Hugging Face's logo

Transformers documentation

SAM

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

SAM

Overview

SAM (Segment Anything Model) was proposed in Segment Anything by Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alex Berg, Wan-Yen Lo, Piotr Dollar, Ross Girshick.

The model can be used to predict segmentation masks of any object of interest given an input image.

example image

The abstract from the paper is the following:

We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest segmentation dataset to date (by far), with over 1 billion masks on 11M licensed and privacy respecting images. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks. We evaluate its capabilities on numerous tasks and find that its zero-shot performance is impressive — often competitive with or even superior to prior fully supervised results. We are releasing the Segment Anything Model (SAM) and corresponding dataset (SA-1B) of 1B masks and 11M images at https://segment-anything.com to foster research into foundation models for computer vision.

Tips:

  • The model predicts binary masks that states the presence or not of the object of interest given an image.
  • The model predicts much better results if input 2D points and/or input bounding boxes are provided
  • You can prompt multiple points for the same image, and predict a single mask.
  • Fine-tuning the model is not supported yet
  • According to the paper, textual input should be also supported. However, at this time of writing this seems not to be supported according to the official repository.

This model was contributed by ybelkada and ArthurZ. The original code can be found here.

Below is an example on how to run mask generation given an image and a 2D point:

import torch
from PIL import Image
import requests
from transformers import SamModel, SamProcessor

device = "cuda" if torch.cuda.is_available() else "cpu"
model = SamModel.from_pretrained("facebook/sam-vit-huge").to(device)
processor = SamProcessor.from_pretrained("facebook/sam-vit-huge")

img_url = "https://huggingface.co/ybelkada/segment-anything/resolve/main/assets/car.png"
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert("RGB")
input_points = [[[450, 600]]]  # 2D location of a window in the image

inputs = processor(raw_image, input_points=input_points, return_tensors="pt").to(device)
with torch.no_grad():
    outputs = model(**inputs)

masks = processor.image_processor.post_process_masks(
    outputs.pred_masks.cpu(), inputs["original_sizes"].cpu(), inputs["reshaped_input_sizes"].cpu()
)
scores = outputs.iou_scores

You can also process your own masks alongside the input images in the processor to be passed to the model.

import torch
from PIL import Image
import requests
from transformers import SamModel, SamProcessor

device = "cuda" if torch.cuda.is_available() else "cpu"
model = SamModel.from_pretrained("facebook/sam-vit-huge").to(device)
processor = SamProcessor.from_pretrained("facebook/sam-vit-huge")

img_url = "https://huggingface.co/ybelkada/segment-anything/resolve/main/assets/car.png"
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert("RGB")
mask_url = "https://huggingface.co/ybelkada/segment-anything/resolve/main/assets/car.png"
segmentation_map = Image.open(requests.get(mask_url, stream=True).raw).convert("1")
input_points = [[[450, 600]]]  # 2D location of a window in the image

inputs = processor(raw_image, input_points=input_points, segmentation_maps=segmentation_map, return_tensors="pt").to(device)
with torch.no_grad():
    outputs = model(**inputs)

masks = processor.image_processor.post_process_masks(
    outputs.pred_masks.cpu(), inputs["original_sizes"].cpu(), inputs["reshaped_input_sizes"].cpu()
)
scores = outputs.iou_scores

Resources

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

SlimSAM

SlimSAM, a pruned version of SAM, was proposed in 0.1% Data Makes Segment Anything Slim by Zigeng Chen et al. SlimSAM reduces the size of the SAM models considerably while maintaining the same performance.

Checkpoints can be found on the hub, and they can be used as a drop-in replacement of SAM.

Grounded SAM

One can combine Grounding DINO with SAM for text-based mask generation as introduced in Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks. You can refer to this demo notebook 🌍 for details.

drawing Grounded SAM overview. Taken from the original repository.

SamConfig

class transformers.SamConfig

< >

( vision_config = None prompt_encoder_config = None mask_decoder_config = None initializer_range = 0.02 **kwargs )

Parameters

  • vision_config (Union[dict, SamVisionConfig], optional) — Dictionary of configuration options used to initialize SamVisionConfig.
  • prompt_encoder_config (Union[dict, SamPromptEncoderConfig], optional) — Dictionary of configuration options used to initialize SamPromptEncoderConfig.
  • mask_decoder_config (Union[dict, SamMaskDecoderConfig], optional) — Dictionary of configuration options used to initialize SamMaskDecoderConfig.
  • kwargs (optional) — Dictionary of keyword arguments.

