Hugging Face's logo

Transformers documentation

DETA

You are viewing v4.34.1 version. A newer version v4.46.2 is available.
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

DETA

Overview

The DETA model was proposed in NMS Strikes Back by Jeffrey Ouyang-Zhang, Jang Hyun Cho, Xingyi Zhou, Philipp Krähenbühl. DETA (short for Detection Transformers with Assignment) improves Deformable DETR by replacing the one-to-one bipartite Hungarian matching loss with one-to-many label assignments used in traditional detectors with non-maximum suppression (NMS). This leads to significant gains of up to 2.5 mAP.

The abstract from the paper is the following:

Detection Transformer (DETR) directly transforms queries to unique objects by using one-to-one bipartite matching during training and enables end-to-end object detection. Recently, these models have surpassed traditional detectors on COCO with undeniable elegance. However, they differ from traditional detectors in multiple designs, including model architecture and training schedules, and thus the effectiveness of one-to-one matching is not fully understood. In this work, we conduct a strict comparison between the one-to-one Hungarian matching in DETRs and the one-to-many label assignments in traditional detectors with non-maximum supervision (NMS). Surprisingly, we observe one-to-many assignments with NMS consistently outperform standard one-to-one matching under the same setting, with a significant gain of up to 2.5 mAP. Our detector that trains Deformable-DETR with traditional IoU-based label assignment achieved 50.2 COCO mAP within 12 epochs (1x schedule) with ResNet50 backbone, outperforming all existing traditional or transformer-based detectors in this setting. On multiple datasets, schedules, and architectures, we consistently show bipartite matching is unnecessary for performant detection transformers. Furthermore, we attribute the success of detection transformers to their expressive transformer architecture.

Tips:

drawing DETA overview. Taken from the original paper.

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

Resources

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

If you’re interested in submitting a resource to be included here, please feel free to open a Pull Request and we’ll review it! The resource should ideally demonstrate something new instead of duplicating an existing resource.

DetaConfig

class transformers.DetaConfig

< >

( backbone_config = None num_queries = 900 max_position_embeddings = 2048 encoder_layers = 6 encoder_ffn_dim = 2048 encoder_attention_heads = 8 decoder_layers = 6 decoder_ffn_dim = 1024 decoder_attention_heads = 8 encoder_layerdrop = 0.0 is_encoder_decoder = True activation_function = 'relu' d_model = 256 dropout = 0.1 attention_dropout = 0.0 activation_dropout = 0.0 init_std = 0.02 init_xavier_std = 1.0 return_intermediate = True auxiliary_loss = False position_embedding_type = 'sine' num_feature_levels = 5 encoder_n_points = 4 decoder_n_points = 4 two_stage = True two_stage_num_proposals = 300 with_box_refine = True assign_first_stage = True class_cost = 1 bbox_cost = 5 giou_cost = 2 mask_loss_coefficient = 1 dice_loss_coefficient = 1 bbox_loss_coefficient = 5 giou_loss_coefficient = 2 eos_coefficient = 0.1 focal_alpha = 0.25 **kwargs )

