# CLIP ## Overview CLIP モデルは、Alec Radford、Jong Wook Kim、Chris Hallacy、Aditya Ramesh、Gabriel Goh Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, Ilya Sutskever [Learning Transferable Visual Models From Natural Language Supervision](https://huggingface.co/papers/2103.00020) で提案されました。 サンディニ・アガルワル、ギリッシュ・サストリー、アマンダ・アスケル、パメラ・ミシュキン、ジャック・クラーク、グレッチェン・クルーガー、イリヤ・サツケヴァー。クリップ (Contrastive Language-Image Pre-Training) は、さまざまな (画像、テキスト) ペアでトレーニングされたニューラル ネットワークです。かもね 直接最適化することなく、与えられた画像から最も関連性の高いテキスト スニペットを予測するように自然言語で指示されます。 GPT-2 および 3 のゼロショット機能と同様に、タスクに対して。 論文の要約は次のとおりです。 *最先端のコンピューター ビジョン システムは、あらかじめ定められたオブジェクト カテゴリの固定セットを予測するようにトレーニングされています。これ 制限された形式の監視では、指定するために追加のラベル付きデータが必要となるため、一般性と使いやすさが制限されます。 その他の視覚的なコンセプト。画像に関する生のテキストから直接学習することは、 より広範な監督源。どのキャプションが表示されるかを予測するという単純な事前トレーニング タスクが有効であることを示します。 400 のデータセットで SOTA 画像表現を最初から学習するための効率的かつスケーラブルな方法はどの画像ですか インターネットから収集された数百万の（画像、テキスト）ペア。事前トレーニング後、自然言語を使用して参照します。 視覚的な概念を学習し（または新しい概念を説明し）、下流のタスクへのモデルのゼロショット転送を可能にします。私たちは勉強します 30 を超えるさまざまな既存のコンピューター ビジョン データセットでタスクをまたがってベンチマークを行うことにより、このアプローチのパフォーマンスを評価します。 OCR、ビデオ内のアクション認識、地理的位置特定、およびさまざまな種類のきめ細かいオブジェクト分類など。の モデルはほとんどのタスクに簡単に移行でき、多くの場合、必要がなくても完全に監視されたベースラインと競合します。 データセット固有のトレーニングに適しています。たとえば、ImageNet ゼロショットではオリジナルの ResNet-50 の精度と一致します。 トレーニングに使用された 128 万のトレーニング サンプルを使用する必要はありません。コードをリリースし、事前トレーニング済み モデルの重みはこの https URL で確認できます。* このモデルは [valhalla](https://huggingface.co/valhalla) によって提供されました。元のコードは [ここ](https://github.com/openai/CLIP) にあります。 ## Usage tips and example CLIP は、マルチモーダルなビジョンおよび言語モデルです。画像とテキストの類似性やゼロショット画像に使用できます。 分類。 CLIP は、ViT のようなトランスフォーマーを使用して視覚的特徴を取得し、因果言語モデルを使用してテキストを取得します 特徴。次に、テキストと視覚の両方の特徴が、同じ次元の潜在空間に投影されます。ドット 投影された画像とテキストの特徴間の積が同様のスコアとして使用されます。 画像を Transformer エンコーダに供給するために、各画像は固定サイズの重複しないパッチのシーケンスに分割されます。 これらは線形に埋め込まれます。 [CLS] トークンは、イメージ全体の表現として機能するために追加されます。作家たち また、絶対位置埋め込みを追加し、結果として得られるベクトルのシーケンスを標準の Transformer エンコーダに供給します。 [CLIPImageProcessor](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPImageProcessor) を使用して、モデルの画像のサイズ変更 (または再スケール) および正規化を行うことができます。 [CLIPTokenizer](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPTokenizer) はテキストのエンコードに使用されます。 [CLIPProcessor](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPProcessor) はラップします [CLIPImageProcessor](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPImageProcessor) と [CLIPTokenizer](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPTokenizer) を両方の単一インスタンスに統合 テキストをエンコードして画像を準備します。次の例は、次のメソッドを使用して画像とテキストの類似性スコアを取得する方法を示しています。 [CLIPProcessor](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPProcessor) と [CLIPModel](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPModel)。 ```python >>> 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 # this is the image-text similarity score >>> probs = logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities ``` ## Resources CLIP を使い始めるのに役立つ公式 Hugging Face およびコミュニティ (🌎 で示されている) リソースのリスト。 - [リモート センシング (衛星) 画像とキャプションを使用した CLIP の微調整](https://huggingface.co/blog/fine-tune-clip-rsicd)、[RSICD データセット] を使用して CLIP を微調整する方法に関するブログ投稿(https://github.com/201528014227051/RSICD_optimal) と、データ拡張によるパフォーマンスの変化の比較。 - この [サンプル スクリプト](https://github.com/huggingface/transformers/tree/main/examples/pytorch/contrastive-image-text) は、プレ- [COCO データセット](https://cocodataset.org/#home) を使用してトレーニングされたビジョンおよびテキスト エンコーダー。 - 画像キャプションのビーム検索による推論に事前トレーニング済み CLIP を使用する方法に関する [ノートブック](https://colab.research.google.com/drive/1tuoAC5F4sC7qid56Z0ap-stR3rwdk0ZV?usp=sharing)。 🌎 **画像検索** - 事前トレーニングされた CLIP を使用した画像検索と MRR (平均相互ランク) スコアの計算に関する [ノートブック](https://colab.research.google.com/drive/1bLVwVKpAndpEDHqjzxVPr_9nGrSbuOQd?usp=sharing)。 🌎 - 画像の取得と類似性スコアの表示に関する [ノートブック](https://colab.research.google.com/github/deep-diver/image_search_with_natural_language/blob/main/notebooks/Image_Search_CLIP.ipynb)。 🌎 - 多言語 CLIP を使用して画像とテキストを同じベクトル空間にマッピングする方法に関する [ノートブック](https://colab.research.google.com/drive/1xO-wC_m_GNzgjIBQ4a4znvQkvDoZJvH4?usp=sharing)。 🌎 - を使用してセマンティック イメージ検索で CLIP を実行する方法に関する [ノートブック](https://colab.research.google.com/github/vivien000/clip-demo/blob/master/clip.ipynb#scrollTo=uzdFhRGqiWkR) [Unsplash](https://unsplash.com) および [TMDB](https://www.themoviedb.org/) データセット。 🌎 **説明可能性** - 入力トークンと画像セグメントの類似性を視覚化する方法に関する [ノートブック](https://colab.research.google.com/github/hila-chefer/Transformer-MM-Explainability/blob/main/CLIP_explainability.ipynb)。 🌎 ここに含めるリソースの送信に興味がある場合は、お気軽にプル リクエストを開いてください。審査させていただきます。 リソースは、既存のリソースを複製するのではなく、何か新しいものを示すことが理想的です。 ## CLIPConfig[[transformers.CLIPConfig]] #### transformers.CLIPConfig[[transformers.CLIPConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/configuration_clip.py#L219) [CLIPConfig](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPConfig) is the configuration class to store the configuration of a [CLIPModel](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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](https://huggingface.co/openai/clip-vit-base-patch32) architecture. Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.2.0/ja/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.2.0/ja/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> 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(text_config=config_text, vision_config=config_vision) ``` **Parameters:** text_config (`dict`, *optional*) : Dictionary of configuration options used to initialize [CLIPTextConfig](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPTextConfig). vision_config (`dict`, *optional*) : Dictionary of configuration options used to initialize [CLIPVisionConfig](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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. ## CLIPTextConfig[[transformers.CLIPTextConfig]] #### transformers.CLIPTextConfig[[transformers.CLIPTextConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/configuration_clip.py#L23) This is the configuration class to store the configuration of a [CLIPTextModel](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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](https://huggingface.co/openai/clip-vit-base-patch32) architecture. Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.2.0/ja/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.2.0/ja/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> 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 ``` **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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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. ## CLIPVisionConfig[[transformers.CLIPVisionConfig]] #### transformers.CLIPVisionConfig[[transformers.CLIPVisionConfig]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/configuration_clip.py#L127) This is the configuration class to store the configuration of a [CLIPVisionModel](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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](https://huggingface.co/openai/clip-vit-base-patch32) architecture. Configuration objects inherit from [PreTrainedConfig](/docs/transformers/v5.2.0/ja/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the documentation from [PreTrainedConfig](/docs/transformers/v5.2.0/ja/main_classes/configuration#transformers.PreTrainedConfig) for more information. Example: ```python >>> 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 ``` **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). ## CLIPTokenizer[[transformers.CLIPTokenizer]] #### transformers.CLIPTokenizer[[transformers.CLIPTokenizer]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/tokenization_clip.py#L28) Construct a CLIP tokenizer (backed by HuggingFace's *tokenizers* library). Based on byte-level Byte-Pair-Encoding. This tokenizer inherits from [TokenizersBackend](/docs/transformers/v5.2.0/ja/main_classes/tokenizer#transformers.TokenizersBackend) which contains most of the main methods. Users should refer to this superclass for more information regarding those methods. get_special_tokens_masktransformers.CLIPTokenizer.get_special_tokens_maskhttps://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/tokenization_utils_base.py#L1294[{"name": "token_ids_0", "val": ": list[int]"}, {"name": "token_ids_1", "val": ": list[int] | None = None"}, {"name": "already_has_special_tokens", "val": ": bool = False"}]- **token_ids_0** -- List of IDs for the (possibly already formatted) sequence. - **token_ids_1** -- Unused when `already_has_special_tokens=True`. Must be None in that case. - **already_has_special_tokens** -- Whether the sequence is already formatted with special tokens.0A 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. For fast tokenizers, data collators call this with `already_has_special_tokens=True` to build a mask over an already-formatted sequence. In that case, we compute the mask by checking membership in `all_special_ids`. **Parameters:** vocab (`str`, `dict` or `list`, *optional*) : Vocabulary dict to use for the tokenizer. merges (`str` or `list`, *optional*) : Merges list to use for the BPE tokenizer. unk_token (`str`, *optional*, defaults to `""`) : 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 `""`) : The beginning of sequence token. eos_token (`str`, *optional*, defaults to `""`) : The end of sequence token. pad_token (`str`, *optional*, defaults to `""`) : The token used for padding, for example when batching sequences of different lengths. **Returns:** `A list of integers in the range [0, 1]` 1 for a special token, 0 for a sequence token. #### save_vocabulary[[transformers.CLIPTokenizer.save_vocabulary]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/tokenization_utils_tokenizers.py#L408) ## CLIPTokenizerFast[[transformers.CLIPTokenizer]] #### transformers.CLIPTokenizer[[transformers.CLIPTokenizer]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/tokenization_clip.py#L28) Construct a CLIP tokenizer (backed by HuggingFace's *tokenizers* library). Based on byte-level Byte-Pair-Encoding. This tokenizer inherits from [TokenizersBackend](/docs/transformers/v5.2.0/ja/main_classes/tokenizer#transformers.TokenizersBackend) which contains most of the main methods. Users should refer to this superclass for more information regarding those methods. **Parameters:** vocab (`str`, `dict` or `list`, *optional*) : Vocabulary dict to use for the tokenizer. merges (`str` or `list`, *optional*) : Merges list to use for the BPE tokenizer. unk_token (`str`, *optional*, defaults to `""`) : 