Transformers documentation

OWL-ViT

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

OWL-ViT

Overview

The OWL-ViT (short for Vision Transformer for Open-World Localization) was proposed in Simple Open-Vocabulary Object Detection with Vision Transformers by Matthias Minderer, Alexey Gritsenko, Austin Stone, Maxim Neumann, Dirk Weissenborn, Alexey Dosovitskiy, Aravindh Mahendran, Anurag Arnab, Mostafa Dehghani, Zhuoran Shen, Xiao Wang, Xiaohua Zhai, Thomas Kipf, and Neil Houlsby. OWL-ViT is an open-vocabulary object detection network trained on a variety of (image, text) pairs. It can be used to query an image with one or multiple text queries to search for and detect target objects described in text.

The abstract from the paper is the following:

Combining simple architectures with large-scale pre-training has led to massive improvements in image classification. For object detection, pre-training and scaling approaches are less well established, especially in the long-tailed and open-vocabulary setting, where training data is relatively scarce. In this paper, we propose a strong recipe for transferring image-text models to open-vocabulary object detection. We use a standard Vision Transformer architecture with minimal modifications, contrastive image-text pre-training, and end-to-end detection fine-tuning. Our analysis of the scaling properties of this setup shows that increasing image-level pre-training and model size yield consistent improvements on the downstream detection task. We provide the adaptation strategies and regularizations needed to attain very strong performance on zero-shot text-conditioned and one-shot image-conditioned object detection. Code and models are available on GitHub.

Usage

OWL-ViT is a zero-shot text-conditioned object detection model. OWL-ViT uses CLIP as its multi-modal backbone, with a ViT-like Transformer to get visual features and a causal language model to get the text features. To use CLIP for detection, OWL-ViT removes the final token pooling layer of the vision model and attaches a lightweight classification and box head to each transformer output token. Open-vocabulary classification is enabled by replacing the fixed classification layer weights with the class-name embeddings obtained from the text model. The authors first train CLIP from scratch and fine-tune it end-to-end with the classification and box heads on standard detection datasets using a bipartite matching loss. One or multiple text queries per image can be used to perform zero-shot text-conditioned object detection.

OwlViTFeatureExtractor can be used to resize (or rescale) and normalize images for the model and CLIPTokenizer is used to encode the text. OwlViTProcessor wraps OwlViTFeatureExtractor and CLIPTokenizer into a single instance to both encode the text and prepare the images. The following example shows how to perform object detection using OwlViTProcessor and OwlViTForObjectDetection.

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

>>> from transformers import OwlViTProcessor, OwlViTForObjectDetection

>>> processor = OwlViTProcessor.from_pretrained("google/owlvit-base-patch32")
>>> model = OwlViTForObjectDetection.from_pretrained("google/owlvit-base-patch32")

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

>>> # Target image sizes (height, width) to rescale box predictions [batch_size, 2]
>>> target_sizes = torch.Tensor([image.size[::-1]])
>>> # Convert outputs (bounding boxes and class logits) to COCO API
>>> results = processor.post_process(outputs=outputs, target_sizes=target_sizes)

>>> i = 0  # Retrieve predictions for the first image for the corresponding text queries
>>> text = texts[i]
>>> boxes, scores, labels = results[i]["boxes"], results[i]["scores"], results[i]["labels"]

>>> score_threshold = 0.1
>>> for box, score, label in zip(boxes, scores, labels):
...     box = [round(i, 2) for i in box.tolist()]
...     if score >= score_threshold:
...         print(f"Detected {text[label]} with confidence {round(score.item(), 3)} at location {box}")
Detected a photo of a cat with confidence 0.243 at location [1.42, 50.69, 308.58, 370.48]
Detected a photo of a cat with confidence 0.298 at location [348.06, 20.56, 642.33, 372.61]

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

OwlViTConfig

class transformers.OwlViTConfig

< >

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

Parameters

  • text_config_dict (dict, optional) — Dictionary of configuration options used to initialize OwlViTTextConfig.
  • vision_config_dict (dict, optional) — Dictionary of configuration options used to initialize OwlViTVisionConfig.
  • 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 parameter. Default is used as per the original OWL-ViT implementation.
  • kwargs (optional) — Dictionary of keyword arguments.