SamConfig is the configuration class to store the configuration of a SamModel. It is used to instantiate a SAM model according to the specified arguments, defining the vision model, prompt-encoder model and mask decoder configs. Instantiating a configuration with the defaults will yield a similar configuration to that of the SAM-ViT-H facebook/sam-vit-huge 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 (
...     SamVisionConfig,
...     SamPromptEncoderConfig,
...     SamMaskDecoderConfig,
...     SamModel,
... )

>>> # Initializing a SamConfig with `"facebook/sam-vit-huge"` style configuration
>>> configuration = SamConfig()

>>> # Initializing a SamModel (with random weights) from the `"facebook/sam-vit-huge"` style configuration
>>> model = SamModel(configuration)

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

>>> # We can also initialize a SamConfig from a SamVisionConfig, SamPromptEncoderConfig, and SamMaskDecoderConfig

>>> # Initializing SAM vision, SAM Q-Former and language model configurations
>>> vision_config = SamVisionConfig()
>>> prompt_encoder_config = SamPromptEncoderConfig()
>>> mask_decoder_config = SamMaskDecoderConfig()

>>> config = SamConfig(vision_config, prompt_encoder_config, mask_decoder_config)

SamVisionConfig

class transformers.SamVisionConfig

< >

( hidden_size = 768 output_channels = 256 num_hidden_layers = 12 num_attention_heads = 12 num_channels = 3 image_size = 1024 patch_size = 16 hidden_act = 'gelu' layer_norm_eps = 1e-06 attention_dropout = 0.0 initializer_range = 1e-10 qkv_bias = True mlp_ratio = 4.0 use_abs_pos = True use_rel_pos = True window_size = 14 global_attn_indexes = [2, 5, 8, 11] num_pos_feats = 128 mlp_dim = None **kwargs )

Parameters

  • hidden_size (int, optional, defaults to 768) — Dimensionality of the encoder layers and the pooler layer.
  • output_channels (int, optional, defaults to 256) — Dimensionality of the output channels in the Patch 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.
  • num_channels (int, optional, defaults to 3) — Number of channels in the input image.
  • image_size (int, optional, defaults to 1024) — Expected resolution. Target size of the resized input image.
  • patch_size (int, optional, defaults to 16) — Size of the patches to be extracted from the input image.
  • hidden_act (str, optional, defaults to "gelu") — The non-linear activation function (function or string)
  • layer_norm_eps (float, optional, defaults to 1e-06) — 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 1e-10) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
  • qkv_bias (bool, optional, defaults to True) — Whether to add a bias to query, key, value projections.
  • mlp_ratio (float, optional, defaults to 4.0) — Ratio of mlp hidden dim to embedding dim.
  • use_abs_pos (bool, optional, defaults to True) — Whether to use absolute position embedding.
  • use_rel_pos (bool, optional, defaults to True) — Whether to use relative position embedding.
  • window_size (int, optional, defaults to 14) — Window size for relative position.
  • global_attn_indexes (List[int], optional, defaults to [2, 5, 8, 11]) — The indexes of the global attention layers.
  • num_pos_feats (int, optional, defaults to 128) — The dimensionality of the position embedding.
  • mlp_dim (int, optional) — The dimensionality of the MLP layer in the Transformer encoder. If None, defaults to mlp_ratio * hidden_size.

This is the configuration class to store the configuration of a SamVisionModel. It is used to instantiate a SAM vision encoder according to the specified arguments, defining the model architecture. Instantiating a configuration defaults will yield a similar configuration to that of the SAM ViT-h facebook/sam-vit-huge architecture.

