Transformers documentation

ViTMatte

Transformers

You are viewing main version, which requires installation from source. If you'd like regular pip install, checkout the latest stable version (v5.3.0).

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

to get started

This model was released on 2023-05-24 and added to Hugging Face Transformers on 2023-09-19.

ViTMatte

Overview

The ViTMatte model was proposed in Boosting Image Matting with Pretrained Plain Vision Transformers by Jingfeng Yao, Xinggang Wang, Shusheng Yang, Baoyuan Wang. ViTMatte leverages plain Vision Transformers for the task of image matting, which is the process of accurately estimating the foreground object in images and videos.

The abstract from the paper is the following:

Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered the problem of image matting. We hypothesize that image matting could also be boosted by ViTs and present a new efficient and robust ViT-based matting system, named ViTMatte. Our method utilizes (i) a hybrid attention mechanism combined with a convolution neck to help ViTs achieve an excellent performance-computation trade-off in matting tasks. (ii) Additionally, we introduce the detail capture module, which just consists of simple lightweight convolutions to complement the detailed information required by matting. To the best of our knowledge, ViTMatte is the first work to unleash the potential of ViT on image matting with concise adaptation. It inherits many superior properties from ViT to matting, including various pretraining strategies, concise architecture design, and flexible inference strategies. We evaluate ViTMatte on Composition-1k and Distinctions-646, the most commonly used benchmark for image matting, our method achieves state-of-the-art performance and outperforms prior matting works by a large margin.

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

ViTMatte high-level overview. Taken from the original paper.

Resources

A list of official Hugging Face and community (indicated by 🌎) resources to help you get started with ViTMatte.

A demo notebook regarding inference with VitMatteForImageMatting, including background replacement, can be found here.

The model expects both the image and trimap (concatenated) as input. Use ViTMatteImageProcessor for this purpose.

VitMatteConfig

class transformers.VitMatteConfig

< source >

( output_hidden_states: bool | None = False return_dict: bool | None = True dtype: typing.Union[str, ForwardRef('torch.dtype'), NoneType] = None chunk_size_feed_forward: int = 0 is_encoder_decoder: bool = False id2label: dict[int, str] | dict[str, str] | None = None label2id: dict[str, int] | dict[str, str] | None = None problem_type: typing.Optional[typing.Literal['regression', 'single_label_classification', 'multi_label_classification']] = None tokenizer_class: str | transformers.tokenization_utils_base.PreTrainedTokenizerBase | None = None backbone_config: dict | transformers.configuration_utils.PreTrainedConfig | None = None hidden_size: int = 384 batch_norm_eps: float = 1e-05 initializer_range: float = 0.02 convstream_hidden_sizes: list[int] | tuple[int, ...] = (48, 96, 192) fusion_hidden_sizes: list[int] | tuple[int, ...] = (256, 128, 64, 32) )

Parameters

output_hidden_states (bool, optional, defaults to False) — Whether or not the model should return all hidden-states.
return_dict (bool, optional, defaults to True) — Whether to return a ModelOutput (dataclass) instead of a plain tuple.
dtype (Union[str, torch.dtype], optional) — The chunk size of all feed forward layers in the residual attention blocks. A chunk size of 0 means that the feed forward layer is not chunked. A chunk size of n means that the feed forward layer processes n < sequence_length embeddings at a time. For more information on feed forward chunking, see How does Feed Forward Chunking work?.
chunk_size_feed_forward (int, optional, defaults to 0) — The dtype of the weights. This attribute can be used to initialize the model to a non-default dtype (which is normally float32) and thus allow for optimal storage allocation. For example, if the saved model is float16, ideally we want to load it back using the minimal amount of memory needed to load float16 weights.
is_encoder_decoder (bool, optional, defaults to False) — Whether the model is used as an encoder/decoder or not.
id2label (Union[dict[int, str], dict[str, str]], optional) — A map from index (for instance prediction index, or target index) to label.
label2id (Union[dict[str, int], dict[str, str]], optional) — A map from label to index for the model.
problem_type (Literal[regression, single_label_classification, multi_label_classification], optional) — Problem type for XxxForSequenceClassification models. Can be one of "regression", "single_label_classification" or "multi_label_classification".
tokenizer_class (Union[str, ~tokenization_utils_base.PreTrainedTokenizerBase], optional) — The class name of model’s tokenizer.
backbone_config (Union[dict, ~configuration_utils.PreTrainedConfig], optional) — The configuration of the backbone model.
hidden_size (int, optional, defaults to 384) — Dimension of the hidden representations.
batch_norm_eps (float, optional, defaults to 1e-05) — The epsilon used by the batch norm layers.
initializer_range (float, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
convstream_hidden_sizes (list[int], optional, defaults to [48, 96, 192]) — The output channels of the ConvStream module.
fusion_hidden_sizes (list[int], optional, defaults to [256, 128, 64, 32]) — The output channels of the Fusion blocks.

