1].

    What are position IDs?

  • output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
  • output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.

Returns

transformers.models.clip.modeling_clip.CLIPTextModelOutput or tuple(torch.FloatTensor)

A transformers.models.clip.modeling_clip.CLIPTextModelOutput 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 (CLIPConfig) and inputs.

  • text_embeds (torch.FloatTensor of shape (batch_size, output_dim) optional returned when model is initialized with with_projection=True) — The text embeddings obtained by applying the projection layer to the pooler_output.

  • last_hidden_state (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional, defaults to None) — Sequence of hidden-states at the output of the last layer of the model.

  • hidden_states (tuple[torch.FloatTensor, ...], optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.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 when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.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 CLIPTextModelWithProjection 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 torch
>>> from transformers import AutoTokenizer, CLIPTextModelWithProjection

>>> model = CLIPTextModelWithProjection.from_pretrained("openai/clip-vit-base-patch32")
>>> tokenizer = AutoTokenizer.from_pretrained("openai/clip-vit-base-patch32")

>>> inputs = tokenizer(["a photo of a cat", "a photo of a dog"], padding=True, return_tensors="pt")

>>> with torch.inference_mode():
...     outputs = model(**inputs)
>>> text_embeds = outputs.text_embeds

CLIPVisionModelWithProjection

class transformers.CLIPVisionModelWithProjection

< >

( config: CLIPVisionConfig )

Parameters

  • config (CLIPVisionConfig) — 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 Clip Model with a projection layer on top (a linear layer on top of the pooled output).

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: typing.Optional[torch.FloatTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None interpolate_pos_encoding: bool = False ) → transformers.models.clip.modeling_clip.CLIPVisionModelOutput or tuple(torch.FloatTensor)

Parameters

  • pixel_values (torch.FloatTensor of shape (batch_size, num_channels, image_size, image_size), optional) — The tensors corresponding to the input images. Pixel values can be obtained using CLIPImageProcessor. See CLIPImageProcessor.call() for details (CLIPProcessor uses CLIPImageProcessor for processing images).
  • output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
  • output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
  • interpolate_pos_encoding (bool, defaults to False) — Whether to interpolate the pre-trained position encodings.

Returns

transformers.models.clip.modeling_clip.CLIPVisionModelOutput or tuple(torch.FloatTensor)

A transformers.models.clip.modeling_clip.CLIPVisionModelOutput 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 (CLIPConfig) and inputs.

  • image_embeds (torch.FloatTensor of shape (batch_size, output_dim) optional returned when model is initialized with with_projection=True) — The image embeddings obtained by applying the projection layer to the pooler_output.

  • last_hidden_state (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional, defaults to None) — Sequence of hidden-states at the output of the last layer of the model.

  • hidden_states (tuple[torch.FloatTensor, ...], optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.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 when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.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 CLIPVisionModelWithProjection 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 torch
>>> from transformers import AutoProcessor, CLIPVisionModelWithProjection
>>> from transformers.image_utils import load_image

>>> model = CLIPVisionModelWithProjection.from_pretrained("openai/clip-vit-base-patch32")
>>> processor = AutoProcessor.from_pretrained("openai/clip-vit-base-patch32")

>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = load_image(url)

>>> inputs = processor(images=image, return_tensors="pt")

>>> with torch.inference_mode():
...     outputs = model(**inputs)
>>> image_embeds = outputs.image_embeds

CLIPVisionModel

class transformers.CLIPVisionModel

< >

( config: CLIPVisionConfig )

Parameters

  • config (CLIPVisionConfig) — 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 vision model from CLIP without any head or projection on top.

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: typing.Optional[torch.FloatTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = 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, image_size, image_size), optional) — The tensors corresponding to the input images. Pixel values can be obtained using CLIPImageProcessor. See CLIPImageProcessor.call() for details (CLIPProcessor uses CLIPImageProcessor for processing images).
  • output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
  • output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
  • interpolate_pos_encoding (bool, defaults to False) — 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 (CLIPConfig) 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 when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.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 when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.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 CLIPVisionModel 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.

Example:

>>> from PIL import Image
>>> import requests
>>> from transformers import AutoProcessor, CLIPVisionModel

>>> model = CLIPVisionModel.from_pretrained("openai/clip-vit-base-patch32")
>>> processor = AutoProcessor.from_pretrained("openai/clip-vit-base-patch32")

>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)

>>> inputs = processor(images=image, return_tensors="pt")

>>> outputs = model(**inputs)
>>> last_hidden_state = outputs.last_hidden_state
>>> pooled_output = outputs.pooler_output  # pooled CLS states

CLIPForImageClassification

class transformers.CLIPForImageClassification

< >

( config: CLIPConfig )

Parameters

  • config (CLIPConfig) — 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.

CLIP vision encoder with an image classification head on top (a linear layer on top of the pooled final hidden states of the patch tokens) e.g. for ImageNet.

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: typing.Optional[torch.Tensor] = None labels: typing.Optional[torch.Tensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None ) → transformers.modeling_outputs.ImageClassifierOutput or tuple(torch.FloatTensor)

Parameters

  • pixel_values (torch.Tensor of shape (batch_size, num_channels, image_size, image_size), optional) — The tensors corresponding to the input images. Pixel values can be obtained using CLIPImageProcessor. See CLIPImageProcessor.call() for details (CLIPProcessor uses CLIPImageProcessor for processing images).
  • labels (torch.LongTensor of shape (batch_size,), optional) — Labels for computing the image classification/regression loss. Indices should be in [0, ..., config.num_labels - 1]. If config.num_labels == 1 a regression loss is computed (Mean-Square loss), If config.num_labels > 1 a classification loss is computed (Cross-Entropy).
  • output_attentions (bool, optional) — Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
  • output_hidden_states (bool, optional) — Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.

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 (CLIPConfig) and inputs.

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels is provided) — Classification (or regression if config.num_labels==1) loss.

  • logits (torch.FloatTensor of shape (batch_size, config.num_labels)) — Classification (or regression if config.num_labels==1) scores (before SoftMax).

  • hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.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 when output_attentions=True is passed or when config.output_attentions=True) — Tuple of torch.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 CLIPForImageClassification 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.

Example:

>>> from transformers import AutoImageProcessor, CLIPForImageClassification
>>> import torch
>>> from datasets import load_dataset

>>> dataset = load_dataset("huggingface/cats-image")
>>> image = dataset["test"]["image"][0]

>>> image_processor = AutoImageProcessor.from_pretrained("openai/clip-vit-base-patch32")
>>> model = CLIPForImageClassification.from_pretrained("openai/clip-vit-base-patch32")

>>> inputs = image_processor(image, return_tensors="pt")

>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> # model predicts one of the 1000 ImageNet classes
>>> predicted_label = logits.argmax(-1).item()
>>> print(model.config.id2label[predicted_label])
...
< > Update on GitHub

←Chinese-CLIP CLIPSeg→