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

SamMaskDecoderConfig

class transformers.SamMaskDecoderConfig

< >

( hidden_size = 256 hidden_act = 'relu' mlp_dim = 2048 num_hidden_layers = 2 num_attention_heads = 8 attention_downsample_rate = 2 num_multimask_outputs = 3 iou_head_depth = 3 iou_head_hidden_dim = 256 layer_norm_eps = 1e-06 **kwargs )

Parameters

  • hidden_size (int, optional, defaults to 256) — Dimensionality of the hidden states.
  • hidden_act (str, optional, defaults to "relu") — The non-linear activation function used inside the SamMaskDecoder module.
  • mlp_dim (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 2) — 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.
  • attention_downsample_rate (int, optional, defaults to 2) — The downsampling rate of the attention layer.
  • num_multimask_outputs (int, optional, defaults to 3) — The number of outputs from the SamMaskDecoder module. In the Segment Anything paper, this is set to 3.
  • iou_head_depth (int, optional, defaults to 3) — The number of layers in the IoU head module.
  • iou_head_hidden_dim (int, optional, defaults to 256) — The dimensionality of the hidden states in the IoU head module.
  • layer_norm_eps (float, optional, defaults to 1e-06) — The epsilon used by the layer normalization layers.

This is the configuration class to store the configuration of a SamMaskDecoder. It is used to instantiate a SAM mask decoder to the specified arguments, defining the model architecture. Instantiating a configuration defaults will yield a similar configuration to that of the SAM-vit-h facebook/sam-vit-huge architecture.

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

SamPromptEncoderConfig

class transformers.SamPromptEncoderConfig

< >

( hidden_size = 256 image_size = 1024 patch_size = 16 mask_input_channels = 16 num_point_embeddings = 4 hidden_act = 'gelu' layer_norm_eps = 1e-06 **kwargs )

Parameters

  • hidden_size (int, optional, defaults to 256) — Dimensionality of the hidden states.
  • image_size (int, optional, defaults to 1024) — The expected output resolution of the image.
  • patch_size (int, optional, defaults to 16) — The size (resolution) of each patch.
  • mask_input_channels (int, optional, defaults to 16) — The number of channels to be fed to the MaskDecoder module.
  • num_point_embeddings (int, optional, defaults to 4) — The number of point embeddings to be used.
  • hidden_act (str, optional, defaults to "gelu") — The non-linear activation function in the encoder and pooler.

This is the configuration class to store the configuration of a SamPromptEncoder. The SamPromptEncoder module is used to encode the input 2D points and bounding boxes. Instantiating a configuration defaults will yield a similar configuration to that of the SAM-vit-h facebook/sam-vit-huge architecture.

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

SamProcessor

class transformers.SamProcessor

< >

( image_processor )

Parameters

  • image_processor (SamImageProcessor) — An instance of SamImageProcessor. The image processor is a required input.

Constructs a SAM processor which wraps a SAM image processor and an 2D points & Bounding boxes processor into a single processor.

SamProcessor offers all the functionalities of SamImageProcessor. See the docstring of call() for more information.

SamImageProcessor

class transformers.SamImageProcessor

< >

( do_resize: bool = True size: typing.Dict[str, int] = None mask_size: typing.Dict[str, int] = None resample: Resampling = <Resampling.BILINEAR: 2> do_rescale: bool = True rescale_factor: typing.Union[int, float] = 0.00392156862745098 do_normalize: bool = True image_mean: typing.Union[float, typing.List[float], NoneType] = None image_std: typing.Union[float, typing.List[float], NoneType] = None do_pad: bool = True pad_size: int = None mask_pad_size: int = None do_convert_rgb: bool = True **kwargs )

