CLIP¶

Overview¶

The CLIP model was proposed in Learning Transferable Visual Models From Natural Language Supervision by 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. CLIP (Contrastive Language-Image Pre-Training) is a neural network trained on a variety of (image, text) pairs. It can be instructed in natural language to predict the most relevant text snippet, given an image, without directly optimizing for the task, similarly to the zero-shot capabilities of GPT-2 and 3.

The abstract from the paper is the following:

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on. We release our code and pre-trained model weights at this https URL.

Usage¶

CLIP is a multi-modal vision and language model. It can be used for image-text similarity and for zero-shot image classification. CLIP uses a ViT like transformer to get visual features and a causal language model to get the text features. Both the text and visual features are then projected to a latent space with identical dimension. The dot product between the projected image and text features is then used as a similar score.

To feed images to the Transformer encoder, each image is split into a sequence of fixed-size non-overlapping patches, which are then linearly embedded. A [CLS] token is added to serve as representation of an entire image. The authors also add absolute position embeddings, and feed the resulting sequence of vectors to a standard Transformer encoder. The CLIPFeatureExtractor can be used to resize (or rescale) and normalize images for the model.

The CLIPTokenizer is used to encode the text. The CLIPProcessor wraps CLIPFeatureExtractor and CLIPTokenizer into a single instance to both encode the text and prepare the images. The following example shows how to get the image-text similarity scores using CLIPProcessor and CLIPModel.

>>> 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

This model was contributed by valhalla. The original code can be found here.

CLIPConfig¶

class transformers.CLIPConfig(text_config_dict=None, vision_config_dict=None, projection_dim=512, logit_scale_init_value=2.6592, **kwargs)[source]¶

CLIPConfig is the configuration class to store the configuration of a CLIPModel. It is used to instantiate CLIP model according to the specified arguments, defining the text model and vision model configs.

Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.

Parameters

text_config_dict (dict, optional) – Dictionary of configuration options used to initialize CLIPTextConfig.
vision_config_dict (dict, optional) – Dictionary of configuration options used to initialize CLIPVisionConfig.
projection_dim (int, optional, defaults to 512) – Dimentionality of text and vision projection layers.
logit_scale_init_value (float, optional, defaults to 2.6592) – The inital value of the logit_scale paramter. Default is used as per the original CLIP implementation.
kwargs (optional) – Dictionary of keyword arguments.

classmethod from_text_vision_configs(text_config: transformers.models.clip.configuration_clip.CLIPTextConfig, vision_config: transformers.models.clip.configuration_clip.CLIPVisionConfig, **kwargs)[source]¶

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

Returns: An instance of a configuration object
Return type: CLIPConfig

CLIPTextConfig¶

class transformers.CLIPTextConfig(vocab_size=49408, hidden_size=512, intermediate_size=2048, num_hidden_layers=12, num_attention_heads=8, max_position_embeddings=77, hidden_act='quick_gelu', layer_norm_eps=1e-05, dropout=0.0, attention_dropout=0.0, initializer_range=0.02, initializer_factor=1.0, pad_token_id=1, bos_token_id=0, eos_token_id=2, **kwargs)[source]¶

This is the configuration class to store the configuration of a CLIPModel. It is used to instantiate an 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 CLIP openai/clip-vit-base-patch32 architecture.

Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.

Parameters

vocab_size (int, optional, defaults to 49408) – Vocabulary size of the CLIP text model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling CLIPModel.
hidden_size (int, optional, defaults to 512) – Dimensionality of the encoder layers and the pooler layer.
intermediate_size (int, optional, defaults to 2048) – Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.
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-5) – The epsilon used by the layer normalization layers.
attention_dropout (float, optional, defaults to 0.0) – The dropout ratio for the attention probabilities.
dropout (float, optional, defaults to 0.0) – The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
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) – A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing).