This is the configuration class to store the configuration of a VitmatteModel. It is used to instantiate a Vitmatte 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 hustvl/vitmatte-small-composition-1k

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 VitMatteConfig, VitMatteForImageMatting

>>> # Initializing a ViTMatte hustvl/vitmatte-small-composition-1k style configuration
>>> configuration = VitMatteConfig()

>>> # Initializing a model (with random weights) from the hustvl/vitmatte-small-composition-1k style configuration
>>> model = VitMatteForImageMatting(configuration)

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

VitMatteImageProcessor

class transformers.VitMatteImageProcessor

< source >

( **kwargs: typing_extensions.Unpack[transformers.models.vitmatte.image_processing_vitmatte.VitMatteImageProcessorKwargs] )

Parameters

size_divisor (int, kwargs, optional, defaults to self.size_divisor) — The width and height of the image will be padded to be divisible by this number.
**kwargs (ImagesKwargs, optional) — Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments.

Constructs a VitMatteImageProcessor image processor.

preprocess

< source >

( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']] trimaps: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), list['PIL.Image.Image'], list[numpy.ndarray], list['torch.Tensor']] **kwargs: typing_extensions.Unpack[transformers.models.vitmatte.image_processing_vitmatte.VitMatteImageProcessorKwargs] ) → ~image_processing_base.BatchFeature

Parameters

images (Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]) — Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set do_rescale=False.
trimaps (Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]) — The trimaps to preprocess.
size_divisor (int, kwargs, optional, defaults to self.size_divisor) — The width and height of the image will be padded to be divisible by this number.
return_tensors (str or TensorType, optional) — Returns stacked tensors if set to 'pt', otherwise returns a list of tensors.
**kwargs (ImagesKwargs, optional) — Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments.

Returns

~image_processing_base.BatchFeature

data (dict) — Dictionary of lists/arrays/tensors returned by the call method (‘pixel_values’, etc.).
tensor_type (Union[None, str, TensorType], optional) — You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization.

VitMatteImageProcessorPil

class transformers.VitMatteImageProcessorPil

< source >

( **kwargs: typing_extensions.Unpack[transformers.models.vitmatte.image_processing_vitmatte.VitMatteImageProcessorKwargs] )

Parameters

size_divisor (int, kwargs, optional, defaults to self.size_divisor) — The width and height of the image will be padded to be divisible by this number.
**kwargs (ImagesKwargs, optional) — Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments.

Constructs a VitMatteImageProcessor image processor.

preprocess

< source >

Parameters

images (Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]) — Image to preprocess. Expects a single or batch of images with pixel values ranging from 0 to 255. If passing in images with pixel values between 0 and 1, set do_rescale=False.
trimaps (Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, list[PIL.Image.Image], list[numpy.ndarray], list[torch.Tensor]]) — The trimaps to preprocess.
size_divisor (int, kwargs, optional, defaults to self.size_divisor) — The width and height of the image will be padded to be divisible by this number.
return_tensors (str or TensorType, optional) — Returns stacked tensors if set to 'pt', otherwise returns a list of tensors.
**kwargs (ImagesKwargs, optional) — Additional image preprocessing options. Model-specific kwargs are listed above; see the TypedDict class for the complete list of supported arguments.

Returns

~image_processing_base.BatchFeature

data (dict) — Dictionary of lists/arrays/tensors returned by the call method (‘pixel_values’, etc.).
tensor_type (Union[None, str, TensorType], optional) — You can give a tensor_type here to convert the lists of integers in PyTorch/Numpy Tensors at initialization.

VitMatteForImageMatting

class transformers.VitMatteForImageMatting

< source >

( config )

Parameters

config (VitMatteForImageMatting) — 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.

ViTMatte framework leveraging any vision backbone e.g. for ADE20k, CityScapes.

This model inherits from PreTrainedModel. Check the superclass documentation for the generic methods the library implements for all its model (such as downloading or saving, resizing the input embeddings, pruning heads etc.)

This model is also a PyTorch torch.nn.Module 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 >

Parameters

pixel_values (torch.Tensor of shape (batch_size, num_channels, image_size, image_size), optional) — The tensors corresponding to the input images. Pixel values can be obtained using VitMatteImageProcessor. See VitMatteImageProcessor.__call__() for details (processor_class uses VitMatteImageProcessor for processing images).
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.
labels (torch.LongTensor of shape (batch_size, height, width), optional) — Ground truth image matting for computing the loss.
return_dict (bool, optional) — Whether or not to return a ModelOutput instead of a plain tuple.

The VitMatteForImageMatting 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 VitMatteImageProcessor, VitMatteForImageMatting
>>> import torch
>>> from PIL import Image
>>> from huggingface_hub import hf_hub_download

>>> processor = VitMatteImageProcessor.from_pretrained("hustvl/vitmatte-small-composition-1k")
>>> model = VitMatteForImageMatting.from_pretrained("hustvl/vitmatte-small-composition-1k")

>>> filepath = hf_hub_download(
...     repo_id="hf-internal-testing/image-matting-fixtures", filename="image.png", repo_type="dataset"
... )
>>> image = Image.open(filepath).convert("RGB")
>>> filepath = hf_hub_download(
...     repo_id="hf-internal-testing/image-matting-fixtures", filename="trimap.png", repo_type="dataset"
... )
>>> trimap = Image.open(filepath).convert("L")

>>> # prepare image + trimap for the model
>>> inputs = processor(images=image, trimaps=trimap, return_tensors="pt")

>>> with torch.no_grad():
...     alphas = model(**inputs).alphas
>>> print(alphas.shape)
torch.Size([1, 1, 640, 960])

Update on GitHub

←ViTMAE ViTMSN→