Parameters

  • backbone_config (PretrainedConfig or dict, optional, defaults to ResNetConfig()) — The configuration of the backbone model.
  • num_queries (int, optional, defaults to 900) — Number of object queries, i.e. detection slots. This is the maximal number of objects DetaModel can detect in a single image. In case two_stage is set to True, we use two_stage_num_proposals instead.
  • d_model (int, optional, defaults to 256) — Dimension of the layers.
  • encoder_layers (int, optional, defaults to 6) — Number of encoder layers.
  • decoder_layers (int, optional, defaults to 6) — Number of decoder layers.
  • encoder_attention_heads (int, optional, defaults to 8) — Number of attention heads for each attention layer in the Transformer encoder.
  • decoder_attention_heads (int, optional, defaults to 8) — Number of attention heads for each attention layer in the Transformer decoder.
  • decoder_ffn_dim (int, optional, defaults to 2048) — Dimension of the “intermediate” (often named feed-forward) layer in decoder.
  • encoder_ffn_dim (int, optional, defaults to 2048) — Dimension of the “intermediate” (often named feed-forward) layer in decoder.
  • activation_function (str or function, optional, defaults to "relu") — The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "silu" and "gelu_new" are supported.
  • dropout (float, optional, defaults to 0.1) — The dropout probability 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.
  • activation_dropout (float, optional, defaults to 0.0) — The dropout ratio for activations inside the fully connected layer.
  • init_std (float, optional, defaults to 0.02) — The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
  • init_xavier_std (float, optional, defaults to 1) — The scaling factor used for the Xavier initialization gain in the HM Attention map module.
  • encoder_layerdrop (float, optional, defaults to 0.0) — The LayerDrop probability for the encoder. See the [LayerDrop paper](see https://arxiv.org/abs/1909.11556) for more details.
  • auxiliary_loss (bool, optional, defaults to False) — Whether auxiliary decoding losses (loss at each decoder layer) are to be used.
  • position_embedding_type (str, optional, defaults to "sine") — Type of position embeddings to be used on top of the image features. One of "sine" or "learned".
  • class_cost (float, optional, defaults to 1) — Relative weight of the classification error in the Hungarian matching cost.
  • bbox_cost (float, optional, defaults to 5) — Relative weight of the L1 error of the bounding box coordinates in the Hungarian matching cost.
  • giou_cost (float, optional, defaults to 2) — Relative weight of the generalized IoU loss of the bounding box in the Hungarian matching cost.
  • mask_loss_coefficient (float, optional, defaults to 1) — Relative weight of the Focal loss in the panoptic segmentation loss.
  • dice_loss_coefficient (float, optional, defaults to 1) — Relative weight of the DICE/F-1 loss in the panoptic segmentation loss.
  • bbox_loss_coefficient (float, optional, defaults to 5) — Relative weight of the L1 bounding box loss in the object detection loss.
  • giou_loss_coefficient (float, optional, defaults to 2) — Relative weight of the generalized IoU loss in the object detection loss.
  • eos_coefficient (float, optional, defaults to 0.1) — Relative classification weight of the ‘no-object’ class in the object detection loss.
  • num_feature_levels (int, optional, defaults to 5) — The number of input feature levels.
  • encoder_n_points (int, optional, defaults to 4) — The number of sampled keys in each feature level for each attention head in the encoder.
  • decoder_n_points (int, optional, defaults to 4) — The number of sampled keys in each feature level for each attention head in the decoder.
  • two_stage (bool, optional, defaults to True) — Whether to apply a two-stage deformable DETR, where the region proposals are also generated by a variant of DETA, which are further fed into the decoder for iterative bounding box refinement.
  • two_stage_num_proposals (int, optional, defaults to 300) — The number of region proposals to be generated, in case two_stage is set to True.
  • with_box_refine (bool, optional, defaults to True) — Whether to apply iterative bounding box refinement, where each decoder layer refines the bounding boxes based on the predictions from the previous layer.
  • focal_alpha (float, optional, defaults to 0.25) — Alpha parameter in the focal loss.

This is the configuration class to store the configuration of a DetaModel. It is used to instantiate a DETA 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 DETA SenseTime/deformable-detr architecture.

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

Examples:

>>> from transformers import DetaConfig, DetaModel

>>> # Initializing a DETA SenseTime/deformable-detr style configuration
>>> configuration = DetaConfig()

>>> # Initializing a model (with random weights) from the SenseTime/deformable-detr style configuration
>>> model = DetaModel(configuration)

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

DetaImageProcessor

class transformers.DetaImageProcessor

< >

( format: typing.Union[str, transformers.models.deta.image_processing_deta.AnnotionFormat] = <AnnotionFormat.COCO_DETECTION: 'coco_detection'> do_resize: bool = True 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]] = None image_std: typing.Union[float, typing.List[float]] = None do_pad: bool = True **kwargs )

