# CLIPSeg

## CLIPSeg

### Overview

The CLIPSeg model was proposed in [Image Segmentation Using Text and Image Prompts](https://arxiv.org/abs/2112.10003) by Timo Lüddecke and Alexander Ecker. CLIPSeg adds a minimal decoder on top of a frozen [CLIP](https://huggingface.co/docs/transformers/model_doc/clip) model for zero- and one-shot image segmentation.

The abstract from the paper is the following:

*Image segmentation is usually addressed by training a model for a fixed set of object classes. Incorporating additional classes or more complex queries later is expensive as it requires re-training the model on a dataset that encompasses these expressions. Here we propose a system that can generate image segmentations based on arbitrary prompts at test time. A prompt can be either a text or an image. This approach enables us to create a unified model (trained once) for three common segmentation tasks, which come with distinct challenges: referring expression segmentation, zero-shot segmentation and one-shot segmentation. We build upon the CLIP model as a backbone which we extend with a transformer-based decoder that enables dense prediction. After training on an extended version of the PhraseCut dataset, our system generates a binary segmentation map for an image based on a free-text prompt or on an additional image expressing the query. We analyze different variants of the latter image-based prompts in detail. This novel hybrid input allows for dynamic adaptation not only to the three segmentation tasks mentioned above, but to any binary segmentation task where a text or image query can be formulated. Finally, we find our system to adapt well to generalized queries involving affordances or properties*

Tips:

* [CLIPSegForImageSegmentation](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegForImageSegmentation) adds a decoder on top of [CLIPSegModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegModel). The latter is identical to [CLIPModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clip#transformers.CLIPModel).
* [CLIPSegForImageSegmentation](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegForImageSegmentation) can generate image segmentations based on arbitrary prompts at test time. A prompt can be either a text (provided to the model as `input_ids`) or an image (provided to the model as `conditional_pixel_values`). One can also provide custom conditional embeddings (provided to the model as `conditional_embeddings`).

<figure><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/clipseg_architecture.png" alt=""><figcaption></figcaption></figure>

CLIPSeg overview. Taken from the [original paper.](https://arxiv.org/abs/2112.10003)

This model was contributed by [nielsr](https://huggingface.co/nielsr). The original code can be found [here](https://github.com/timojl/clipseg).

### Resources

A list of official BOINC AI and community (indicated by 🌎) resources to help you get started with CLIPSeg. If you’re interested in submitting a resource to be included here, please feel free to open a Pull Request and we’ll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.

Image Segmentation

* A notebook that illustrates [zero-shot image segmentation with CLIPSeg](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/CLIPSeg/Zero_shot_image_segmentation_with_CLIPSeg.ipynb).

### CLIPSegConfig

#### class transformers.CLIPSegConfig

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/configuration_clipseg.py#L239)

( text\_config = Nonevision\_config = Noneprojection\_dim = 512logit\_scale\_init\_value = 2.6592extract\_layers = \[3, 6, 9]reduce\_dim = 64decoder\_num\_attention\_heads = 4decoder\_attention\_dropout = 0.0decoder\_hidden\_act = 'quick\_gelu'decoder\_intermediate\_size = 2048conditional\_layer = 0use\_complex\_transposed\_convolution = False\*\*kwargs )