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 `""`) : The beginning of sequence token. eos_token (`str`, *optional*, defaults to `""`) : The end of sequence token. pad_token (`str`, *optional*, defaults to `""`) : The token used for padding, for example when batching sequences of different lengths. ## CLIPImageProcessor[[transformers.CLIPImageProcessor]] #### transformers.CLIPImageProcessor[[transformers.CLIPImageProcessor]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/image_processing_clip.py#L51) Constructs a CLIP image processor. preprocesstransformers.CLIPImageProcessor.preprocesshttps://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/image_processing_clip.py#L199[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']]"}, {"name": "do_resize", "val": ": bool | None = None"}, {"name": "size", "val": ": dict[str, int] | None = None"}, {"name": "resample", "val": ": PIL.Image.Resampling | None = None"}, {"name": "do_center_crop", "val": ": bool | None = None"}, {"name": "crop_size", "val": ": int | None = None"}, {"name": "do_rescale", "val": ": bool | None = None"}, {"name": "rescale_factor", "val": ": float | None = None"}, {"name": "do_normalize", "val": ": bool | None = None"}, {"name": "image_mean", "val": ": float | list[float] | None = None"}, {"name": "image_std", "val": ": float | list[float] | None = None"}, {"name": "do_convert_rgb", "val": ": bool | None = None"}, {"name": "return_tensors", "val": ": str | transformers.utils.generic.TensorType | None = None"}, {"name": "data_format", "val": ": transformers.image_utils.ChannelDimension | None = "}, {"name": "input_data_format", "val": ": str | transformers.image_utils.ChannelDimension | None = None"}, {"name": "**kwargs", "val": ""}]- **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.0 Preprocess an image or batch of images. **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. ## CLIPImageProcessorFast[[transformers.CLIPImageProcessorFast]] #### transformers.CLIPImageProcessorFast[[transformers.CLIPImageProcessorFast]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/image_processing_clip_fast.py#L23) Constructs a fast Clip image processor. preprocesstransformers.CLIPImageProcessorFast.preprocesshttps://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/image_processing_utils_fast.py#L838[{"name": "images", "val": ": typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']]"}, {"name": "*args", "val": ""}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.processing_utils.ImagesKwargs]"}]- **images** (`Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list, list, list]`) -- 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_convert_rgb** (`bool | None.do_convert_rgb`) -- Whether to convert the image to RGB. - **do_resize** (`bool | None.do_resize`) -- Whether to resize the image. - **size** (`Annotated[int | list[int] | tuple[int, ...] | dict[str, int] | None, None]`) -- Describes the maximum input dimensions to the model. - **crop_size** (`Annotated[int | list[int] | tuple[int, ...] | dict[str, int] | None, None]`) -- Size of the output image after applying `center_crop`. - **resample** (`Annotated[Union[PILImageResampling, int, NoneType], None]`) -- 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_rescale** (`bool | None.do_rescale`) -- Whether to rescale the image. - **rescale_factor** (`float | None.rescale_factor`) -- Rescale factor to rescale the image by if `do_rescale` is set to `True`. - **do_normalize** (`bool | None.do_normalize`) -- Whether to normalize the image. - **image_mean** (`float | list[float] | tuple[float, ...] | None.image_mean`) -- Image mean to use for normalization. Only has an effect if `do_normalize` is set to `True`. - **image_std** (`float | list[float] | tuple[float, ...] | None.image_std`) -- Image standard deviation to use for normalization. Only has an effect if `do_normalize` is set to `True`. - **do_pad** (`bool | None.do_pad`) -- Whether to pad the image. Padding is done either to the largest size in the batch or to a fixed square size per image. The exact padding strategy depends on the model. - **pad_size** (`Annotated[int | list[int] | tuple[int, ...] | dict[str, int] | None, None]`) -- The size in `{"height": int, "width" int}` to pad the images to. Must be larger than any image size provided for preprocessing. If `pad_size` is not provided, images will be padded to the largest height and width in the batch. Applied only when `do_pad=True.