Parameters

  • do_resize (bool, optional, defaults to True) — Whether to resize the image’s (height, width) dimensions to the specified size. Can be overridden by the do_resize parameter in the preprocess method.
  • size (dict, optional, defaults to {"longest_edge" -- 1024}): Size of the output image after resizing. Resizes the longest edge of the image to match size["longest_edge"] while maintaining the aspect ratio. Can be overridden by the size parameter in the preprocess method.
  • mask_size (dict, optional, defaults to {"longest_edge" -- 256}): Size of the output segmentation map after resizing. Resizes the longest edge of the image to match size["longest_edge"] while maintaining the aspect ratio. Can be overridden by the mask_size parameter in the preprocess method.
  • resample (PILImageResampling, optional, defaults to Resampling.BILINEAR) — Resampling filter to use if resizing the image. Can be overridden by the resample parameter in the preprocess method.
  • do_rescale (bool, optional, defaults to True) — Wwhether to rescale the image by the specified scale rescale_factor. Can be overridden by the do_rescale parameter in the preprocess method.
  • rescale_factor (int or float, optional, defaults to 1/255) — Scale factor to use if rescaling the image. Only has an effect if do_rescale is set to True. Can be overridden by the rescale_factor parameter in the preprocess method.
  • do_normalize (bool, optional, defaults to True) — Whether to normalize the image. Can be overridden by the do_normalize parameter in the preprocess method. Can be overridden by the do_normalize parameter in the preprocess method.
  • image_mean (float or List[float], optional, defaults to IMAGENET_DEFAULT_MEAN) — Mean to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the image_mean parameter in the preprocess method. Can be overridden by the image_mean parameter in the preprocess method.
  • image_std (float or List[float], optional, defaults to IMAGENET_DEFAULT_STD) — Standard deviation to use if normalizing the image. This is a float or list of floats the length of the number of channels in the image. Can be overridden by the image_std parameter in the preprocess method. Can be overridden by the image_std parameter in the preprocess method.
  • do_pad (bool, optional, defaults to True) — Whether to pad the image to the specified pad_size. Can be overridden by the do_pad parameter in the preprocess method.
  • pad_size (dict, optional, defaults to {"height" -- 1024, "width": 1024}): Size of the output image after padding. Can be overridden by the pad_size parameter in the preprocess method.
  • mask_pad_size (dict, optional, defaults to {"height" -- 256, "width": 256}): Size of the output segmentation map after padding. Can be overridden by the mask_pad_size parameter in the preprocess method.
  • do_convert_rgb (bool, optional, defaults to True) — Whether to convert the image to RGB.

Constructs a SAM image processor.

filter_masks

< >

( masks iou_scores original_size cropped_box_image pred_iou_thresh = 0.88 stability_score_thresh = 0.95 mask_threshold = 0 stability_score_offset = 1 return_tensors = 'pt' )

Parameters

  • masks (Union[torch.Tensor, tf.Tensor]) — Input masks.
  • iou_scores (Union[torch.Tensor, tf.Tensor]) — List of IoU scores.
  • original_size (Tuple[int,int]) — Size of the orginal image.
  • cropped_box_image (np.array) — The cropped image.
  • pred_iou_thresh (float, optional, defaults to 0.88) — The threshold for the iou scores.
  • stability_score_thresh (float, optional, defaults to 0.95) — The threshold for the stability score.
  • mask_threshold (float, optional, defaults to 0) — The threshold for the predicted masks.
  • stability_score_offset (float, optional, defaults to 1) — The offset for the stability score used in the _compute_stability_score method.
  • return_tensors (str, optional, defaults to pt) — If pt, returns torch.Tensor. If tf, returns tf.Tensor.

Filters the predicted masks by selecting only the ones that meets several criteria. The first criterion being that the iou scores needs to be greater than pred_iou_thresh. The second criterion is that the stability score needs to be greater than stability_score_thresh. The method also converts the predicted masks to bounding boxes and pad the predicted masks if necessary.

generate_crop_boxes

< >

( image target_size crop_n_layers: int = 0 overlap_ratio: float = 0.3413333333333333 points_per_crop: typing.Optional[int] = 32 crop_n_points_downscale_factor: typing.Optional[typing.List[int]] = 1 device: typing.Optional[ForwardRef('torch.device')] = None input_data_format: typing.Union[str, transformers.image_utils.ChannelDimension, NoneType] = None return_tensors: str = 'pt' )

Parameters

  • image (np.array) — Input original image
  • target_size (int) — Target size of the resized image
  • crop_n_layers (int, optional, defaults to 0) — If >0, mask prediction will be run again on crops of the image. Sets the number of layers to run, where each layer has 2**i_layer number of image crops.
  • overlap_ratio (float, optional, defaults to 512/1500) — Sets the degree to which crops overlap. In the first crop layer, crops will overlap by this fraction of the image length. Later layers with more crops scale down this overlap.
  • points_per_crop (int, optional, defaults to 32) — Number of points to sample from each crop.
  • crop_n_points_downscale_factor (List[int], optional, defaults to 1) — The number of points-per-side sampled in layer n is scaled down by crop_n_points_downscale_factor**n.
  • device (torch.device, optional, defaults to None) — Device to use for the computation. If None, cpu will be used.
  • input_data_format (str or ChannelDimension, optional) — The channel dimension format of the input image. If not provided, it will be inferred.
  • return_tensors (str, optional, defaults to pt) — If pt, returns torch.Tensor. If tf, returns tf.Tensor.