OwlViTConfig is the configuration class to store the configuration of an OwlViTModel. It is used to instantiate an OWL-ViT 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.

from_text_vision_configs

< >

( text_config: typing.Dict vision_config: typing.Dict **kwargs ) → OwlViTConfig

Returns

OwlViTConfig

An instance of a configuration object

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

OwlViTTextConfig

class transformers.OwlViTTextConfig

< >

( vocab_size = 49408 hidden_size = 512 intermediate_size = 2048 num_hidden_layers = 12 num_attention_heads = 8 max_position_embeddings = 16 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 = 0 bos_token_id = 49406 eos_token_id = 49407 **kwargs )

Parameters

  • vocab_size (int, optional, defaults to 49408) — Vocabulary size of the OWL-ViT text model. Defines the number of different tokens that can be represented by the inputs_ids passed when calling OwlViTTextModel.
  • 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 16) — 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).

This is the configuration class to store the configuration of an OwlViTTextModel. It is used to instantiate an OwlViT text encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the OwlViT google/owlvit-base-patch32 architecture.

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

Example:

>>> from transformers import OwlViTTextConfig, OwlViTTextModel

>>> # Initializing a OwlViTTextModel with google/owlvit-base-patch32 style configuration
>>> configuration = OwlViTTextConfig()

>>> # Initializing a OwlViTTextConfig from the google/owlvit-base-patch32 style configuration
>>> model = OwlViTTextModel(configuration)

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

OwlViTVisionConfig

class transformers.OwlViTVisionConfig

< >

( hidden_size = 768 intermediate_size = 3072 num_hidden_layers = 12 num_attention_heads = 12 image_size = 768 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 )

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 768) — 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).

This is the configuration class to store the configuration of an OwlViTVisionModel. It is used to instantiate an OWL-ViT image encoder according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the OWL-ViT google/owlvit-base-patch32 architecture.

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

Example:

>>> from transformers import OwlViTVisionConfig, OwlViTVisionModel

>>> # Initializing a OwlViTVisionModel with google/owlvit-base-patch32 style configuration
>>> configuration = OwlViTVisionConfig()

>>> # Initializing a OwlViTVisionModel model from the google/owlvit-base-patch32 style configuration
>>> model = OwlViTVisionModel(configuration)

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

OwlViTFeatureExtractor

class transformers.OwlViTFeatureExtractor

< >

( do_resize = True size = 768 resample = <Resampling.BICUBIC: 3> crop_size = 768 do_center_crop = True do_normalize = True image_mean = None image_std = None **kwargs )

Parameters

  • do_resize (bool, optional, defaults to True) — Whether to resize the shorter edge of the input to a certain size.
  • size (int, optional, defaults to 768) — Resize the shorter edge of 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 768) —
  • do_normalize (bool, optional, defaults to True) — Whether or not to normalize the input with image_mean and image_std. Desired output size when applying center-cropping. Only has an effect if do_center_crop is set to True.
  • image_mean (List[int], optional, defaults to [0.48145466, 0.4578275, 0.40821073]) — The sequence of means for each channel, to be used when normalizing images.
  • image_std (List[int], optional, defaults to [0.26862954, 0.26130258, 0.27577711]) — The sequence of standard deviations for each channel, to be used when normalizing images.

Constructs an OWL-ViT 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.

__call__

< >

( images: typing.Union[PIL.Image.Image, numpy.ndarray, ForwardRef('torch.Tensor'), typing.List[PIL.Image.Image], typing.List[numpy.ndarray], typing.List[ForwardRef('torch.Tensor')]] return_tensors: typing.Union[str, transformers.utils.generic.TensorType, NoneType] = None **kwargs ) → BatchFeature

Parameters

  • images (PIL.Image.Image, np.ndarray, torch.Tensor, List[PIL.Image.Image], List[np.ndarray], List[torch.Tensor]) — The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W) or (H, W, C), where C is a number of channels, H and W are image height and width.
  • return_tensors (str or TensorType, optional, defaults to 'np') — If set, will return tensors of a particular framework. Acceptable values are:

    • 'tf': Return TensorFlow tf.constant objects.
    • 'pt': Return PyTorch torch.Tensor objects.
    • 'np': Return NumPy np.ndarray objects.
    • 'jax': Return JAX jnp.ndarray objects.