Parameters

  • format (str, optional, defaults to "coco_detection") — Data format of the annotations. One of “coco_detection” or “coco_panoptic”.
  • do_resize (bool, optional, defaults to True) — Controls 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[str, int] optional, defaults to {"shortest_edge" -- 800, "longest_edge": 1333}): Size of the image’s (height, width) dimensions after resizing. Can be overridden by the size parameter in the preprocess method.
  • resample (PILImageResampling, optional, defaults to PILImageResampling.BILINEAR) — Resampling filter to use if resizing the image.
  • do_rescale (bool, optional, defaults to True) — Controls whether 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. Can be overridden by the rescale_factor parameter in the preprocess method. do_normalize — Controls whether to normalize the image. 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 values to use when normalizing the image. Can be a single value or a list of values, one for each channel. 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 values to use when normalizing the image. Can be a single value or a list of values, one for each channel. Can be overridden by the image_std parameter in the preprocess method.
  • do_pad (bool, optional, defaults to True) — Controls whether to pad the image to the largest image in a batch and create a pixel mask. Can be overridden by the do_pad parameter in the preprocess method.

Constructs a Deformable DETR image processor.

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')]] annotations: typing.Union[typing.List[typing.Dict], typing.List[typing.List[typing.Dict]], NoneType] = None return_segmentation_masks: bool = None masks_path: typing.Union[str, pathlib.Path, NoneType] = None do_resize: typing.Optional[bool] = None size: typing.Union[typing.Dict[str, int], NoneType] = None resample = 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 format: typing.Union[str, transformers.models.deta.image_processing_deta.AnnotionFormat, NoneType] = None return_tensors: typing.Union[str, transformers.utils.generic.TensorType, NoneType] = None data_format: typing.Union[str, transformers.image_utils.ChannelDimension] = <ChannelDimension.FIRST: 'channels_first'> input_data_format: typing.Union[str, transformers.image_utils.ChannelDimension, NoneType] = None **kwargs )

Parameters

  • images (ImageInput) — Image or batch of images 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.
  • annotations (List[Dict] or List[List[Dict]], optional) — List of annotations associated with the image or batch of images. If annotionation is for object detection, the annotations should be a dictionary with the following keys:
    • “image_id” (int): The image id.
    • “annotations” (List[Dict]): List of annotations for an image. Each annotation should be a dictionary. An image can have no annotations, in which case the list should be empty. If annotionation is for segmentation, the annotations should be a dictionary with the following keys:
    • “image_id” (int): The image id.
    • “segments_info” (List[Dict]): List of segments for an image. Each segment should be a dictionary. An image can have no segments, in which case the list should be empty.
    • “file_name” (str): The file name of the image.
  • return_segmentation_masks (bool, optional, defaults to self.return_segmentation_masks) — Whether to return segmentation masks.
  • masks_path (str or pathlib.Path, optional) — Path to the directory containing the segmentation masks.
  • do_resize (bool, optional, defaults to self.do_resize) — Whether to resize the image.
  • size (Dict[str, int], optional, defaults to self.size) — Size of the image after resizing.
  • resample (PILImageResampling, optional, defaults to self.resample) — Resampling filter to use when resizing the image.
  • do_rescale (bool, optional, defaults to self.do_rescale) — Whether to rescale the image.
  • rescale_factor (float, optional, defaults to self.rescale_factor) — Rescale factor to use when rescaling the image.
  • 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) — Mean to use when normalizing the image.
  • image_std (float or List[float], optional, defaults to self.image_std) — Standard deviation to use when normalizing the image.
  • do_pad (bool, optional, defaults to self.do_pad) — Whether to pad the image.
  • format (str or AnnotionFormat, optional, defaults to self.format) — Format of the annotations.
  • return_tensors (str or TensorType, optional, defaults to self.return_tensors) — Type of tensors to return. If None, will return the list of images.
  • 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 a batch of images so that it can be used by the model.

post_process_object_detection

< >

( outputs threshold: float = 0.5 target_sizes: typing.Union[transformers.utils.generic.TensorType, typing.List[typing.Tuple]] = None nms_threshold: float = 0.7 ) → List[Dict]

Parameters

  • outputs (DetrObjectDetectionOutput) — Raw outputs of the model.
  • threshold (float, optional, defaults to 0.5) — Score threshold to keep object detection predictions.
  • target_sizes (torch.Tensor or List[Tuple[int, int]], optional) — Tensor of shape (batch_size, 2) or list of tuples (Tuple[int, int]) containing the target size (height, width) of each image in the batch. If left to None, predictions will not be resized.
  • nms_threshold (float, optional, defaults to 0.7) — NMS threshold.