Parameters

* **text\_config** (`dict`, *optional*) — Dictionary of configuration options used to initialize [CLIPSegTextConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegTextConfig).
* **vision\_config** (`dict`, *optional*) — Dictionary of configuration options used to initialize [CLIPSegVisionConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegVisionConfig).
* **projection\_dim** (`int`, *optional*, defaults to 512) — Dimensionality of text and vision projection layers.
* **logit\_scale\_init\_value** (`float`, *optional*, defaults to 2.6592) — The inital value of the *logit\_scale* paramter. Default is used as per the original CLIPSeg implementation.
* **extract\_layers** (`List[int]`, *optional*, defaults to \[3, 6, 9]) — Layers to extract when forwarding the query image through the frozen visual backbone of CLIP.
* **reduce\_dim** (`int`, *optional*, defaults to 64) — Dimensionality to reduce the CLIP vision embedding.
* **decoder\_num\_attention\_heads** (`int`, *optional*, defaults to 4) — Number of attention heads in the decoder of CLIPSeg.
* **decoder\_attention\_dropout** (`float`, *optional*, defaults to 0.0) — The dropout ratio for the attention probabilities.
* **decoder\_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.
* **decoder\_intermediate\_size** (`int`, *optional*, defaults to 2048) — Dimensionality of the “intermediate” (i.e., feed-forward) layers in the Transformer decoder.
* **conditional\_layer** (`int`, *optional*, defaults to 0) — The layer to use of the Transformer encoder whose activations will be combined with the condition embeddings using FiLM (Feature-wise Linear Modulation). If 0, the last layer is used.
* **use\_complex\_transposed\_convolution** (`bool`, *optional*, defaults to `False`) — Whether to use a more complex transposed convolution in the decoder, enabling more fine-grained segmentation.
* **kwargs** (*optional*) — Dictionary of keyword arguments.

[CLIPSegConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegConfig) is the configuration class to store the configuration of a [CLIPSegModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegModel). It is used to instantiate a CLIPSeg model according to the specified arguments, defining the text model and vision model configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the CLIPSeg [CIDAS/clipseg-rd64](https://huggingface.co/CIDAS/clipseg-rd64) architecture.

Configuration objects inherit from [PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig) and can be used to control the model outputs. Read the documentation from [PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig) for more information.

Example:

Copied

```
>>> from transformers import CLIPSegConfig, CLIPSegModel

>>> # Initializing a CLIPSegConfig with CIDAS/clipseg-rd64 style configuration
>>> configuration = CLIPSegConfig()

>>> # Initializing a CLIPSegModel (with random weights) from the CIDAS/clipseg-rd64 style configuration
>>> model = CLIPSegModel(configuration)

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

>>> # We can also initialize a CLIPSegConfig from a CLIPSegTextConfig and a CLIPSegVisionConfig

>>> # Initializing a CLIPSegText and CLIPSegVision configuration
>>> config_text = CLIPSegTextConfig()
>>> config_vision = CLIPSegVisionConfig()

>>> config = CLIPSegConfig.from_text_vision_configs(config_text, config_vision)
```

**from\_text\_vision\_configs**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/configuration_clipseg.py#L414)

( text\_config: CLIPSegTextConfigvision\_config: CLIPSegVisionConfig\*\*kwargs ) → [CLIPSegConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegConfig)

Returns

[CLIPSegConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegConfig)

An instance of a configuration object

Instantiate a [CLIPSegConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegConfig) (or a derived class) from clipseg text model configuration and clipseg vision model configuration.

### CLIPSegTextConfig

#### class transformers.CLIPSegTextConfig

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/configuration_clipseg.py#L31)

( vocab\_size = 49408hidden\_size = 512intermediate\_size = 2048num\_hidden\_layers = 12num\_attention\_heads = 8max\_position\_embeddings = 77hidden\_act = 'quick\_gelu'layer\_norm\_eps = 1e-05attention\_dropout = 0.0initializer\_range = 0.02initializer\_factor = 1.0pad\_token\_id = 1bos\_token\_id = 49406eos\_token\_id = 49407\*\*kwargs )

Parameters

* **vocab\_size** (`int`, *optional*, defaults to 49408) — Vocabulary size of the CLIPSeg text model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [CLIPSegModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegModel).
* **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.
* **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).

This is the configuration class to store the configuration of a [CLIPSegModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegModel). It is used to instantiate an CLIPSeg 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 CLIPSeg [CIDAS/clipseg-rd64](https://huggingface.co/CIDAS/clipseg-rd64) architecture.

Configuration objects inherit from [PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig) and can be used to control the model outputs. Read the documentation from [PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig) for more information.