` - **do_center_crop** (`bool | None.do_center_crop`) -- Whether to center crop the image. - **data_format** (`str | ~image_utils.ChannelDimension | None.data_format`) -- Only `ChannelDimension.FIRST` is supported. Added for compatibility with slow processors. - **input_data_format** (`str | ~image_utils.ChannelDimension | None.input_data_format`) -- 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. - **device** (`Annotated[Union[str, torch.device, NoneType], None]`) -- The device to process the images on. If unset, the device is inferred from the input images. - **return_tensors** (`Annotated[str | ~utils.generic.TensorType | None, None]`) -- Returns stacked tensors if set to `pt, otherwise returns a list of tensors. - **disable_grouping** (`bool | None.disable_grouping`) -- Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 - **image_seq_length** (`int | None.image_seq_length`) -- The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models.0``- **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. **Parameters:** images (`Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list, list, list]`) : 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_convert_rgb (`bool | None.do_convert_rgb`) : Whether to convert the image to RGB. do_resize (`bool | None.do_resize`) : Whether to resize the image. size (`Annotated[int | list[int] | tuple[int, ...] | dict[str, int] | None, None]`) : Describes the maximum input dimensions to the model. crop_size (`Annotated[int | list[int] | tuple[int, ...] | dict[str, int] | None, None]`) : Size of the output image after applying `center_crop`. resample (`Annotated[Union[PILImageResampling, int, NoneType], None]`) : 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_rescale (`bool | None.do_rescale`) : Whether to rescale the image. rescale_factor (`float | None.rescale_factor`) : Rescale factor to rescale the image by if `do_rescale` is set to `True`. do_normalize (`bool | None.do_normalize`) : Whether to normalize the image. image_mean (`float | list[float] | tuple[float, ...] | None.image_mean`) : Image mean to use for normalization. Only has an effect if `do_normalize` is set to `True`. image_std (`float | list[float] | tuple[float, ...] | None.image_std`) : Image standard deviation to use for normalization. Only has an effect if `do_normalize` is set to `True`. do_pad (`bool | None.do_pad`) : Whether to pad the image. Padding is done either to the largest size in the batch or to a fixed square size per image. The exact padding strategy depends on the model. pad_size (`Annotated[int | list[int] | tuple[int, ...] | dict[str, int] | None, None]`) : The size in `{"height": int, "width" int}` to pad the images to. Must be larger than any image size provided for preprocessing. If `pad_size` is not provided, images will be padded to the largest height and width in the batch. Applied only when `do_pad=True.` do_center_crop (`bool | None.do_center_crop`) : Whether to center crop the image. data_format (`str | ~image_utils.ChannelDimension | None.data_format`) : Only `ChannelDimension.FIRST` is supported. Added for compatibility with slow processors. input_data_format (`str | ~image_utils.ChannelDimension | None.input_data_format`) : 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. device (`Annotated[Union[str, torch.device, NoneType], None]`) : The device to process the images on. If unset, the device is inferred from the input images. return_tensors (`Annotated[str | ~utils.generic.TensorType | None, None]`) : Returns stacked tensors if set to `pt, otherwise returns a list of tensors. disable_grouping (`bool | None.disable_grouping`) : Whether to disable grouping of images by size to process them individually and not in batches. If None, will be set to True if the images are on CPU, and False otherwise. This choice is based on empirical observations, as detailed here: https://github.com/huggingface/transformers/pull/38157 image_seq_length (`int | None.image_seq_length`) : The number of image tokens to be used for each image in the input. Added for backward compatibility but this should be set as a processor attribute in future models. **Returns:** ```` - **data** (`dict`) -- Dictionary of lists/arrays/tensors returned by the __call__ method ('pixel_values', etc.). - **tensor_type** (`Union[None, str, TensorType]`, *optional*) -- You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization. ## CLIPProcessor[[transformers.CLIPProcessor]] #### transformers.CLIPProcessor[[transformers.CLIPProcessor]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/processing_clip.py#L23) Constructs a CLIPProcessor which wraps a image processor and a tokenizer into a single processor. [CLIPProcessor](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPProcessor) offers all the functionalities of [CLIPImageProcessorFast](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPImageProcessorFast) and [CLIPTokenizer](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPTokenizer). See the [~CLIPImageProcessorFast](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPImageProcessorFast) and [~CLIPTokenizer](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPTokenizer) for more information. **Parameters:** image_processor (`CLIPImageProcessorFast`) : The image processor is a required input. tokenizer (`CLIPTokenizer`) : The tokenizer is a required input. ## CLIPModel[[transformers.CLIPModel]] #### transformers.CLIPModel[[transformers.CLIPModel]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/modeling_clip.py#L761) The bare Clip Model outputting raw hidden-states without any specific head on top. This model inherits from [PreTrainedModel](/docs/transformers/v5.2.0/ja/main_classes/model#transformers.