# Chinese-CLIP

## Overview

Chinese-CLIP An Yang, Junshu Pan, Junyang Lin, Rui Men, Yichang Zhang, Jingren Zhou, Chang Zhou [Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese](https://huggingface.co/papers/2211.01335) で提案されました。周、張周。
Chinese-CLIP は、中国語の画像とテキストのペアの大規模なデータセットに対する CLIP (Radford et al., 2021) の実装です。クロスモーダル検索を実行できるほか、ゼロショット画像分類、オープンドメインオブジェクト検出などのビジョンタスクのビジョンバックボーンとしても機能します。オリジナルの中国語-CLIPコードは[このリンクで](https://github.com/OFA-Sys/Chinese-CLIP)。

論文の要約は次のとおりです。

*CLIP の大成功 (Radford et al., 2021) により、視覚言語の事前訓練のための対照学習の研究と応用が促進されました。この研究では、ほとんどのデータが公開されているデータセットから取得された中国語の画像とテキストのペアの大規模なデータセットを構築し、新しいデータセットで中国語の CLIP モデルを事前トレーニングします。当社では、7,700 万から 9 億 5,800 万のパラメータにわたる、複数のサイズの 5 つの中国 CLIP モデルを開発しています。さらに、モデルのパフォーマンスを向上させるために、最初に画像エンコーダーをフリーズさせてモデルをトレーニングし、次にすべてのパラメーターを最適化してトレーニングする 2 段階の事前トレーニング方法を提案します。私たちの包括的な実験では、中国の CLIP がゼロショット学習と微調整のセットアップで MUGE、Flickr30K-CN、および COCO-CN 上で最先端のパフォーマンスを達成でき、ゼロで競争力のあるパフォーマンスを達成できることを実証しています。 - ELEVATER ベンチマークでの評価に基づくショット画像の分類 (Li et al., 2022)。コード、事前トレーニング済みモデル、デモがリリースされました。*

Chinese-CLIP モデルは、[OFA-Sys](https://huggingface.co/OFA-Sys) によって提供されました。

## Usage example

以下のコード スニペットは、画像とテキストの特徴と類似性を計算する方法を示しています。

```python
>>> from PIL import Image
>>> import requests
>>> from transformers import ChineseCLIPProcessor, ChineseCLIPModel

>>> model = ChineseCLIPModel.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16")
>>> processor = ChineseCLIPProcessor.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16")

>>> url = "https://clip-cn-beijing.oss-cn-beijing.aliyuncs.com/pokemon.jpeg"
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> # Squirtle, Bulbasaur, Charmander, Pikachu in English
>>> texts = ["杰尼龟", "妙蛙种子", "小火龙", "皮卡丘"]

>>> # compute image feature
>>> inputs = processor(images=image, return_tensors="pt")
>>> image_features = model.get_image_features(**inputs)
>>> image_features = image_features / image_features.norm(p=2, dim=-1, keepdim=True)  # normalize

>>> # compute text features
>>> inputs = processor(text=texts, padding=True, return_tensors="pt")
>>> text_features = model.get_text_features(**inputs)
>>> text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)  # normalize

>>> # compute image-text similarity scores
>>> inputs = processor(text=texts, 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)  # probs: [[1.2686e-03, 5.4499e-02, 6.7968e-04, 9.4355e-01]]
```

現在、次のスケールの事前トレーニング済み Chinese-CLIP モデルが 🤗 Hub で利用可能です。

- [OFA-Sys/chinese-clip-vit-base-patch16](https://huggingface.co/OFA-Sys/chinese-clip-vit-base-patch16)
- [OFA-Sys/chinese-clip-vit-large-patch14](https://huggingface.co/OFA-Sys/chinese-clip-vit-large-patch14)
- [OFA-Sys/chinese-clip-vit-large-patch14-336px](https://huggingface.co/OFA-Sys/chinese-clip-vit-large-patch14-336px)
- [OFA-Sys/chinese-clip-vit-huge-patch14](https://huggingface.co/OFA-Sys/chinese-clip-vit-huge-patch14)

## ChineseCLIPConfig[[transformers.ChineseCLIPConfig]]

#### transformers.ChineseCLIPConfig[[transformers.ChineseCLIPConfig]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/chinese_clip/configuration_chinese_clip.py#L126)