Returns

List[Dict]

A list of dictionaries, each dictionary containing the scores, labels and boxes for an image in the batch as predicted by the model.

Converts the output of DetaForObjectDetection into final bounding boxes in (top_left_x, top_left_y, bottom_right_x, bottom_right_y) format. Only supports PyTorch.

DetaModel

class transformers.DetaModel

< >

( config: DetaConfig )

Parameters

  • config (DetaConfig) — 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.

The bare DETA Model (consisting of a backbone and encoder-decoder Transformer) outputting raw hidden-states without any specific head on top.

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: FloatTensor pixel_mask: typing.Optional[torch.LongTensor] = None decoder_attention_mask: typing.Optional[torch.FloatTensor] = None encoder_outputs: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None decoder_inputs_embeds: 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.models.deta.modeling_deta.DetaModelOutput or tuple(torch.FloatTensor)

Parameters

  • pixel_values (torch.FloatTensor of shape (batch_size, num_channels, height, width)) — Pixel values. Padding will be ignored by default should you provide it.

    Pixel values can be obtained using AutoImageProcessor. See AutoImageProcessor.__call__() for details.

  • pixel_mask (torch.LongTensor of shape (batch_size, height, width), optional) — Mask to avoid performing attention on padding pixel values. Mask values selected in [0, 1]:

    • 1 for pixels that are real (i.e. not masked),
    • 0 for pixels that are padding (i.e. masked).

    What are attention masks?

  • decoder_attention_mask (torch.FloatTensor of shape (batch_size, num_queries), optional) — Not used by default. Can be used to mask object queries.
  • encoder_outputs (tuple(tuple(torch.FloatTensor), optional) — Tuple consists of (last_hidden_state, optional: hidden_states, optional: attentions) last_hidden_state of shape (batch_size, sequence_length, hidden_size), optional) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.
  • inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing the flattened feature map (output of the backbone + projection layer), you can choose to directly pass a flattened representation of an image.
  • decoder_inputs_embeds (torch.FloatTensor of shape (batch_size, num_queries, hidden_size), optional) — Optionally, instead of initializing the queries with a tensor of zeros, you can choose to directly pass an embedded representation.
  • 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.deta.modeling_deta.DetaModelOutput or tuple(torch.FloatTensor)

A transformers.models.deta.modeling_deta.DetaModelOutput 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 (DetaConfig) and inputs.

  • init_reference_points (torch.FloatTensor of shape (batch_size, num_queries, 4)) — Initial reference points sent through the Transformer decoder.
  • last_hidden_state (torch.FloatTensor of shape (batch_size, num_queries, hidden_size)) — Sequence of hidden-states at the output of the last layer of the decoder of the model.
  • intermediate_hidden_states (torch.FloatTensor of shape (batch_size, config.decoder_layers, num_queries, hidden_size)) — Stacked intermediate hidden states (output of each layer of the decoder).
  • intermediate_reference_points (torch.FloatTensor of shape (batch_size, config.decoder_layers, num_queries, 4)) — Stacked intermediate reference points (reference points of each layer of the decoder).
  • decoder_hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.FloatTensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, num_queries, hidden_size). Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
  • decoder_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, num_queries, num_queries). Attentions weights of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
  • cross_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_queries, num_heads, 4, 4). Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
  • encoder_last_hidden_state (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder of the model.
  • encoder_hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.FloatTensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size). Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
  • encoder_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_queries, num_heads, 4, 4). Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
  • enc_outputs_class (torch.FloatTensor of shape (batch_size, sequence_length, config.num_labels), optional, returned when config.with_box_refine=True and config.two_stage=True) — Predicted bounding boxes scores where the top config.two_stage_num_proposals scoring bounding boxes are picked as region proposals in the first stage. Output of bounding box binary classification (i.e. foreground and background).
  • enc_outputs_coord_logits (torch.FloatTensor of shape (batch_size, sequence_length, 4), optional, returned when config.with_box_refine=True and config.two_stage=True) — Logits of predicted bounding boxes coordinates in the first stage.