Example:

>>> from transformers import CLIPTextModel, CLIPTextConfig

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

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

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

CLIPVisionConfig¶

class transformers.CLIPVisionConfig(hidden_size=768, intermediate_size=3072, num_hidden_layers=12, num_attention_heads=12, image_size=224, patch_size=32, hidden_act='quick_gelu', layer_norm_eps=1e-05, dropout=0.0, attention_dropout=0.0, initializer_range=0.02, initializer_factor=1.0, **kwargs)[source]¶

This is the configuration class to store the configuration of a CLIPModel. It is used to instantiate an 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 CLIP openai/clip-vit-base-patch32 architecture.

Configuration objects inherit from PretrainedConfig and can be used to control the model outputs. Read the documentation from PretrainedConfig for more information.

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.
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.
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-5) – The epsilon used by the layer normalization layers.
dropout (float, optional, defaults to 0.0) – The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler.
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) – A factor for initializing all weight matrices (should be kept to 1, used internally for initialization testing).

Example:

>>> from transformers import CLIPVisionModel, CLIPVisionConfig

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

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

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

CLIPTokenizer¶

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

This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will be encoded differently whether it is at the beginning of the sentence (without space) or not:

You can get around that behavior by passing add_prefix_space=True when instantiating this tokenizer or when you call it on some text, but since the model was not pretrained this way, it might yield a decrease in performance.

Note

When used with is_split_into_words=True, this tokenizer will add a space before each word (even the first one).

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

Parameters

vocab_file (str) – Path to the vocabulary file.
merges_file (str) – Path to the merges file.
errors (str, optional, defaults to "replace") – Paradigm to follow when decoding bytes to UTF-8. See bytes.decode for more information.
unk_token (str, optional, defaults to <|endoftext|>) – The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.
bos_token (str, optional, defaults to <|endoftext|>) – The beginning of sequence token.
eos_token (str, optional, defaults to <|endoftext|>) – The end of sequence token.
add_prefix_space (bool, optional, defaults to False) – Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word. (CLIP tokenizer detect beginning of words by the preceding space).

build_inputs_with_special_tokens(token_ids_0: List[int], token_ids_1: Optional[List[int]] = None) → List[int][source]¶

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

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

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

Parameters

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

Returns

List of input IDs with the appropriate special tokens.

Return type

List[int]

create_token_type_ids_from_sequences(token_ids_0: List[int], token_ids_1: Optional[List[int]] = None) → List[int]¶

Create the token type IDs corresponding to the sequences passed. What are token type IDs?

Should be overridden in a subclass if the model has a special way of building those.

Parameters

token_ids_0 (List[int]) – The first tokenized sequence.
token_ids_1 (List[int], optional) – The second tokenized sequence.

Returns

The token type ids.

Return type

List[int]

get_special_tokens_mask(token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False) → List[int][source]¶

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

Parameters

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

Returns

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

Return type

List[int]

save_vocabulary(save_directory: str, filename_prefix: Optional[str] = None) → Tuple[str][source]¶

Save only the vocabulary of the tokenizer (vocabulary + added tokens).

This method won’t save the configuration and special token mappings of the tokenizer. Use _save_pretrained() to save the whole state of the tokenizer.

Parameters

save_directory (str) – The directory in which to save the vocabulary.
filename_prefix (str, optional) – An optional prefix to add to the named of the saved files.

Returns

Paths to the files saved.

Return type

Tuple(str)

CLIPTokenizerFast¶

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

This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will be encoded differently whether it is at the beginning of the sentence (without space) or not:

>>> from transformers import CLIPTokenizerFast
>>> tokenizer = CLIPTokenizerFast.from_pretrained("openai/clip-vit-base-patch32")
>>> tokenizer("Hello world")['input_ids']
[15496, 995]
>>> tokenizer(" Hello world")['input_ids']
[18435, 995]

You can get around that behavior by passing add_prefix_space=True when instantiating this tokenizer or when you call it on some text, but since the model was not pretrained this way, it might yield a decrease in performance.