Returns

BatchFeature

A BatchFeature with the following fields:

  • pixel_values — Pixel values to be fed to a model.

Main method to prepare for the model one or several image(s).

NumPy arrays and PyTorch tensors are converted to PIL images when resizing, so the most efficient is to pass PIL images.

OwlViTProcessor

class transformers.OwlViTProcessor

< >

( feature_extractor tokenizer )

Parameters

  • feature_extractor (OwlViTFeatureExtractor) — The feature extractor is a required input.
  • tokenizer ([CLIPTokenizer, CLIPTokenizerFast]) — The tokenizer is a required input.

Constructs an OWL-ViT processor which wraps OwlViTFeatureExtractor and CLIPTokenizer/CLIPTokenizerFast into a single processor that interits both the feature extractor and tokenizer functionalities. See the __call__() and decode() for more information.

batch_decode

< >

( *args **kwargs )

This method forwards all its arguments to CLIPTokenizerFast’s batch_decode(). Please refer to the docstring of this method for more information.

decode

< >

( *args **kwargs )

This method forwards all its arguments to CLIPTokenizerFast’s decode(). Please refer to the docstring of this method for more information.

post_process

< >

( *args **kwargs )

This method forwards all its arguments to OwlViTFeatureExtractor.post_process(). Please refer to the docstring of this method for more information.

OwlViTModel

class transformers.OwlViTModel

< >

( config: OwlViTConfig )

Parameters

  • 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. — config (OwlViTConfig): 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: typing.Optional[torch.LongTensor] = None pixel_values: typing.Optional[torch.FloatTensor] = None attention_mask: typing.Optional[torch.Tensor] = None return_loss: typing.Optional[bool] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.models.owlvit.modeling_owlvit.OwlViTOutput or tuple(torch.FloatTensor)

Parameters

  • input_ids (torch.LongTensor of shape (batch_size, sequence_length)) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using CLIPTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details. What are input IDs?
  • attention_mask (torch.Tensor of shape (batch_size, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • pixel_values (torch.FloatTensor of shape (batch_size, num_channels, height, width)) — Pixel values.
  • 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

transformers.models.owlvit.modeling_owlvit.OwlViTOutput or tuple(torch.FloatTensor)

A transformers.models.owlvit.modeling_owlvit.OwlViTOutput 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.owlvit.configuration_owlvit.OwlViTConfig'>) 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 * num_max_text_queries, output_dim) — The text embeddings obtained by applying the projection layer to the pooled output of OwlViTTextModel.
  • image_embeds (torch.FloatTensor of shape (batch_size, output_dim) — The image embeddings obtained by applying the projection layer to the pooled output of OwlViTVisionModel.
  • text_model_output (TupleBaseModelOutputWithPooling) — The output of the OwlViTTextModel.
  • vision_model_output (BaseModelOutputWithPooling) — The output of the OwlViTVisionModel.

The OwlViTModel forward method, overrides the __call__ special method.

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

Examples:

>>> from PIL import Image
>>> import requests
>>> from transformers import OwlViTProcessor, OwlViTModel

>>> model = OwlViTModel.from_pretrained("google/owlvit-base-patch32")
>>> processor = OwlViTProcessor.from_pretrained("google/owlvit-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")
>>> outputs = model(**inputs)
>>> logits_per_image = outputs.logits_per_image  # this is the image-text similarity score
>>> probs = logits_per_image.softmax(dim=1)  # we can take the softmax to get the label probabilities

get_text_features

< >

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

Parameters

  • input_ids (torch.LongTensor of shape (batch_size * num_max_text_queries, sequence_length)) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using CLIPTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details. What are input IDs?
  • attention_mask (torch.Tensor of shape (batch_size, num_max_text_queries, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 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 OwlViTTextModel.