Generates a list of crop boxes of different sizes. Each layer has (2i)2 boxes for the ith layer.

pad_image

< >

( image: ndarray pad_size: typing.Dict[str, int] data_format: typing.Union[str, transformers.image_utils.ChannelDimension, NoneType] = None input_data_format: typing.Union[str, transformers.image_utils.ChannelDimension, NoneType] = None **kwargs )

Parameters

  • image (np.ndarray) — Image to pad.
  • pad_size (Dict[str, int]) — Size of the output image after padding.
  • data_format (str or ChannelDimension, optional) — The data format of the image. Can be either “channels_first” or “channels_last”. If None, the data_format of the image will be used.
  • input_data_format (str or ChannelDimension, optional) — The channel dimension format of the input image. If not provided, it will be inferred.

Pad an image to (pad_size["height"], pad_size["width"]) with zeros to the right and bottom.

post_process_for_mask_generation

< >

( all_masks all_scores all_boxes crops_nms_thresh return_tensors = 'pt' )

Parameters

  • all_masks (Union[List[torch.Tensor], List[tf.Tensor]]) — List of all predicted segmentation masks
  • all_scores (Union[List[torch.Tensor], List[tf.Tensor]]) — List of all predicted iou scores
  • all_boxes (Union[List[torch.Tensor], List[tf.Tensor]]) — List of all bounding boxes of the predicted masks
  • crops_nms_thresh (float) — Threshold for NMS (Non Maximum Suppression) algorithm.
  • return_tensors (str, optional, defaults to pt) — If pt, returns torch.Tensor. If tf, returns tf.Tensor.

Post processes mask that are generated by calling the Non Maximum Suppression algorithm on the predicted masks.

post_process_masks

< >

( masks original_sizes reshaped_input_sizes mask_threshold = 0.0 binarize = True pad_size = None return_tensors = 'pt' ) → (Union[torch.Tensor, tf.Tensor])

Parameters

  • masks (Union[List[torch.Tensor], List[np.ndarray], List[tf.Tensor]]) — Batched masks from the mask_decoder in (batch_size, num_channels, height, width) format.
  • original_sizes (Union[torch.Tensor, tf.Tensor, List[Tuple[int,int]]]) — The original sizes of each image before it was resized to the model’s expected input shape, in (height, width) format.
  • reshaped_input_sizes (Union[torch.Tensor, tf.Tensor, List[Tuple[int,int]]]) — The size of each image as it is fed to the model, in (height, width) format. Used to remove padding.
  • mask_threshold (float, optional, defaults to 0.0) — The threshold to use for binarizing the masks.
  • binarize (bool, optional, defaults to True) — Whether to binarize the masks.
  • pad_size (int, optional, defaults to self.pad_size) — The target size the images were padded to before being passed to the model. If None, the target size is assumed to be the processor’s pad_size.
  • return_tensors (str, optional, defaults to "pt") — If "pt", return PyTorch tensors. If "tf", return TensorFlow tensors.

Returns

(Union[torch.Tensor, tf.Tensor])

Batched masks in batch_size, num_channels, height, width) format, where (height, width) is given by original_size.

Remove padding and upscale masks to the original image size.

preprocess

< >

( images: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), typing.List[ForwardRef('PIL.Image.Image')], typing.List[numpy.ndarray], typing.List[ForwardRef('torch.Tensor')]] segmentation_maps: typing.Union[ForwardRef('PIL.Image.Image'), numpy.ndarray, ForwardRef('torch.Tensor'), typing.List[ForwardRef('PIL.Image.Image')], typing.List[numpy.ndarray], typing.List[ForwardRef('torch.Tensor')], NoneType] = None do_resize: typing.Optional[bool] = None size: typing.Optional[typing.Dict[str, int]] = None mask_size: typing.Optional[typing.Dict[str, int]] = None resample: typing.Optional[ForwardRef('PILImageResampling')] = None do_rescale: typing.Optional[bool] = None rescale_factor: typing.Union[int, float, NoneType] = None do_normalize: typing.Optional[bool] = None image_mean: typing.Union[float, typing.List[float], NoneType] = None image_std: typing.Union[float, typing.List[float], NoneType] = None do_pad: typing.Optional[bool] = None pad_size: typing.Optional[typing.Dict[str, int]] = None mask_pad_size: typing.Optional[typing.Dict[str, int]] = None do_convert_rgb: typing.Optional[bool] = None return_tensors: typing.Union[str, transformers.utils.generic.TensorType, NoneType] = None data_format: ChannelDimension = <ChannelDimension.FIRST: 'channels_first'> input_data_format: typing.Union[str, transformers.image_utils.ChannelDimension, NoneType] = None )