Example:

Copied

```
>>> from transformers import CLIPSegTextConfig, CLIPSegTextModel

>>> # Initializing a CLIPSegTextConfig with CIDAS/clipseg-rd64 style configuration
>>> configuration = CLIPSegTextConfig()

>>> # Initializing a CLIPSegTextModel (with random weights) from the CIDAS/clipseg-rd64 style configuration
>>> model = CLIPSegTextModel(configuration)

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

### CLIPSegVisionConfig

#### class transformers.CLIPSegVisionConfig

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/configuration_clipseg.py#L136)

( hidden\_size = 768intermediate\_size = 3072num\_hidden\_layers = 12num\_attention\_heads = 12num\_channels = 3image\_size = 224patch\_size = 32hidden\_act = 'quick\_gelu'layer\_norm\_eps = 1e-05attention\_dropout = 0.0initializer\_range = 0.02initializer\_factor = 1.0\*\*kwargs )

Parameters

* **hidden\_size** (`int`, *optional*, defaults to 768) — Dimensionality of the encoder layers and the pooler layer.
* **intermediate\_size** (`int`, *optional*, defaults to 3072) — Dimensionality of the “intermediate” (i.e., feed-forward) layer in the Transformer encoder.
* **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.
* **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).

This is the configuration class to store the configuration of a [CLIPSegModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegModel). It is used to instantiate an CLIPSeg 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 CLIPSeg [CIDAS/clipseg-rd64](https://huggingface.co/CIDAS/clipseg-rd64) architecture.

Configuration objects inherit from [PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig) and can be used to control the model outputs. Read the documentation from [PretrainedConfig](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/configuration#transformers.PretrainedConfig) for more information.

Example:

Copied

```
>>> from transformers import CLIPSegVisionConfig, CLIPSegVisionModel

>>> # Initializing a CLIPSegVisionConfig with CIDAS/clipseg-rd64 style configuration
>>> configuration = CLIPSegVisionConfig()

>>> # Initializing a CLIPSegVisionModel (with random weights) from the CIDAS/clipseg-rd64 style configuration
>>> model = CLIPSegVisionModel(configuration)

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

### CLIPSegProcessor

#### class transformers.CLIPSegProcessor

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/processing_clipseg.py#L25)

( image\_processor = Nonetokenizer = None\*\*kwargs )

Parameters

* **image\_processor** ([ViTImageProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vit#transformers.ViTImageProcessor)) — The image processor is a required input.
* **tokenizer** ([CLIPTokenizerFast](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clip#transformers.CLIPTokenizerFast)) — The tokenizer is a required input.

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

[CLIPSegProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegProcessor) offers all the functionalities of [ViTImageProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vit#transformers.ViTImageProcessor) and [CLIPTokenizerFast](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clip#transformers.CLIPTokenizerFast). See the `__call__()` and [decode()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegProcessor.decode) for more information.

**batch\_decode**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/processing_clipseg.py#L133)

( \*args\*\*kwargs )

This method forwards all its arguments to CLIPTokenizerFast’s [batch\_decode()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/speecht5#transformers.SpeechT5Tokenizer.batch_decode). Please refer to the docstring of this method for more information.

**decode**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/processing_clipseg.py#L140)

( \*args\*\*kwargs )

This method forwards all its arguments to CLIPTokenizerFast’s [decode()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/speecht5#transformers.SpeechT5Tokenizer.decode). Please refer to the docstring of this method for more information.

### CLIPSegModel

#### class transformers.CLIPSegModel

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/modeling_clipseg.py#L968)

( config: CLIPSegConfig )

Parameters

* **config** ([CLIPSegConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegConfig)) — 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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

This model is 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.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/modeling_clipseg.py#L1099)

( input\_ids: typing.Optional\[torch.LongTensor] = Nonepixel\_values: typing.Optional\[torch.FloatTensor] = Noneattention\_mask: typing.Optional\[torch.Tensor] = Noneposition\_ids: typing.Optional\[torch.LongTensor] = Nonereturn\_loss: typing.Optional\[bool] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → `transformers.models.clipseg.modeling_clipseg.CLIPSegOutput` or `tuple(torch.FloatTensor)`

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 [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **position\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.