The OwlViTModel forward method, overrides the __call__ special method.

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

Examples:

>>> from transformers import OwlViTProcessor, OwlViTModel

>>> model = OwlViTModel.from_pretrained("google/owlvit-base-patch32")
>>> processor = OwlViTProcessor.from_pretrained("google/owlvit-base-patch32")
>>> inputs = processor(
...     text=[["a photo of a cat", "a photo of a dog"], ["photo of a astranaut"]], return_tensors="pt"
... )
>>> text_features = model.get_text_features(**inputs)

get_image_features

< >

( pixel_values: typing.Optional[torch.FloatTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None return_projected: typing.Optional[bool] = True ) → 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.
  • 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 OwlViTVisionModel.

The OwlViTModel forward method, overrides the __call__ special method.

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

Examples:

>>> from PIL import Image
>>> import requests
>>> from transformers import OwlViTProcessor, OwlViTModel

>>> model = OwlViTModel.from_pretrained("google/owlvit-base-patch32")
>>> processor = OwlViTProcessor.from_pretrained("google/owlvit-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)

OwlViTTextModel

class transformers.OwlViTTextModel

< >

( config: OwlViTTextConfig )

forward

< >

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

Parameters

  • input_ids (torch.LongTensor of shape (batch_size * num_max_text_queries, sequence_length)) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using CLIPTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details. What are input IDs?
  • attention_mask (torch.Tensor of shape (batch_size, num_max_text_queries, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:
  • 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.

A transformers.modeling_outputs.BaseModelOutputWithPooling or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (<class 'transformers.models.owlvit.configuration_owlvit.OwlViTTextConfig'>) 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 OwlViTTextModel forward method, overrides the __call__ special method.

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

Examples:

>>> from transformers import OwlViTProcessor, OwlViTTextModel

>>> model = OwlViTTextModel.from_pretrained("google/owlvit-base-patch32")
>>> processor = OwlViTProcessor.from_pretrained("google/owlvit-base-patch32")
>>> inputs = processor(
...     text=[["a photo of a cat", "a photo of a dog"], ["photo of a astranaut"]], return_tensors="pt"
... )
>>> outputs = model(**inputs)
>>> last_hidden_state = outputs.last_hidden_state
>>> pooled_output = outputs.pooler_output  # pooled (EOS token) states

OwlViTVisionModel

class transformers.OwlViTVisionModel

< >

( config: OwlViTVisionConfig )

forward

< >

( pixel_values: typing.Optional[torch.FloatTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.modeling_outputs.BaseModelOutputWithPooling or tuple(torch.FloatTensor)

Parameters

  • pixel_values (torch.FloatTensor of shape (batch_size, num_channels, height, width)) — Pixel values.
  • 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.

A transformers.modeling_outputs.BaseModelOutputWithPooling or a tuple of torch.FloatTensor (if return_dict=False is passed or when config.return_dict=False) comprising various elements depending on the configuration (<class 'transformers.models.owlvit.configuration_owlvit.OwlViTVisionConfig'>) 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 OwlViTVisionModel forward method, overrides the __call__ special method.

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

Examples:

>>> from PIL import Image
>>> import requests
>>> from transformers import OwlViTProcessor, OwlViTVisionModel

>>> model = OwlViTVisionModel.from_pretrained("google/owlvit-base-patch32")
>>> processor = OwlViTProcessor.from_pretrained("google/owlvit-base-patch32")
>>> url = "http://images.cocodataset.org/val2017/000000039769.jpg"
>>> image = Image.open(requests.get(url, stream=True).raw)

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

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

OwlViTForObjectDetection

class transformers.OwlViTForObjectDetection

< >

( config: OwlViTConfig )

forward

< >

( input_ids: Tensor pixel_values: FloatTensor attention_mask: typing.Optional[torch.Tensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.models.owlvit.modeling_owlvit.OwlViTObjectDetectionOutput or tuple(torch.FloatTensor)