Note

When used with is_split_into_words=True, this tokenizer needs to be instantiated with add_prefix_space=True.

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

Parameters

vocab_file (str) – Path to the vocabulary file.
merges_file (str) – Path to the merges file.
errors (str, optional, defaults to "replace") – Paradigm to follow when decoding bytes to UTF-8. See bytes.decode for more information.
unk_token (str, optional, defaults to <|endoftext|>) – The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this token instead.
bos_token (str, optional, defaults to <|endoftext|>) – The beginning of sequence token.
eos_token (str, optional, defaults to <|endoftext|>) – The end of sequence token.
add_prefix_space (bool, optional, defaults to False) – Whether or not to add an initial space to the input. This allows to treat the leading word just as any other word. (CLIP tokenizer detect beginning of words by the preceding space).
trim_offsets (bool, optional, defaults to True) – Whether or not the post-processing step should trim offsets to avoid including whitespaces.

property pad_token_id¶

Id of the padding token in the vocabulary. Returns None if the token has not been set.

Type: Optional[int]

save_vocabulary(save_directory: str, filename_prefix: Optional[str] = None) → Tuple[str][source]¶

Save only the vocabulary of the tokenizer (vocabulary + added tokens).

This method won’t save the configuration and special token mappings of the tokenizer. Use _save_pretrained() to save the whole state of the tokenizer.

Parameters

save_directory (str) – The directory in which to save the vocabulary.
filename_prefix (str, optional) – An optional prefix to add to the named of the saved files.

Returns

Paths to the files saved.

Return type

Tuple(str)

slow_tokenizer_class¶: alias of transformers.models.clip.tokenization_clip.CLIPTokenizer

CLIPFeatureExtractor¶

class transformers.CLIPFeatureExtractor(do_resize=True, size=224, resample=3, do_center_crop=True, crop_size=224, do_normalize=True, image_mean=None, image_std=None, **kwargs)[source]¶

Constructs a CLIP feature extractor.

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

Parameters

do_resize (bool, optional, defaults to True) – Whether to resize the input to a certain size.
size (int, optional, defaults to 224) – Resize the input to the given size. Only has an effect if do_resize is set to True.
resample (int, optional, defaults to PIL.Image.BICUBIC) – An optional resampling filter. This can be one of PIL.Image.NEAREST, PIL.Image.BOX, PIL.Image.BILINEAR, PIL.Image.HAMMING, PIL.Image.BICUBIC or PIL.Image.LANCZOS. Only has an effect if do_resize is set to True.
do_center_crop (bool, optional, defaults to True) – Whether to crop the input at the center. If the input size is smaller than crop_size along any edge, the image is padded with 0’s and then center cropped.
crop_size (int, optional, defaults to 224) – Desired output size when applying center-cropping. Only has an effect if do_center_crop is set to True.
do_normalize (bool, optional, defaults to True) – Whether or not to normalize the input with image_mean and image_std.
image_mean (List[int], defaults to [0.485, 0.456, 0.406]) – The sequence of means for each channel, to be used when normalizing images.
image_std (List[int], defaults to [0.229, 0.224, 0.225]) – The sequence of standard deviations for each channel, to be used when normalizing images.

center_crop(image, size)[source]¶

Crops image to the given size using a center crop. Note that if the image is too small to be cropped to the size is given, it will be padded (so the returned result has the size asked).

Parameters

image (PIL.Image.Image or np.ndarray or torch.Tensor) – The image to resize.
size (int or Tuple[int, int]) – The size to which crop the image.

resize(image, size, resample=3)[source]¶

Resizes image. Note that this will trigger a conversion of image to a PIL Image.

Parameters

image (PIL.Image.Image or np.ndarray or torch.Tensor) – The image to resize.
size (int or Tuple[int, int]) – The size to use for resizing the image. If int it will be resized to match the shorter side
resample (int, optional, defaults to PIL.Image.BILINEAR) – The filter to user for resampling.