  [What are position IDs?](https://huggingface.co/docs/transformers/glossary#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 [AutoImageProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoImageProcessor). See [CLIPImageProcessor.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/deit#transformers.DeiTFeatureExtractor.__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](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

`transformers.models.clipseg.modeling_clipseg.CLIPSegOutput` or `tuple(torch.FloatTensor)`

A `transformers.models.clipseg.modeling_clipseg.CLIPSegOutput` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration (`<class 'transformers.models.clipseg.configuration_clipseg.CLIPSegConfig'>`) and inputs.

* **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `return_loss` is `True`) — Contrastive loss for image-text similarity.
* **logits\_per\_image:(`torch.FloatTensor`** of shape `(image_batch_size, text_batch_size)`) — The scaled dot product scores between `image_embeds` and `text_embeds`. This represents the image-text similarity scores.
* **logits\_per\_text:(`torch.FloatTensor`** of shape `(text_batch_size, image_batch_size)`) — The scaled dot product scores between `text_embeds` and `image_embeds`. This represents the text-image similarity scores.
* **text\_embeds(`torch.FloatTensor`** of shape `(batch_size, output_dim`) — The text embeddings obtained by applying the projection layer to the pooled output of [CLIPSegTextModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegTextModel).
* **image\_embeds(`torch.FloatTensor`** of shape `(batch_size, output_dim`) — The image embeddings obtained by applying the projection layer to the pooled output of [CLIPSegVisionModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegVisionModel).
* **text\_model\_output(`BaseModelOutputWithPooling`):** The output of the [CLIPSegTextModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegTextModel).
* **vision\_model\_output(`BaseModelOutputWithPooling`):** The output of the [CLIPSegVisionModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegVisionModel).

The [CLIPSegModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegModel) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Examples:

Copied

```
>>> from PIL import Image
>>> import requests
>>> from transformers import AutoProcessor, CLIPSegModel

>>> processor = AutoProcessor.from_pretrained("CIDAS/clipseg-rd64-refined")
>>> model = CLIPSegModel.from_pretrained("CIDAS/clipseg-rd64-refined")

>>> 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
```

**get\_text\_features**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/modeling_clipseg.py#L1003)

( input\_ids: typing.Optional\[torch.Tensor] = Noneattention\_mask: typing.Optional\[torch.Tensor] = Noneposition\_ids: typing.Optional\[torch.Tensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → text\_features (`torch.FloatTensor` of shape `(batch_size, output_dim`)

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 [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **position\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.

  [What are position IDs?](https://huggingface.co/docs/transformers/glossary#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](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.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 [CLIPSegTextModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegTextModel).

The [CLIPSegModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegModel) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Examples:

Copied

```
>>> from transformers import AutoTokenizer, CLIPSegModel

>>> tokenizer = AutoTokenizer.from_pretrained("CIDAS/clipseg-rd64-refined")
>>> model = CLIPSegModel.from_pretrained("CIDAS/clipseg-rd64-refined")

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

**get\_image\_features**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/modeling_clipseg.py#L1050)

( pixel\_values: typing.Optional\[torch.FloatTensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → image\_features (`torch.FloatTensor` of shape `(batch_size, output_dim`)

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 [AutoImageProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoImageProcessor). See [CLIPImageProcessor.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/deit#transformers.DeiTFeatureExtractor.__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](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.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 [CLIPSegVisionModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegVisionModel).

The [CLIPSegModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegModel) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Examples:

Copied

```
>>> from PIL import Image
>>> import requests
>>> from transformers import AutoProcessor, CLIPSegModel

>>> processor = AutoProcessor.from_pretrained("CIDAS/clipseg-rd64-refined")
>>> model = CLIPSegModel.from_pretrained("CIDAS/clipseg-rd64-refined")