This is the configuration class to store the configuration of a ChineseCLIPModel. It is used to instantiate a Chinese Clip
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
defaults will yield a similar configuration to that of the [OFA-Sys/chinese-clip-vit-base-patch16](https://huggingface.co/OFA-Sys/chinese-clip-vit-base-patch16)

Configuration objects inherit from [PreTrainedConfig](/docs/transformers/main/ja/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the
documentation from [PreTrainedConfig](/docs/transformers/main/ja/main_classes/configuration#transformers.PreTrainedConfig) for more information.

Example:

```python
>>> from transformers import ChineseCLIPConfig, ChineseCLIPModel

>>> # Initializing a ChineseCLIPConfig with OFA-Sys/chinese-clip-vit-base-patch16 style configuration
>>> configuration = ChineseCLIPConfig()

>>> # Initializing a ChineseCLIPModel (with random weights) from the OFA-Sys/chinese-clip-vit-base-patch16 style configuration
>>> model = ChineseCLIPModel(configuration)

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

>>> # We can also initialize a ChineseCLIPConfig from a ChineseCLIPTextConfig and a ChineseCLIPVisionConfig

>>> # Initializing a ChineseCLIPTextConfig and ChineseCLIPVisionConfig configuration
>>> config_text = ChineseCLIPTextConfig()
>>> config_vision = ChineseCLIPVisionConfig()

>>> config = ChineseCLIPConfig(text_config=config_text, vision_config=config_vision)
```

**Parameters:**

text_config (`Union[dict, ~models.chinese_clip.configuration_chinese_clip.ChineseCLIPTextConfig]`, *optional*) : The config object or dictionary of the text backbone.

vision_config (`Union[dict, ~models.chinese_clip.configuration_chinese_clip.ChineseCLIPVisionConfig]`, *optional*) : The config object or dictionary of the vision backbone.

projection_dim (`int`, *optional*, defaults to `512`) : Dimensionality of text and vision projection layers.

logit_scale_init_value (`Union[float, int]`, *optional*, defaults to `2.6592`) : The initial value of the *logit_scale* parameter.

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).

initializer_range (`float`, *optional*, defaults to `0.02`) : The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

## ChineseCLIPTextConfig[[transformers.ChineseCLIPTextConfig]]

#### transformers.ChineseCLIPTextConfig[[transformers.ChineseCLIPTextConfig]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/chinese_clip/configuration_chinese_clip.py#L31)

This is the configuration class to store the configuration of a ChineseCLIPModel. It is used to instantiate a Chinese Clip
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
defaults will yield a similar configuration to that of the [OFA-Sys/chinese-clip-vit-base-patch16](https://huggingface.co/OFA-Sys/chinese-clip-vit-base-patch16)

Configuration objects inherit from [PreTrainedConfig](/docs/transformers/main/ja/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the
documentation from [PreTrainedConfig](/docs/transformers/main/ja/main_classes/configuration#transformers.PreTrainedConfig) for more information.