CLIPProcessor¶

class transformers.CLIPProcessor(feature_extractor, tokenizer)[source]¶

Constructs a CLIP processor which wraps a CLIP feature extractor and a CLIP tokenizer into a single processor.

CLIPProcessor offers all the functionalities of CLIPFeatureExtractor and CLIPTokenizer. See the __call__() and decode() for more information.

Parameters

feature_extractor (CLIPFeatureExtractor) – The feature extractor is a required input.
tokenizer (CLIPTokenizer) – The tokenizer is a required input.

batch_decode(*args, **kwargs)[source]¶: This method forwards all its arguments to CLIPTokenizer’s batch_decode(). Please refer to the docstring of this method for more information.

decode(*args, **kwargs)[source]¶: This method forwards all its arguments to CLIPTokenizer’s decode(). Please refer to the docstring of this method for more information.

classmethod from_pretrained(pretrained_model_name_or_path, **kwargs)[source]¶

Instantiate a CLIPProcessor from a pretrained CLIP processor.

Note

This class method is simply calling CLIPFeatureExtractor’s from_pretrained() and CLIPTokenizer’s from_pretrained(). Please refer to the docstrings of the methods above for more information.

Parameters

pretrained_model_name_or_path (str or os.PathLike) –
This can be either:
- a string, the model id of a pretrained feature_extractor hosted inside a model repo on huggingface.co. Valid model ids can be located at the root-level, like clip-vit-base-patch32, or namespaced under a user or organization name, like openai/clip-vit-base-patch32.
- a path to a directory containing a feature extractor file saved using the save_pretrained() method, e.g., ./my_model_directory/.
- a path or url to a saved feature extractor JSON file, e.g., ./my_model_directory/preprocessor_config.json.
**kwargs – Additional keyword arguments passed along to both PreTrainedFeatureExtractor and PreTrainedTokenizer

save_pretrained(save_directory)[source]¶

Save a CLIP feature extractor object and CLIP tokenizer object to the directory save_directory, so that it can be re-loaded using the from_pretrained() class method.

Note

This class method is simply calling save_pretrained() and save_pretrained(). Please refer to the docstrings of the methods above for more information.

Parameters: save_directory (str or os.PathLike) – Directory where the feature extractor JSON file and the tokenizer files will be saved (directory will be created if it does not exist).

CLIPModel¶

class transformers.CLIPModel(config: transformers.models.clip.configuration_clip.CLIPConfig)[source]¶

This model is a PyTorch torch.nn.Module subclass. Use it as a regular PyTorch Module and refer to the PyTorch documentation for all matter related to general usage and behavior.

Parameters: config (CLIPConfig) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

forward(input_ids=None, pixel_values=None, attention_mask=None, position_ids=None, return_loss=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶

The CLIPModel forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

Indices can be obtained using CLIPTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

What are input IDs?
attention_mask (torch.Tensor of shape (batch_size, sequence_length), optional) –
Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
- 1 for tokens that are not masked,
- 0 for tokens that are masked.
What are attention masks?
position_ids (torch.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.max_position_embeddings - 1].

What are position IDs?
pixel_values (torch.FloatTensor of shape (batch_size, num_channels, height, width)) – Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using CLIPFeatureExtractor. See transformers.CLIPFeatureExtractor.__call__() for details.
return_loss (bool, optional) – Whether or not to return the contrastive loss.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.

Returns

A 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 (~transformers.) and inputs.

loss (torch.FloatTensor of shape (1,), optional, returned when return_loss is True) – Contrastive loss for image-text similarity.
logits_per_image:(:obj:`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:(:obj:`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(:obj:`torch.FloatTensor` of shape (batch_size, output_dim) – The text embeddings obtained by applying the projection layer to the pooled output of CLIPTextModel.
image_embeds(:obj:`torch.FloatTensor` of shape (batch_size, output_dim) – The image embeddings obtained by applying the projection layer to the pooled output of CLIPVisionModel.
text_model_output(:obj:`BaseModelOutputWithPooling`): The output of the CLIPTextModel.
vision_model_output(:obj:`BaseModelOutputWithPooling`): The output of the CLIPVisionModel.