The DetaModel 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 AutoImageProcessor, DetaModel
>>> from PIL import Image
>>> import requests

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

>>> image_processor = AutoImageProcessor.from_pretrained("jozhang97/deta-swin-large-o365")
>>> model = DetaModel.from_pretrained("jozhang97/deta-swin-large-o365", two_stage=False)

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

>>> outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 900, 256]

DetaForObjectDetection

class transformers.DetaForObjectDetection

< >

( config: DetaConfig )

Parameters

  • config (DetaConfig) — 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.

DETA Model (consisting of a backbone and encoder-decoder Transformer) with object detection heads on top, for tasks such as COCO detection.

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: FloatTensor pixel_mask: typing.Optional[torch.LongTensor] = None decoder_attention_mask: typing.Optional[torch.FloatTensor] = None encoder_outputs: typing.Optional[torch.FloatTensor] = None inputs_embeds: typing.Optional[torch.FloatTensor] = None decoder_inputs_embeds: typing.Optional[torch.FloatTensor] = None labels: typing.Optional[typing.List[dict]] = None output_attentions: typing.Optional[bool] = None output_hidden_states: typing.Optional[bool] = None return_dict: typing.Optional[bool] = None ) → transformers.models.deta.modeling_deta.DetaObjectDetectionOutput or tuple(torch.FloatTensor)

Parameters

  • pixel_values (torch.FloatTensor of shape (batch_size, num_channels, height, width)) — Pixel values. Padding will be ignored by default should you provide it.

    Pixel values can be obtained using AutoImageProcessor. See AutoImageProcessor.__call__() for details.

  • pixel_mask (torch.LongTensor of shape (batch_size, height, width), optional) — Mask to avoid performing attention on padding pixel values. Mask values selected in [0, 1]:

    • 1 for pixels that are real (i.e. not masked),
    • 0 for pixels that are padding (i.e. masked).

    What are attention masks?

  • decoder_attention_mask (torch.FloatTensor of shape (batch_size, num_queries), optional) — Not used by default. Can be used to mask object queries.
  • encoder_outputs (tuple(tuple(torch.FloatTensor), optional) — Tuple consists of (last_hidden_state, optional: hidden_states, optional: attentions) last_hidden_state of shape (batch_size, sequence_length, hidden_size), optional) is a sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention of the decoder.
  • inputs_embeds (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Optionally, instead of passing the flattened feature map (output of the backbone + projection layer), you can choose to directly pass a flattened representation of an image.
  • decoder_inputs_embeds (torch.FloatTensor of shape (batch_size, num_queries, hidden_size), optional) — Optionally, instead of initializing the queries with a tensor of zeros, you can choose to directly pass an embedded representation.
  • 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.
  • labels (List[Dict] of len (batch_size,), optional) — Labels for computing the bipartite matching loss. List of dicts, each dictionary containing at least the following 2 keys: ‘class_labels’ and ‘boxes’ (the class labels and bounding boxes of an image in the batch respectively). The class labels themselves should be a torch.LongTensor of len (number of bounding boxes in the image,) and the boxes a torch.FloatTensor of shape (number of bounding boxes in the image, 4).