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](https://pytorch.org/docs/stable/nn.html#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. forwardtransformers.CLIPModel.forwardhttps://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/modeling_clip.py#L874[{"name": "input_ids", "val": ": torch.LongTensor | None = None"}, {"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.LongTensor | None = None"}, {"name": "return_loss", "val": ": bool | None = None"}, {"name": "interpolate_pos_encoding", "val": ": bool = False"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **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](/docs/transformers/v5.2.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.2.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.2.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#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 [CLIPImageProcessorFast](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPImageProcessorFast). See `CLIPImageProcessorFast.__call__()` for details ([CLIPProcessor](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPProcessor) uses [CLIPImageProcessorFast](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPImageProcessorFast) 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?](../glossary#attention-mask) - **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?](../glossary#position-ids) - **return_loss** (`bool`, *optional*) -- Whether or not to return the contrastive loss. - **interpolate_pos_encoding** (`bool`, *optional*, defaults to `False`) -- Whether to interpolate the pre-trained position encodings.0`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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPVisionModel). - **text_model_output** (`.text_model_output`, defaults to `None`) -- The output of the [CLIPTextModel](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPTextModel). - **vision_model_output** (`.vision_model_output`, defaults to `None`) -- The output of the [CLIPVisionModel](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPVisionModel). The [CLIPModel](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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: ```python >>> 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 ``` **Parameters:** config ([CLIPConfig](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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()](/docs/transformers/v5.2.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPVisionModel). - **text_model_output** (`.text_model_output`, defaults to `None`) -- The output of the [CLIPTextModel](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPTextModel). - **vision_model_output** (`.vision_model_output`, defaults to `None`) -- The output of the [CLIPVisionModel](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPVisionModel). #### get_text_features[[transformers.CLIPModel.get_text_features]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/modeling_clip.py#L800) Examples: ```python >>> 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) ``` **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](/docs/transformers/v5.2.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.2.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.2.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#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?](../glossary#attention-mask) 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?](../glossary#position-ids) **Returns:** `[transformers.modeling_outputs.BaseModelOutputWithPooling](/docs/transformers/v5.2.0/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [transformers.modeling_outputs.BaseModelOutputWithPooling](/docs/transformers/v5.2.0/ja/main_classes/output#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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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. #### get_image_features[[transformers.CLIPModel.get_image_features]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/modeling_clip.py#L836) Examples: ```python >>> 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) ``` **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 [CLIPImageProcessorFast](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPImageProcessorFast). See `CLIPImageProcessorFast.__call__()` for details ([CLIPProcessor](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPProcessor) uses [CLIPImageProcessorFast](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPImageProcessorFast) for processing images). interpolate_pos_encoding (`bool`, *optional*, defaults to `False`) : Whether to interpolate the pre-trained position encodings. **Returns:** `[transformers.modeling_outputs.BaseModelOutputWithPooling](/docs/transformers/v5.2.0/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [transformers.modeling_outputs.BaseModelOutputWithPooling](/docs/transformers/v5.2.0/ja/main_classes/output#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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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. ## CLIPTextModel[[transformers.CLIPTextModel]] #### transformers.CLIPTextModel[[transformers.CLIPTextModel]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/modeling_clip.py#L606) The text model from CLIP without any head or projection on top. This model inherits from [PreTrainedModel](/docs/transformers/v5.2.0/ja/main_classes/model#transformers.