Examples:

>>> 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

Return type

CLIPOutput or tuple(torch.FloatTensor)

get_image_features(pixel_values=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶

The CLIPModel forward method, overrides the __call__() special method.

Note

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.

Parameters

pixel_values (torch.FloatTensor of shape (batch_size, num_channels, height, width)) – Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using CLIPFeatureExtractor. See transformers.CLIPFeatureExtractor.__call__() for details.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.
Returns – image_features (torch.FloatTensor of shape (batch_size, output_dim): The image embeddings obtained by applying the projection layer to the pooled output of CLIPVisionModel.

Examples:: –

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

>>> image_features = model.get_image_features(**inputs)

get_text_features(input_ids=None, attention_mask=None, position_ids=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶

The CLIPModel forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

Indices can be obtained using CLIPTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

What are input IDs?
attention_mask (torch.Tensor of shape (batch_size, sequence_length), optional) –
Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
- 1 for tokens that are not masked,
- 0 for tokens that are masked.
What are attention masks?
position_ids (torch.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.max_position_embeddings - 1].

What are position IDs?
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.
Returns – text_features (torch.FloatTensor of shape (batch_size, output_dim): The text embeddings obtained by applying the projection layer to the pooled output of CLIPTextModel.

Examples:: –

>>> from transformers import CLIPTokenizer, CLIPModel

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

>>> inputs = tokenizer(["a photo of a cat", "a photo of a dog"],  padding=True, return_tensors="pt")
>>> text_features = model.get_text_features(**inputs)

CLIPTextModel¶

class transformers.CLIPTextModel(config: transformers.models.clip.configuration_clip.CLIPTextConfig)[source]¶

forward(input_ids=None, attention_mask=None, position_ids=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶

The CLIPTextModel forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (torch.LongTensor of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

Indices can be obtained using CLIPTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

What are input IDs?
attention_mask (torch.Tensor of shape (batch_size, sequence_length), optional) –
Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
- 1 for tokens that are not masked,
- 0 for tokens that are masked.
What are attention masks?
position_ids (torch.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.max_position_embeddings - 1].

What are position IDs?
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.

Returns

A 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 (~transformers.) 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 + 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 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:

>>> from transformers import CLIPTokenizer, CLIPTextModel

>>> model = CLIPTextModel.from_pretrained("openai/clip-vit-base-patch32")
>>> tokenizer = CLIPTokenizer.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.pooled_output # pooled (EOS token) states

Return type

BaseModelOutputWithPooling or tuple(torch.FloatTensor)

CLIPVisionModel¶

class transformers.CLIPVisionModel(config: transformers.models.clip.configuration_clip.CLIPVisionConfig)[source]¶

forward(pixel_values=None, output_attentions=None, output_hidden_states=None, return_dict=None)[source]¶

The CLIPVisionModel forward method, overrides the __call__() special method.

Note

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.

Parameters

pixel_values (torch.FloatTensor of shape (batch_size, num_channels, height, width)) – Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using CLIPFeatureExtractor. See transformers.CLIPFeatureExtractor.__call__() for details.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.

Returns

A 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 (~transformers.) 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 + 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 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:

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

>>> model = CLIPVisionModel.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(images=image, return_tensors="pt")

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

Return type

BaseModelOutputWithPooling or tuple(torch.FloatTensor)

FlaxCLIPModel¶

class transformers.FlaxCLIPModel(config: transformers.models.clip.configuration_clip.CLIPConfig, input_shape: Optional[Tuple] = None, seed: int = 0, dtype: numpy.dtype = <class 'jax._src.numpy.lax_numpy.float32'>, **kwargs)[source]¶

This model inherits from FlaxPreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading, saving and converting weights from PyTorch models)

This model is also a Flax Linen flax.linen.Module subclass. Use it as a regular Flax linen Module and refer to the Flax documentation for all matter related to general usage and behavior.