Parameters

  • pixel_values (torch.FloatTensor of shape (batch_size, num_channels, height, width)) — Pixel values.
  • input_ids (torch.LongTensor of shape (batch_size * num_max_text_queries, sequence_length)) — Indices of input sequence tokens in the vocabulary. Indices can be obtained using CLIPTokenizer. See PreTrainedTokenizer.encode() and PreTrainedTokenizer.call() for details. What are input IDs?
  • attention_mask (torch.Tensor of shape (batch_size, num_max_text_queries, sequence_length), optional) — Mask to avoid performing attention on padding token indices. Mask values selected in [0, 1]:

Returns

transformers.models.owlvit.modeling_owlvit.OwlViTObjectDetectionOutput or tuple(torch.FloatTensor)

A transformers.models.owlvit.modeling_owlvit.OwlViTObjectDetectionOutput 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.owlvit.configuration_owlvit.OwlViTConfig'>) and inputs.

  • loss (torch.FloatTensor of shape (1,), optional, returned when labels are provided)) — Total loss as a linear combination of a negative log-likehood (cross-entropy) for class prediction and a bounding box loss. The latter is defined as a linear combination of the L1 loss and the generalized scale-invariant IoU loss.
  • loss_dict (Dict, optional) — A dictionary containing the individual losses. Useful for logging.
  • logits (torch.FloatTensor of shape (batch_size, num_patches, num_queries)) — Classification logits (including no-object) for all queries.
  • pred_boxes (torch.FloatTensor of shape (batch_size, num_patches, 4)) — Normalized boxes coordinates for all queries, represented as (center_x, center_y, width, height). These values are normalized in [0, 1], relative to the size of each individual image in the batch (disregarding possible padding). You can use post_process() to retrieve the unnormalized bounding boxes.
  • text_embeds (torch.FloatTensor of shape (batch_size, num_max_text_queries, output_dim) — The text embeddings obtained by applying the projection layer to the pooled output of OwlViTTextModel.
  • image_embeds (torch.FloatTensor of shape (batch_size, patch_size, patch_size, output_dim) — Pooled output of OwlViTVisionModel. OWL-ViT represents images as a set of image patches and computes image embeddings for each patch.
  • class_embeds (torch.FloatTensor of shape (batch_size, num_patches, hidden_size)) — Class embeddings of all image patches. OWL-ViT represents images as a set of image patches where the total number of patches is (image_size / patch_size)**2.
  • text_model_last_hidden_states (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size))) — Last hidden states extracted from the OwlViTTextModel.
  • vision_model_last_hidden_states (torch.FloatTensor of shape (batch_size, num_patches + 1, hidden_size))) — Last hidden states extracted from the OwlViTVisionModel. OWL-ViT represents images as a set of image patches where the total number of patches is (image_size / patch_size)**2.

The OwlViTForObjectDetection forward method, overrides the __call__ special method.

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

Examples:

>>> import requests
>>> from PIL import Image
>>> import torch
>>> from transformers import OwlViTProcessor, OwlViTForObjectDetection

>>> processor = OwlViTProcessor.from_pretrained("google/owlvit-base-patch32")
>>> model = OwlViTForObjectDetection.from_pretrained("google/owlvit-base-patch32")

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

>>> # Target image sizes (height, width) to rescale box predictions [batch_size, 2]
>>> target_sizes = torch.Tensor([image.size[::-1]])
>>> # Convert outputs (bounding boxes and class logits) to COCO API
>>> results = processor.post_process(outputs=outputs, target_sizes=target_sizes)

>>> i = 0  # Retrieve predictions for the first image for the corresponding text queries
>>> text = texts[i]
>>> boxes, scores, labels = results[i]["boxes"], results[i]["scores"], results[i]["labels"]

>>> score_threshold = 0.1
>>> for box, score, label in zip(boxes, scores, labels):
...     box = [round(i, 2) for i in box.tolist()]
...     if score >= score_threshold:
...         print(f"Detected {text[label]} with confidence {round(score.item(), 3)} at location {box}")
Detected a photo of a cat with confidence 0.243 at location [1.42, 50.69, 308.58, 370.48]
Detected a photo of a cat with confidence 0.298 at location [348.06, 20.56, 642.33, 372.61]