Example:

```python
>>> from transformers import ChineseCLIPTextConfig, ChineseCLIPTextModel

>>> # Initializing a ChineseCLIPTextConfig with OFA-Sys/chinese-clip-vit-base-patch16 style configuration
>>> configuration = ChineseCLIPTextConfig()

>>> # Initializing a ChineseCLIPTextModel (with random weights) from the OFA-Sys/chinese-clip-vit-base-patch16 style configuration
>>> model = ChineseCLIPTextModel(configuration)

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

**Parameters:**

vocab_size (`int`, *optional*, defaults to `30522`) : Vocabulary size of the model. Defines the number of different tokens that can be represented by the `input_ids`.

hidden_size (`int`, *optional*, defaults to `768`) : Dimension of the hidden representations.

intermediate_size (`int`, *optional*, defaults to `3072`) : Dimension of the MLP representations.

num_hidden_layers (`int`, *optional*, defaults to `12`) : Number of hidden layers in the Transformer decoder.

num_attention_heads (`int`, *optional*, defaults to `12`) : Number of attention heads for each attention layer in the Transformer decoder.

max_position_embeddings (`int`, *optional*, defaults to `512`) : The maximum sequence length that this model might ever be used with.

hidden_act (`str`, *optional*, defaults to `gelu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc.

layer_norm_eps (`float`, *optional*, defaults to `1e-12`) : The epsilon used by the layer normalization layers.

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 `0`) : Token id used for padding in the vocabulary.

bos_token_id (`int`, *optional*, defaults to `0`) : Token id used for beginning-of-stream in the vocabulary.

eos_token_id (`int`, *optional*) : Token id used for end-of-stream in the vocabulary.

hidden_dropout_prob (`Union[float, int]`, *optional*, defaults to `0.1`) : The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.

attention_probs_dropout_prob (`Union[float, int]`, *optional*, defaults to `0.1`) : The dropout ratio for the attention probabilities.

type_vocab_size (`int`, *optional*, defaults to 2) : The vocabulary size of the `token_type_ids` passed when calling [ChineseCLIPModel](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPModel).

## ChineseCLIPVisionConfig[[transformers.ChineseCLIPVisionConfig]]

#### transformers.ChineseCLIPVisionConfig[[transformers.ChineseCLIPVisionConfig]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/chinese_clip/configuration_chinese_clip.py#L82)

This is the configuration class to store the configuration of a ChineseCLIPModel. It is used to instantiate a Chinese Clip
model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
defaults will yield a similar configuration to that of the [OFA-Sys/chinese-clip-vit-base-patch16](https://huggingface.co/OFA-Sys/chinese-clip-vit-base-patch16)

Configuration objects inherit from [PreTrainedConfig](/docs/transformers/main/ja/main_classes/configuration#transformers.PreTrainedConfig) and can be used to control the model outputs. Read the
documentation from [PreTrainedConfig](/docs/transformers/main/ja/main_classes/configuration#transformers.PreTrainedConfig) for more information.

Example:
```python
>>> from transformers import ChineseCLIPVisionConfig, ChineseCLIPVisionModel

>>> # Initializing a ChineseCLIPVisionConfig with OFA-Sys/chinese-clip-vit-base-patch16 style configuration
>>> configuration = ChineseCLIPVisionConfig()

>>> # Initializing a ChineseCLIPVisionModel (with random weights) from the OFA-Sys/chinese-clip-vit-base-patch16 style configuration
>>> model = ChineseCLIPVisionModel(configuration)

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

**Parameters:**

hidden_size (`int`, *optional*, defaults to `768`) : Dimension of the hidden representations.

intermediate_size (`int`, *optional*, defaults to `3072`) : Dimension of the MLP representations.

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 decoder.

num_attention_heads (`int`, *optional*, defaults to `12`) : Number of attention heads for each attention layer in the Transformer decoder.

num_channels (`int`, *optional*, defaults to `3`) : The number of input channels.

image_size (`Union[int, list[int], tuple[int, int]]`, *optional*, defaults to `224`) : The size (resolution) of each image.

patch_size (`Union[int, list[int], tuple[int, int]]`, *optional*, defaults to `32`) : The size (resolution) of each patch.

hidden_act (`str`, *optional*, defaults to `quick_gelu`) : The non-linear activation function (function or string) in the decoder. For example, `"gelu"`, `"relu"`, `"silu"`, etc.

layer_norm_eps (`float`, *optional*, defaults to `1e-05`) : The epsilon used by the layer normalization layers.

attention_dropout (`Union[int, 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).

## ChineseCLIPImageProcessor[[transformers.ChineseCLIPImageProcessor]]

#### transformers.ChineseCLIPImageProcessor[[transformers.ChineseCLIPImageProcessor]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/chinese_clip/image_processing_chinese_clip.py#L22)

Constructs a ChineseCLIPImageProcessor image processor.

preprocesstransformers.ChineseCLIPImageProcessor.preprocesshttps://github.com/huggingface/transformers/blob/main/src/transformers/image_processing_utils.py#L382[{"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[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]`) --
  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`.
- **return_tensors** (`str` or [TensorType](/docs/transformers/main/ja/internal/file_utils#transformers.TensorType), *optional*) --
  Returns stacked tensors if set to `'pt'`, otherwise returns a list of tensors.
- ****kwargs** (`ImagesKwargs`, *optional*) --
  Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class
  for the complete list of supported arguments.0`~image_processing_base.BatchFeature`- **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:**

- ****kwargs** (`ImagesKwargs`, *optional*) : Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments.