>>> 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)
```

### CLIPSegTextModel

#### class transformers.CLIPSegTextModel

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/modeling_clipseg.py#L800)

( config: CLIPSegTextConfig )

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/modeling_clipseg.py#L817)

( input\_ids: typing.Optional\[torch.Tensor] = Noneattention\_mask: typing.Optional\[torch.Tensor] = Noneposition\_ids: typing.Optional\[torch.Tensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.BaseModelOutputWithPooling](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`

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 [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **position\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.

  [What are position IDs?](https://huggingface.co/docs/transformers/glossary#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](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_outputs.BaseModelOutputWithPooling](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.BaseModelOutputWithPooling](https://huggingface.co/docs/transformers/v4.34.1/en/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 (`<class 'transformers.models.clipseg.configuration_clipseg.CLIPSegTextConfig'>`) and inputs.

* **last\_hidden\_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) — Sequence of hidden-states at the output of the last layer of the model.
* **pooler\_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) — Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining.
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [CLIPSegTextModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegTextModel) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Examples:

Copied

```
>>> from transformers import AutoTokenizer, CLIPSegTextModel

>>> tokenizer = AutoTokenizer.from_pretrained("CIDAS/clipseg-rd64-refined")
>>> model = CLIPSegTextModel.from_pretrained("CIDAS/clipseg-rd64-refined")

>>> 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
```

### CLIPSegVisionModel

#### class transformers.CLIPSegVisionModel

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/modeling_clipseg.py#L915)

( config: CLIPSegVisionConfig )

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/modeling_clipseg.py#L928)

( pixel\_values: typing.Optional\[torch.FloatTensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → [transformers.modeling\_outputs.BaseModelOutputWithPooling](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`

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 [AutoImageProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoImageProcessor). See [CLIPImageProcessor.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/deit#transformers.DeiTFeatureExtractor.__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](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.

Returns

[transformers.modeling\_outputs.BaseModelOutputWithPooling](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.modeling_outputs.BaseModelOutputWithPooling) or `tuple(torch.FloatTensor)`

A [transformers.modeling\_outputs.BaseModelOutputWithPooling](https://huggingface.co/docs/transformers/v4.34.1/en/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 (`<class 'transformers.models.clipseg.configuration_clipseg.CLIPSegVisionConfig'>`) and inputs.

* **last\_hidden\_state** (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`) — Sequence of hidden-states at the output of the last layer of the model.
* **pooler\_output** (`torch.FloatTensor` of shape `(batch_size, hidden_size)`) — Last layer hidden-state of the first token of the sequence (classification token) after further processing through the layers used for the auxiliary pretraining task. E.g. for BERT-family of models, this returns the classification token after processing through a linear layer and a tanh activation function. The linear layer weights are trained from the next sentence prediction (classification) objective during pretraining.
* **hidden\_states** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`) — Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, + one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.

  Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
* **attentions** (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`) — Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length, sequence_length)`.

  Attentions weights after the attention softmax, used to compute the weighted average in the self-attention heads.

The [CLIPSegVisionModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegVisionModel) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Examples:

Copied

```
>>> from PIL import Image
>>> import requests
>>> from transformers import AutoProcessor, CLIPSegVisionModel

>>> processor = AutoProcessor.from_pretrained("CIDAS/clipseg-rd64-refined")
>>> model = CLIPSegVisionModel.from_pretrained("CIDAS/clipseg-rd64-refined")

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

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

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

### CLIPSegForImageSegmentation

#### class transformers.CLIPSegForImageSegmentation

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/modeling_clipseg.py#L1356)

( config: CLIPSegConfig )

Parameters

* **config** ([CLIPSegConfig](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegConfig)) — 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()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/model#transformers.PreTrainedModel.from_pretrained) method to load the model weights.

CLIPSeg model with a Transformer-based decoder on top for zero-shot and one-shot image segmentation.

This model is 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.