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](https://pytorch.org/docs/stable/nn.html#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. forwardtransformers.CLIPTextModel.forwardhttps://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/modeling_clip.py#L624[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.Tensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **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](/docs/transformers/v5.2.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.2.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.2.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#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?](../glossary#attention-mask) - **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?](../glossary#position-ids)0[transformers.modeling_outputs.BaseModelOutputWithPooling](/docs/transformers/v5.2.0/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`A [transformers.modeling_outputs.BaseModelOutputWithPooling](/docs/transformers/v5.2.0/ja/main_classes/output#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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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: ```python >>> 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 ``` **Parameters:** config ([CLIPTextConfig](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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()](/docs/transformers/v5.2.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[transformers.modeling_outputs.BaseModelOutputWithPooling](/docs/transformers/v5.2.0/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [transformers.modeling_outputs.BaseModelOutputWithPooling](/docs/transformers/v5.2.0/ja/main_classes/output#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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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. ## CLIPTextModelWithProjection[[transformers.CLIPTextModelWithProjection]] #### transformers.CLIPTextModelWithProjection[[transformers.CLIPTextModelWithProjection]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/modeling_clip.py#L957) The Clip Model with a projection layer on top (a linear layer on top of the pooled output). This model inherits from [PreTrainedModel](/docs/transformers/v5.2.0/ja/main_classes/model#transformers.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](https://pytorch.org/docs/stable/nn.html#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. forwardtransformers.CLIPTextModelWithProjection.forwardhttps://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/modeling_clip.py#L980[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.Tensor | None = None"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **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](/docs/transformers/v5.2.0/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/v5.2.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/v5.2.0/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.__call__) for details. [What are input IDs?](../glossary#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?](../glossary#attention-mask) - **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?](../glossary#position-ids)0`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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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 | None.last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, defaults to `None`) -- Sequence of hidden-states at the output of the last layer of the model. - **hidden_states** (`tuple[torch.FloatTensor, ...] | None.hidden_states`, 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, ...] | None.attentions`, 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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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: ```python >>> 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 ``` **Parameters:** config ([CLIPTextConfig](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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()](/docs/transformers/v5.2.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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 | None.last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, defaults to `None`) -- Sequence of hidden-states at the output of the last layer of the model. - **hidden_states** (`tuple[torch.FloatTensor, ...] | None.hidden_states`, 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, ...] | None.attentions`, 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. ## CLIPVisionModelWithProjection[[transformers.CLIPVisionModelWithProjection]] #### transformers.CLIPVisionModelWithProjection[[transformers.CLIPVisionModelWithProjection]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/modeling_clip.py#L1024) The Clip Model with a projection layer on top (a linear layer on top of the pooled output). This model inherits from [PreTrainedModel](/docs/transformers/v5.2.0/ja/main_classes/model#transformers.