**Returns:**

``~image_processing_base.BatchFeature``

- **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.

## ChineseCLIPImageProcessorFast[[transformers.ChineseCLIPImageProcessor]]

#### transformers.ChineseCLIPImageProcessor[[transformers.ChineseCLIPImageProcessor]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/chinese_clip/image_processing_chinese_clip.py#L22)

Constructs a ChineseCLIPImageProcessor image processor.

preprocesstransformers.ChineseCLIPImageProcessor.preprocesshttps://github.com/huggingface/transformers/blob/main/src/transformers/image_processing_utils.py#L382[{"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[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]`) --
  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`.
- **return_tensors** (`str` or [TensorType](/docs/transformers/main/ja/internal/file_utils#transformers.TensorType), *optional*) --
  Returns stacked tensors if set to `'pt'`, otherwise returns a list of tensors.
- ****kwargs** (`ImagesKwargs`, *optional*) --
  Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class
  for the complete list of supported arguments.0`~image_processing_base.BatchFeature`- **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:**

- ****kwargs** (`ImagesKwargs`, *optional*) : Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments.

**Returns:**

``~image_processing_base.BatchFeature``

- **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.

## ChineseCLIPProcessor[[transformers.ChineseCLIPProcessor]]

#### transformers.ChineseCLIPProcessor[[transformers.ChineseCLIPProcessor]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/chinese_clip/processing_chinese_clip.py#L23)

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

[ChineseCLIPProcessor](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPProcessor) offers all the functionalities of [ChineseCLIPImageProcessor](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPImageProcessor) and [BertTokenizer](/docs/transformers/main/ja/model_doc/bert#transformers.BertTokenizer). See the
[~ChineseCLIPImageProcessor](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPImageProcessor) and [~BertTokenizer](/docs/transformers/main/ja/model_doc/bert#transformers.BertTokenizer) for more information.

**Parameters:**

image_processor (`ChineseCLIPImageProcessor`) : The image processor is a required input.

tokenizer (`BertTokenizer`) : The tokenizer is a required input.

## ChineseCLIPModel[[transformers.ChineseCLIPModel]]

#### transformers.ChineseCLIPModel[[transformers.ChineseCLIPModel]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/chinese_clip/modeling_chinese_clip.py#L820)

The bare Chinese Clip Model outputting raw hidden-states without any specific head on top.

This model inherits from [PreTrainedModel](/docs/transformers/main/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.ChineseCLIPModel.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/chinese_clip/modeling_chinese_clip.py#L916[{"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": "token_type_ids", "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/main/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/main/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/main/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
  [ChineseCLIPImageProcessor](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPImageProcessor). See `ChineseCLIPImageProcessor.__call__()` for details ([ChineseCLIPProcessor](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPProcessor) uses
  [ChineseCLIPImageProcessor](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPImageProcessor) 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)
- **token_type_ids** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:

  - 0 corresponds to a *sentence A* token,
  - 1 corresponds to a *sentence B* token.

  [What are token type IDs?](../glossary#token-type-ids)
- **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`ChineseCLIPOutput` or `tuple(torch.FloatTensor)`A `ChineseCLIPOutput` 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 ([ChineseCLIPConfig](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPConfig)) and inputs.
The [ChineseCLIPModel](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPModel) 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.

- **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 [ChineseCLIPTextModel](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPTextModel).
- **image_embeds** (`torch.FloatTensor` of shape `(batch_size, output_dim`) -- The image embeddings obtained by applying the projection layer to the pooled output of [ChineseCLIPVisionModel](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPVisionModel).
- **text_model_output** (`~modeling_outputs.BaseModelOutputWithPooling`, defaults to `None`) -- The output of the [ChineseCLIPTextModel](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPTextModel).
- **vision_model_output** (`~modeling_outputs.BaseModelOutputWithPooling`, defaults to `None`) -- The output of the [ChineseCLIPVisionModel](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPVisionModel).