**forward**

[\<source>](https://github.com/huggingface/transformers/blob/v4.34.1/src/transformers/models/clipseg/modeling_clipseg.py#L1401)

( input\_ids: typing.Optional\[torch.FloatTensor] = Nonepixel\_values: typing.Optional\[torch.FloatTensor] = Noneconditional\_pixel\_values: typing.Optional\[torch.FloatTensor] = Noneconditional\_embeddings: typing.Optional\[torch.FloatTensor] = Noneattention\_mask: typing.Optional\[torch.Tensor] = Noneposition\_ids: typing.Optional\[torch.LongTensor] = Nonelabels: typing.Optional\[torch.LongTensor] = Noneoutput\_attentions: typing.Optional\[bool] = Noneoutput\_hidden\_states: typing.Optional\[bool] = Nonereturn\_dict: typing.Optional\[bool] = None ) → `transformers.models.clipseg.modeling_clipseg.CLIPSegImageSegmentationOutput` or `tuple(torch.FloatTensor)`

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 [AutoTokenizer](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoTokenizer). See [PreTrainedTokenizer.encode()](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/tokenizer#transformers.PreTrainedTokenizerFast.encode) and [PreTrainedTokenizer.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/vits#transformers.VitsTokenizer.__call__) for details.

  [What are input IDs?](https://huggingface.co/docs/transformers/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?](https://huggingface.co/docs/transformers/glossary#attention-mask)
* **position\_ids** (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*) — Indices of positions of each input sequence tokens in the position embeddings. Selected in the range `[0, config.max_position_embeddings - 1]`.

  [What are position IDs?](https://huggingface.co/docs/transformers/glossary#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 [AutoImageProcessor](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/auto#transformers.AutoImageProcessor). See [CLIPImageProcessor.**call**()](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/deit#transformers.DeiTFeatureExtractor.__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](https://huggingface.co/docs/transformers/v4.34.1/en/main_classes/output#transformers.utils.ModelOutput) instead of a plain tuple.
* **labels** (`torch.LongTensor` of shape `(batch_size,)`, *optional*) — Labels for computing the sequence classification/regression loss. Indices should be in `[0, ..., config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If `config.num_labels > 1` a classification loss is computed (Cross-Entropy).

Returns

`transformers.models.clipseg.modeling_clipseg.CLIPSegImageSegmentationOutput` or `tuple(torch.FloatTensor)`

A `transformers.models.clipseg.modeling_clipseg.CLIPSegImageSegmentationOutput` or a tuple of `torch.FloatTensor` (if `return_dict=False` is passed or when `config.return_dict=False`) comprising various elements depending on the configuration (`<class 'transformers.models.clipseg.configuration_clipseg.CLIPSegTextConfig'>`) and inputs.

* **loss** (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `return_loss` is `True`) — Contrastive loss for image-text similarity. …
* **vision\_model\_output** (`BaseModelOutputWithPooling`) — The output of the [CLIPSegVisionModel](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegVisionModel).

The [CLIPSegForImageSegmentation](https://huggingface.co/docs/transformers/v4.34.1/en/model_doc/clipseg#transformers.CLIPSegForImageSegmentation) forward method, overrides the `__call__` special method.

Although the recipe for forward pass needs to be defined within this function, one should call the `Module` instance afterwards instead of this since the former takes care of running the pre and post processing steps while the latter silently ignores them.

Examples:

Copied

```
>>> from transformers import AutoProcessor, CLIPSegForImageSegmentation
>>> from PIL import Image
>>> import requests

>>> processor = AutoProcessor.from_pretrained("CIDAS/clipseg-rd64-refined")
>>> model = CLIPSegForImageSegmentation.from_pretrained("CIDAS/clipseg-rd64-refined")

>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> texts = ["a cat", "a remote", "a blanket"]
>>> inputs = processor(text=texts, images=[image] * len(texts), padding=True, return_tensors="pt")

>>> outputs = model(**inputs)

>>> logits = outputs.logits
>>> print(logits.shape)
torch.Size([3, 352, 352])
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://boinc-ai.gitbook.io/transformers/api/models/multimodal-models/clipseg.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.