Parameters

  • images (ImageInput) — 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.
  • segmentation_maps (ImageInput, optional) — Segmentation map to preprocess.
  • do_resize (bool, optional, defaults to self.do_resize) — Whether to resize the image.
  • size (Dict[str, int], optional, defaults to self.size) — Controls the size of the image after resize. The longest edge of the image is resized to size["longest_edge"] whilst preserving the aspect ratio.
  • mask_size (Dict[str, int], optional, defaults to self.mask_size) — Controls the size of the segmentation map after resize. The longest edge of the image is resized to size["longest_edge"] whilst preserving the aspect ratio.
  • resample (PILImageResampling, optional, defaults to self.resample) — PILImageResampling filter to use when resizing the image e.g. PILImageResampling.BILINEAR.
  • do_rescale (bool, optional, defaults to self.do_rescale) — Whether to rescale the image pixel values by rescaling factor.
  • rescale_factor (int or float, optional, defaults to self.rescale_factor) — Rescale factor to apply to the image pixel values.
  • do_normalize (bool, optional, defaults to self.do_normalize) — Whether to normalize the image.
  • image_mean (float or List[float], optional, defaults to self.image_mean) — Image mean to normalize the image by if do_normalize is set to True.
  • image_std (float or List[float], optional, defaults to self.image_std) — Image standard deviation to normalize the image by if do_normalize is set to True.
  • do_pad (bool, optional, defaults to self.do_pad) — Whether to pad the image.
  • pad_size (Dict[str, int], optional, defaults to self.pad_size) — Controls the size of the padding applied to the image. The image is padded to pad_size["height"] and pad_size["width"] if do_pad is set to True.
  • mask_pad_size (Dict[str, int], optional, defaults to self.mask_pad_size) — Controls the size of the padding applied to the segmentation map. The image is padded to mask_pad_size["height"] and mask_pad_size["width"] if do_pad is set to True.
  • do_convert_rgb (bool, optional, defaults to self.do_convert_rgb) — Whether to convert the image to RGB.
  • return_tensors (str or TensorType, optional) — The type of tensors to return. Can be one of:
    • Unset: Return a list of np.ndarray.
    • TensorType.TENSORFLOW or 'tf': Return a batch of type tf.Tensor.
    • TensorType.PYTORCH or 'pt': Return a batch of type torch.Tensor.
    • TensorType.NUMPY or 'np': Return a batch of type np.ndarray.
    • TensorType.JAX or 'jax': Return a batch of type jax.numpy.ndarray.
  • data_format (ChannelDimension or str, optional, defaults to ChannelDimension.FIRST) — The channel dimension format for the output image. Can be one of:
    • "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
    • "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format.
    • Unset: Use the channel dimension format of the input image.
  • input_data_format (ChannelDimension or str, optional) — The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of:
    • "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
    • "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format.
    • "none" or ChannelDimension.NONE: image in (height, width) format.

Preprocess an image or batch of images.

resize

< >

( image: ndarray size: typing.Dict[str, int] resample: Resampling = <Resampling.BICUBIC: 3> data_format: typing.Union[str, transformers.image_utils.ChannelDimension, NoneType] = None input_data_format: typing.Union[str, transformers.image_utils.ChannelDimension, NoneType] = None **kwargs ) → np.ndarray

Parameters

  • image (np.ndarray) — Image to resize.
  • size (Dict[str, int]) — Dictionary in the format {"longest_edge": int} specifying the size of the output image. The longest edge of the image will be resized to the specified size, while the other edge will be resized to maintain the aspect ratio.
  • resample — PILImageResampling filter to use when resizing the image e.g. PILImageResampling.BILINEAR.
  • data_format (ChannelDimension or str, optional) — The channel dimension format for the output image. If unset, the channel dimension format of the input image is used. Can be one of:
    • "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
    • "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format.
  • input_data_format (ChannelDimension or str, optional) — The channel dimension format for the input image. If unset, the channel dimension format is inferred from the input image. Can be one of:
    • "channels_first" or ChannelDimension.FIRST: image in (num_channels, height, width) format.
    • "channels_last" or ChannelDimension.LAST: image in (height, width, num_channels) format.