Returns

transformers.models.deta.modeling_deta.DetaObjectDetectionOutput or tuple(torch.FloatTensor)

A transformers.models.deta.modeling_deta.DetaObjectDetectionOutput 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 (DetaConfig) 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_queries, num_classes + 1)) — Classification logits (including no-object) for all queries.
  • pred_boxes (torch.FloatTensor of shape (batch_size, num_queries, 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 ~DetaProcessor.post_process_object_detection to retrieve the unnormalized bounding boxes.
  • auxiliary_outputs (list[Dict], optional) — Optional, only returned when auxilary losses are activated (i.e. config.auxiliary_loss is set to True) and labels are provided. It is a list of dictionaries containing the two above keys (logits and pred_boxes) for each decoder layer.
  • last_hidden_state (torch.FloatTensor of shape (batch_size, num_queries, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the decoder of the model.
  • decoder_hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.FloatTensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, num_queries, hidden_size). Hidden-states of the decoder at the output of each layer plus the initial embedding outputs.
  • decoder_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, num_queries, num_queries). Attentions weights of the decoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
  • cross_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_queries, num_heads, 4, 4). Attentions weights of the decoder’s cross-attention layer, after the attention softmax, used to compute the weighted average in the cross-attention heads.
  • encoder_last_hidden_state (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size), optional) — Sequence of hidden-states at the output of the last layer of the encoder of the model.
  • encoder_hidden_states (tuple(torch.FloatTensor), optional, returned when output_hidden_states=True is passed or when config.output_hidden_states=True) — Tuple of torch.FloatTensor (one for the output of the embeddings + one for the output of each layer) of shape (batch_size, sequence_length, hidden_size). Hidden-states of the encoder at the output of each layer plus the initial embedding outputs.
  • encoder_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, sequence_length, num_heads, 4, 4). Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.
  • intermediate_hidden_states (torch.FloatTensor of shape (batch_size, config.decoder_layers, num_queries, hidden_size)) — Stacked intermediate hidden states (output of each layer of the decoder).
  • intermediate_reference_points (torch.FloatTensor of shape (batch_size, config.decoder_layers, num_queries, 4)) — Stacked intermediate reference points (reference points of each layer of the decoder).
  • init_reference_points (torch.FloatTensor of shape (batch_size, num_queries, 4)) — Initial reference points sent through the Transformer decoder.
  • enc_outputs_class (torch.FloatTensor of shape (batch_size, sequence_length, config.num_labels), optional, returned when config.with_box_refine=True and config.two_stage=True) — Predicted bounding boxes scores where the top config.two_stage_num_proposals scoring bounding boxes are picked as region proposals in the first stage. Output of bounding box binary classification (i.e. foreground and background).
  • enc_outputs_coord_logits (torch.FloatTensor of shape (batch_size, sequence_length, 4), optional, returned when config.with_box_refine=True and config.two_stage=True) — Logits of predicted bounding boxes coordinates in the first stage.

The DetaForObjectDetection 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 AutoImageProcessor, DetaForObjectDetection
>>> from PIL import Image
>>> import requests

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

>>> image_processor = AutoImageProcessor.from_pretrained("jozhang97/deta-swin-large")
>>> model = DetaForObjectDetection.from_pretrained("jozhang97/deta-swin-large")

>>> inputs = image_processor(images=image, return_tensors="pt")
>>> outputs = model(**inputs)

>>> # convert outputs (bounding boxes and class logits) to COCO API
>>> target_sizes = torch.tensor([image.size[::-1]])
>>> results = image_processor.post_process_object_detection(outputs, threshold=0.5, target_sizes=target_sizes)[
...     0
... ]
>>> for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
...     box = [round(i, 2) for i in box.tolist()]
...     print(
...         f"Detected {model.config.id2label[label.item()]} with confidence "
...         f"{round(score.item(), 3)} at location {box}"
...     )
Detected cat with confidence 0.683 at location [345.85, 23.68, 639.86, 372.83]
Detected cat with confidence 0.683 at location [8.8, 52.49, 316.93, 473.45]
Detected remote with confidence 0.568 at location [40.02, 73.75, 175.96, 117.33]
Detected remote with confidence 0.546 at location [333.68, 77.13, 370.12, 187.51]

←DeiT DETR→