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](https://pytorch.org/docs/stable/nn.html#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. forwardtransformers.CLIPVisionModelWithProjection.forwardhttps://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/modeling_clip.py#L1043[{"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "interpolate_pos_encoding", "val": ": bool = False"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **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 [CLIPImageProcessorFast](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPImageProcessorFast). See `CLIPImageProcessorFast.__call__()` for details ([CLIPProcessor](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPProcessor) uses [CLIPImageProcessorFast](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPImageProcessorFast) for processing images). - **interpolate_pos_encoding** (`bool`, *optional*, defaults to `False`) -- Whether to interpolate the pre-trained position encodings.0`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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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 | None.last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, defaults to `None`) -- Sequence of hidden-states at the output of the last layer of the model. - **hidden_states** (`tuple[torch.FloatTensor, ...] | None.hidden_states`, 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, ...] | None.attentions`, 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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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: ```python >>> 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 ``` **Parameters:** config ([CLIPVisionConfig](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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()](/docs/transformers/v5.2.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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 | None.last_hidden_state` of shape `(batch_size, sequence_length, hidden_size)`, defaults to `None`) -- Sequence of hidden-states at the output of the last layer of the model. - **hidden_states** (`tuple[torch.FloatTensor, ...] | None.hidden_states`, 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, ...] | None.attentions`, 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. ## CLIPVisionModel[[transformers.CLIPVisionModel]] #### transformers.CLIPVisionModel[[transformers.CLIPVisionModel]] [Source](https://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/modeling_clip.py#L708) The vision model from CLIP without any head or projection on top. This model inherits from [PreTrainedModel](/docs/transformers/v5.2.0/ja/main_classes/model#transformers.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](https://pytorch.org/docs/stable/nn.html#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. forwardtransformers.CLIPVisionModel.forwardhttps://github.com/huggingface/transformers/blob/v5.2.0/src/transformers/models/clip/modeling_clip.py#L723[{"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "interpolate_pos_encoding", "val": ": bool = False"}, {"name": "**kwargs", "val": ": typing_extensions.Unpack[transformers.utils.generic.TransformersKwargs]"}]- **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 [CLIPImageProcessorFast](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPImageProcessorFast). See `CLIPImageProcessorFast.__call__()` for details ([CLIPProcessor](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPProcessor) uses [CLIPImageProcessorFast](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.CLIPImageProcessorFast) for processing images). - **interpolate_pos_encoding** (`bool`, *optional*, defaults to `False`) -- Whether to interpolate the pre-trained position encodings.0[transformers.modeling_outputs.BaseModelOutputWithPooling](/docs/transformers/v5.2.0/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`A [transformers.modeling_outputs.BaseModelOutputWithPooling](/docs/transformers/v5.2.0/ja/main_classes/output#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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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: ```python >>> from PIL import Image >>> import httpx >>> from io import BytesIO >>> 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" >>> with httpx.stream("GET", url) as response: ... image = Image.open(BytesIO(response.read())) >>> 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 ``` **Parameters:** config ([CLIPVisionConfig](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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()](/docs/transformers/v5.2.0/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights. **Returns:** `[transformers.modeling_outputs.BaseModelOutputWithPooling](/docs/transformers/v5.2.0/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`` A [transformers.modeling_outputs.BaseModelOutputWithPooling](/docs/transformers/v5.2.0/ja/main_classes/output#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](/docs/transformers/v5.2.0/ja/model_doc/clip#transformers.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.