Returns

np.ndarray

The resized image.

Resize an image to (size["height"], size["width"]).

SamModel

class transformers.SamModel

< >

( config )

Parameters

  • config (SamConfig) — 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.

Segment Anything Model (SAM) for generating segmentation masks, given an input image and optional 2D location and bounding boxes. 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

< >

( pixel_values: typing.Optional[torch.FloatTensor] = None input_points: typing.Optional[torch.FloatTensor] = None input_labels: typing.Optional[torch.LongTensor] = None input_boxes: typing.Optional[torch.FloatTensor] = None input_masks: typing.Optional[torch.LongTensor] = None image_embeddings: typing.Optional[torch.FloatTensor] = None multimask_output: bool = True attention_similarity: typing.Optional[torch.FloatTensor] = None target_embedding: typing.Optional[torch.FloatTensor] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None **kwargs )

Parameters

  • pixel_values (torch.FloatTensor of shape (batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using SamProcessor. See SamProcessor.__call__() for details.
  • input_points (torch.FloatTensor of shape (batch_size, num_points, 2)) — Input 2D spatial points, this is used by the prompt encoder to encode the prompt. Generally yields to much better results. The points can be obtained by passing a list of list of list to the processor that will create corresponding torch tensors of dimension 4. The first dimension is the image batch size, the second dimension is the point batch size (i.e. how many segmentation masks do we want the model to predict per input point), the third dimension is the number of points per segmentation mask (it is possible to pass multiple points for a single mask), and the last dimension is the x (vertical) and y (horizontal) coordinates of the point. If a different number of points is passed either for each image, or for each mask, the processor will create “PAD” points that will correspond to the (0, 0) coordinate, and the computation of the embedding will be skipped for these points using the labels.
  • input_labels (torch.LongTensor of shape (batch_size, point_batch_size, num_points)) — Input labels for the points, this is used by the prompt encoder to encode the prompt. According to the official implementation, there are 3 types of labels

    • 1: the point is a point that contains the object of interest
    • 0: the point is a point that does not contain the object of interest
    • -1: the point corresponds to the background

    We added the label:

    • -10: the point is a padding point, thus should be ignored by the prompt encoder

    The padding labels should be automatically done by the processor.

  • input_boxes (torch.FloatTensor of shape (batch_size, num_boxes, 4)) — Input boxes for the points, this is used by the prompt encoder to encode the prompt. Generally yields to much better generated masks. The boxes can be obtained by passing a list of list of list to the processor, that will generate a torch tensor, with each dimension corresponding respectively to the image batch size, the number of boxes per image and the coordinates of the top left and botton right point of the box. In the order (x1, y1, x2, y2):

    • x1: the x coordinate of the top left point of the input box
    • y1: the y coordinate of the top left point of the input box
    • x2: the x coordinate of the bottom right point of the input box
    • y2: the y coordinate of the bottom right point of the input box
  • input_masks (torch.FloatTensor of shape (batch_size, image_size, image_size)) — SAM model also accepts segmentation masks as input. The mask will be embedded by the prompt encoder to generate a corresponding embedding, that will be fed later on to the mask decoder. These masks needs to be manually fed by the user, and they need to be of shape (batch_size, image_size, image_size).
  • image_embeddings (torch.FloatTensor of shape (batch_size, output_channels, window_size, window_size)) — Image embeddings, this is used by the mask decder to generate masks and iou scores. For more memory efficient computation, users can first retrieve the image embeddings using the get_image_embeddings method, and then feed them to the forward method instead of feeding the pixel_values.
  • multimask_output (bool, optional) — In the original implementation and paper, the model always outputs 3 masks per image (or per point / per bounding box if relevant). However, it is possible to just output a single mask, that corresponds to the “best” mask, by specifying multimask_output=False.
  • attention_similarity (torch.FloatTensor, optional) — Attention similarity tensor, to be provided to the mask decoder for target-guided attention in case the model is used for personalization as introduced in PerSAM.
  • target_embedding (torch.FloatTensor, optional) — Embedding of the target concept, to be provided to the mask decoder for target-semantic prompting in case the model is used for personalization as introduced in PerSAM.
  • 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.
  • Example —
  • ```python —

    from PIL import Image import requests from transformers import AutoModel, AutoProcessor

The SamModel 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.