Examples:

```python
>>> import torch
>>> from transformers import AutoProcessor, ChineseCLIPModel
>>> from transformers.image_utils import load_image

>>> model = ChineseCLIPModel.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16")
>>> processor = AutoProcessor.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16")

>>> url = "https://clip-cn-beijing.oss-cn-beijing.aliyuncs.com/pokemon.jpeg"
>>> image = load_image(url)

>>> inputs = processor(text=["杰尼龟", "妙蛙种子", "小火龙", "皮卡丘"], 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 ([ChineseCLIPConfig](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPConfig)) : 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/main/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

``ChineseCLIPOutput` or `tuple(torch.FloatTensor)``

A `ChineseCLIPOutput` 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 ([ChineseCLIPConfig](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPConfig)) and inputs.
#### get_text_features[[transformers.ChineseCLIPModel.get_text_features]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/chinese_clip/modeling_chinese_clip.py#L840)

- **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.

Examples:

```python
>>> import torch
>>> from transformers import AutoTokenizer, ChineseCLIPModel

>>> model = ChineseCLIPModel.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16")
>>> tokenizer = AutoTokenizer.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16")

>>> inputs = tokenizer(["杰尼龟", "妙蛙种子", "小火龙", "皮卡丘"], padding=True, return_tensors="pt")
>>> with torch.inference_mode():
...     text_features = model.get_text_features(**inputs)
>>> text_features = text_features / text_features.norm(p=2, dim=-1, keepdim=True)
```

**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/main/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/main/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and [PreTrainedTokenizer.__call__()](/docs/transformers/main/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)

token_type_ids (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) : Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:  - 0 corresponds to a *sentence A* token, - 1 corresponds to a *sentence B* token.  [What are token type IDs?](../glossary#token-type-ids)

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:**

`[BaseModelOutputWithPooling](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)``

A [BaseModelOutputWithPooling](/docs/transformers/main/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 ([ChineseCLIPConfig](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPConfig)) and inputs.
#### get_image_features[[transformers.ChineseCLIPModel.get_image_features]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/chinese_clip/modeling_chinese_clip.py#L877)

- **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.

Examples:

```python
>>> import torch
>>> from transformers import AutoProcessor, ChineseCLIPModel
>>> from transformers.image_utils import load_image

>>> model = ChineseCLIPModel.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16")
>>> processor = AutoProcessor.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16")

>>> url = "https://clip-cn-beijing.oss-cn-beijing.aliyuncs.com/pokemon.jpeg"
>>> image = load_image(url)

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

>>> with torch.inference_mode():
...     image_features = model.get_image_features(**inputs)
>>> image_features = image_features / image_features.norm(p=2, dim=-1, keepdim=True)
```

**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 [ChineseCLIPImageProcessor](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPImageProcessor). See `ChineseCLIPImageProcessor.__call__()` for details ([ChineseCLIPProcessor](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPProcessor) uses [ChineseCLIPImageProcessor](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPImageProcessor) for processing images).

interpolate_pos_encoding (`bool`, *optional*, defaults to `False`) : Whether to interpolate the pre-trained position encodings.

**Returns:**

`[BaseModelOutputWithPooling](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)``

A [BaseModelOutputWithPooling](/docs/transformers/main/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 ([ChineseCLIPConfig](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPConfig)) and inputs.

## ChineseCLIPTextModel[[transformers.ChineseCLIPTextModel]]

#### transformers.ChineseCLIPTextModel[[transformers.ChineseCLIPTextModel]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/chinese_clip/modeling_chinese_clip.py#L716)

The text model from CHINESE_CLIP without any head or projection on top.

This model inherits from [PreTrainedModel](/docs/transformers/main/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.ChineseCLIPTextModel.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/chinese_clip/modeling_chinese_clip.py#L739[{"name": "input_ids", "val": ": torch.Tensor | None = None"}, {"name": "attention_mask", "val": ": torch.Tensor | None = None"}, {"name": "token_type_ids", "val": ": torch.Tensor | None = None"}, {"name": "position_ids", "val": ": torch.Tensor | None = None"}, {"name": "inputs_embeds", "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/main/ja/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](/docs/transformers/main/ja/internal/tokenization_utils#transformers.PreTrainedTokenizerBase.encode) and
  [PreTrainedTokenizer.__call__()](/docs/transformers/main/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)
- **token_type_ids** (`torch.Tensor` of shape `(batch_size, sequence_length)`, *optional*) --
  Segment token indices to indicate first and second portions of the inputs. Indices are selected in `[0, 1]`:

  - 0 corresponds to a *sentence A* token,
  - 1 corresponds to a *sentence B* token.

  [What are token type IDs?](../glossary#token-type-ids)
- **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)
- **inputs_embeds** (`torch.Tensor` of shape `(batch_size, sequence_length, hidden_size)`, *optional*) --
  Optionally, instead of passing `input_ids` you can choose to directly pass an embedded representation. This
  is useful if you want more control over how to convert `input_ids` indices into associated vectors than the
  model's internal embedding lookup matrix.0[BaseModelOutputWithPooling](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`A [BaseModelOutputWithPooling](/docs/transformers/main/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 ([ChineseCLIPConfig](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPConfig)) and inputs.
The [ChineseCLIPTextModel](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPTextModel) 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.

- **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.

Examples:

```python
>>> from transformers import AutoTokenizer, ChineseCLIPTextModel

>>> model = ChineseCLIPTextModel.from_pretrained("openai/chinese_clip-vit-base-patch32")
>>> tokenizer = AutoTokenizer.from_pretrained("openai/chinese_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 ([ChineseCLIPTextModel](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPTextModel)) : 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/main/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

add_pooling_layer (`bool`, *optional*, defaults to `True`) : Whether to add a pooling layer

**Returns:**

`[BaseModelOutputWithPooling](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)``

A [BaseModelOutputWithPooling](/docs/transformers/main/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 ([ChineseCLIPConfig](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPConfig)) and inputs.

## ChineseCLIPVisionModel[[transformers.ChineseCLIPVisionModel]]

#### transformers.ChineseCLIPVisionModel[[transformers.ChineseCLIPVisionModel]]

[Source](https://github.com/huggingface/transformers/blob/main/src/transformers/models/chinese_clip/modeling_chinese_clip.py#L645)

The vision model from CHINESE_CLIP without any head or projection on top.

This model inherits from [PreTrainedModel](/docs/transformers/main/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.ChineseCLIPVisionModel.forwardhttps://github.com/huggingface/transformers/blob/main/src/transformers/models/chinese_clip/modeling_chinese_clip.py#L661[{"name": "pixel_values", "val": ": torch.FloatTensor | None = None"}, {"name": "interpolate_pos_encoding", "val": ": bool | None = 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
  [ChineseCLIPImageProcessor](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPImageProcessor). See `ChineseCLIPImageProcessor.__call__()` for details ([ChineseCLIPProcessor](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPProcessor) uses
  [ChineseCLIPImageProcessor](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPImageProcessor) for processing images).
- **interpolate_pos_encoding** (`bool`, *optional*, defaults to `False`) --
  Whether to interpolate the pre-trained position encodings.0[BaseModelOutputWithPooling](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`A [BaseModelOutputWithPooling](/docs/transformers/main/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 ([ChineseCLIPConfig](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPConfig)) and inputs.
The [ChineseCLIPVisionModel](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPVisionModel) 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.

- **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.

Examples:

```python
>>> import httpx
>>> from io import BytesIO
>>> from PIL import Image
>>> from transformers import CLIPProcessor, ChineseCLIPVisionModel

>>> model = ChineseCLIPVisionModel.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16")
>>> processor = CLIPProcessor.from_pretrained("OFA-Sys/chinese-clip-vit-base-patch16")

>>> url = "https://clip-cn-beijing.oss-cn-beijing.aliyuncs.com/pokemon.jpeg"
>>> 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 ([ChineseCLIPVisionConfig](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPVisionConfig)) : 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/main/ja/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

**Returns:**

`[BaseModelOutputWithPooling](/docs/transformers/main/ja/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)``

A [BaseModelOutputWithPooling](/docs/transformers/main/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 ([ChineseCLIPConfig](/docs/transformers/main/ja/model_doc/chinese_clip#transformers.ChineseCLIPConfig)) and inputs.