Finally, this model supports inherent JAX features such as:

Parameters: config (CLIPConfig) – Model configuration class with all the parameters of the model. Initializing with a config file does not load the weights associated with the model, only the configuration. Check out the from_pretrained() method to load the model weights.

__call__(input_ids, pixel_values, attention_mask=None, position_ids=None, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None, train: bool = False, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None)¶

The FlaxCLIPPreTrainedModel forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (numpy.ndarray of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

Indices can be obtained using CLIPTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

What are input IDs?
attention_mask (numpy.ndarray of shape (batch_size, sequence_length), optional) –
Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
- 1 for tokens that are not masked,
- 0 for tokens that are masked.
What are attention masks?
position_ids (numpy.ndarray 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.max_position_embeddings - 1].

What are position IDs?
pixel_values (numpy.ndarray of shape (batch_size, num_channels, height, width)) – Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using CLIPFeatureExtractor. See transformers.CLIPFeatureExtractor.__call__() for details.
return_loss (bool, optional) – Whether or not to return the contrastive loss.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.

Returns

A FlaxCLIPOutput 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 (~transformers.) and inputs.

logits_per_image:(:obj:`jnp.ndarray` 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:(:obj:`jnp.ndarray` 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(:obj:`jnp.ndarray` of shape (batch_size, output_dim) – The text embeddings obtained by applying the projection layer to the pooled output of FlaxCLIPTextModel.
image_embeds(:obj:`jnp.ndarray` of shape (batch_size, output_dim) – The image embeddings obtained by applying the projection layer to the pooled output of FlaxCLIPVisionModel.
text_model_output(:obj:`FlaxBaseModelOutputWithPooling`): The output of the FlaxCLIPTextModel.
vision_model_output(:obj:`FlaxBaseModelOutputWithPooling`): The output of the FlaxCLIPVisionModel.

Return type

FlaxCLIPOutput or tuple(torch.FloatTensor)

Example:

>>> import jax
>>> from PIL import Image
>>> import requests
>>> from transformers import CLIPProcessor, FlaxCLIPModel

>>> model = FlaxCLIPModel.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="np", padding=True)

>>> outputs = model(**inputs)
>>> logits_per_image = outputs.logits_per_image # this is the image-text similarity score
>>> probs = jax.nn.softmax(logits_per_image, axis=1) # we can take the softmax to get the label probabilities

get_image_features(pixel_values, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None, train=False)¶

Parameters: pixel_values (numpy.ndarray of shape (batch_size, num_channels, height, width)) – Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using CLIPFeatureExtractor. See transformers.CLIPFeatureExtractor.__call__() for details.
Returns: The image embeddings obtained by applying the projection layer to the pooled output of FlaxCLIPVisionModel
Return type: image_features (jnp.ndarray of shape (batch_size, output_dim)

Examples:

>>> from PIL import Image
>>> import requests
>>> from transformers import CLIPProcessor, FlaxCLIPModel

>>> model = FlaxCLIPModel.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(images=image, return_tensors="np")

>>> image_features = model.get_image_features(**inputs)

get_text_features(input_ids, attention_mask=None, position_ids=None, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None, train=False)¶

Parameters

input_ids (numpy.ndarray of shape (batch_size, sequence_length)) –

Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

Indices can be obtained using CLIPTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

What are input IDs?

Returns

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

Return type

text_features (jnp.ndarray of shape (batch_size, output_dim)

Examples:

>>> from transformers import CLIPTokenizer, FlaxCLIPModel

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

>>> inputs = tokenizer(["a photo of a cat", "a photo of a dog"],  padding=True, return_tensors="np")
>>> text_features = model.get_text_features(**inputs)

FlaxCLIPTextModel¶

class transformers.FlaxCLIPTextModel(config: transformers.models.clip.configuration_clip.CLIPTextConfig, input_shape=(1, 1), seed: int = 0, dtype: numpy.dtype = <class 'jax._src.numpy.lax_numpy.float32'>, **kwargs)[source]¶

__call__(input_ids, attention_mask=None, position_ids=None, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None, train: bool = False, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None)¶

The FlaxCLIPTextPreTrainedModel forward method, overrides the __call__() special method.