TFSamModel

class transformers.TFSamModel

< >

( config **kwargs )

Parameters

  • config (SamConfig) — 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.

Segment Anything Model (SAM) for generating segmentation masks, given an input image and optional 2D location and bounding boxes. This model inherits from TFPreTrainedModel. 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 TensorFlow keras.Model subclass. Use it as a regular TensorFlow Model and refer to the TensorFlow documentation for all matter related to general usage and behavior.

call

< >

( pixel_values: TFModelInputType | None = None input_points: tf.Tensor | None = None input_labels: tf.Tensor | None = None input_boxes: tf.Tensor | None = None input_masks: tf.Tensor | None = None image_embeddings: tf.Tensor | None = None multimask_output: bool = True output_attentions: bool | None = None output_hidden_states: bool | None = None return_dict: bool | None = None training: bool = False **kwargs )

Parameters

  • pixel_values (tf.Tensor of shape (batch_size, num_channels, height, width)) — Pixel values. Pixel values can be obtained using SamProcessor. See SamProcessor.__call__() for details.
  • input_points (tf.Tensor of shape (batch_size, num_points, 2)) — Input 2D spatial points, this is used by the prompt encoder to encode the prompt. Generally yields to much better results. The points can be obtained by passing a list of list of list to the processor that will create corresponding tf tensors of dimension 4. The first dimension is the image batch size, the second dimension is the point batch size (i.e. how many segmentation masks do we want the model to predict per input point), the third dimension is the number of points per segmentation mask (it is possible to pass multiple points for a single mask), and the last dimension is the x (vertical) and y (horizontal) coordinates of the point. If a different number of points is passed either for each image, or for each mask, the processor will create “PAD” points that will correspond to the (0, 0) coordinate, and the computation of the embedding will be skipped for these points using the labels.
  • input_labels (tf.Tensor of shape (batch_size, point_batch_size, num_points)) — Input labels for the points, this is used by the prompt encoder to encode the prompt. According to the official implementation, there are 3 types of labels

    • 1: the point is a point that contains the object of interest
    • 0: the point is a point that does not contain the object of interest
    • -1: the point corresponds to the background

    We added the label:

    • -10: the point is a padding point, thus should be ignored by the prompt encoder

    The padding labels should be automatically done by the processor.

  • input_boxes (tf.Tensor of shape (batch_size, num_boxes, 4)) — Input boxes for the points, this is used by the prompt encoder to encode the prompt. Generally yields to much better generated masks. The boxes can be obtained by passing a list of list of list to the processor, that will generate a tf tensor, with each dimension corresponding respectively to the image batch size, the number of boxes per image and the coordinates of the top left and botton right point of the box. In the order (x1, y1, x2, y2):

    • x1: the x coordinate of the top left point of the input box
    • y1: the y coordinate of the top left point of the input box
    • x2: the x coordinate of the bottom right point of the input box
    • y2: the y coordinate of the bottom right point of the input box
  • input_masks (tf.Tensor of shape (batch_size, image_size, image_size)) — SAM model also accepts segmentation masks as input. The mask will be embedded by the prompt encoder to generate a corresponding embedding, that will be fed later on to the mask decoder. These masks needs to be manually fed by the user, and they need to be of shape (batch_size, image_size, image_size).
  • image_embeddings (tf.Tensor of shape (batch_size, output_channels, window_size, window_size)) — Image embeddings, this is used by the mask decder to generate masks and iou scores. For more memory efficient computation, users can first retrieve the image embeddings using the get_image_embeddings method, and then feed them to the call method instead of feeding the pixel_values.
  • multimask_output (bool, optional) — In the original implementation and paper, the model always outputs 3 masks per image (or per point / per bounding box if relevant). However, it is possible to just output a single mask, that corresponds to the “best” mask, by specifying multimask_output=False.
  • 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.

The TFSamModel 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.

< > Update on GitHub

←Qwen2VL SigLIP→