Note

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.

Parameters

input_ids (numpy.ndarray of shape (batch_size, sequence_length)) –
Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

Indices can be obtained using CLIPTokenizer. See transformers.PreTrainedTokenizer.encode() and transformers.PreTrainedTokenizer.__call__() for details.

What are input IDs?
attention_mask (numpy.ndarray of shape (batch_size, sequence_length), optional) –
Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
- 1 for tokens that are not masked,
- 0 for tokens that are masked.
What are attention masks?
position_ids (numpy.ndarray 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.max_position_embeddings - 1].

What are position IDs?
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.

Returns

A FlaxBaseModelOutputWithPooling 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 (~transformers.) and inputs.

last_hidden_state (jnp.ndarray of shape (batch_size, sequence_length, hidden_size)) – Sequence of hidden-states at the output of the last layer of the model.
pooler_output (jnp.ndarray of shape (batch_size, hidden_size)) – Last layer hidden-state of the first token of the sequence (classification token) further processed by 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(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (one for the output of the embeddings + 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 initial embedding outputs.
attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (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.

Return type

FlaxBaseModelOutputWithPooling or tuple(torch.FloatTensor)

Example:

>>> from transformers import CLIPTokenizer, FlaxCLIPTextModel

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

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

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

FlaxCLIPVisionModel¶

class transformers.FlaxCLIPVisionModel(config: transformers.models.clip.configuration_clip.CLIPVisionConfig, input_shape: Optional[Tuple] = None, seed: int = 0, dtype: numpy.dtype = <class 'jax._src.numpy.lax_numpy.float32'>, **kwargs)[source]¶

__call__(pixel_values, params: dict = None, dropout_rng: jax._src.random.PRNGKey = None, train: bool = False, output_attentions: Optional[bool] = None, output_hidden_states: Optional[bool] = None, return_dict: Optional[bool] = None)¶

The FlaxCLIPVisionPreTrainedModel forward method, overrides the __call__() special method.

Note

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.

Parameters

pixel_values (numpy.ndarray of shape (batch_size, num_channels, height, width)) – Pixel values. Padding will be ignored by default should you provide it. Pixel values can be obtained using CLIPFeatureExtractor. See transformers.CLIPFeatureExtractor.__call__() for details.
output_attentions (bool, optional) – Whether or not to return the attentions tensors of all attention layers. See attentions under returned tensors for more detail.
output_hidden_states (bool, optional) – Whether or not to return the hidden states of all layers. See hidden_states under returned tensors for more detail.
return_dict (bool, optional) – Whether or not to return a ModelOutput instead of a plain tuple.

Returns

A FlaxBaseModelOutputWithPooling 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 (~transformers.) and inputs.

last_hidden_state (jnp.ndarray of shape (batch_size, sequence_length, hidden_size)) – Sequence of hidden-states at the output of the last layer of the model.
pooler_output (jnp.ndarray of shape (batch_size, hidden_size)) – Last layer hidden-state of the first token of the sequence (classification token) further processed by 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(jnp.ndarray), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) – Tuple of jnp.ndarray (one for the output of the embeddings + 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 initial embedding outputs.
attentions (tuple(jnp.ndarray), optional, returned when output_attentions=True is passed or when config.output_attentions=True) – Tuple of jnp.ndarray (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.

Return type

FlaxBaseModelOutputWithPooling or tuple(torch.FloatTensor)

Example:

>>> from PIL import Image
>>> import requests
>>> from transformers import CLIPProcessor, FlaxCLIPVisionModel

>>> model = FlaxCLIPVisionModel.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(images=image, return_tensors="np")

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