Hugging Face's logo

Transformers documentation

DETR

You are viewing v4.39.0 version. A newer version v4.46.3 is available.
Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

DETR

Overview

DETR モデルは、Transformers を使用したエンドツーエンドのオブジェクト検出 で提案されました。 Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov and Sergey Zagoruyko ルイコ。 DETR 畳み込みバックボーンと、その後にエンドツーエンドでトレーニングできるエンコーダー/デコーダー Transformer で構成されます。 物体の検出。 Faster-R-CNN や Mask-R-CNN などのモデルの複雑さの多くが大幅に簡素化されます。 領域提案、非最大抑制手順、アンカー生成などです。さらに、DETR は次のようにすることもできます。 デコーダ出力の上にマスク ヘッドを追加するだけで、パノプティック セグメンテーションを実行できるように自然に拡張されています。

論文の要約は次のとおりです。

物体検出を直接集合予測問題として見る新しい方法を紹介します。私たちのアプローチは、 検出パイプラインにより、非最大抑制などの多くの手作業で設計されたコンポーネントの必要性が効果的に排除されます。 タスクに関する事前の知識を明示的にエンコードするプロシージャまたはアンカーの生成。の主な成分は、 DEtection TRansformer または DETR と呼ばれる新しいフレームワークは、セットベースのグローバル損失であり、 二部マッチング、およびトランスフォーマー エンコーダー/デコーダー アーキテクチャ。学習されたオブジェクト クエリの固定された小さなセットが与えられると、 DETR は、オブジェクトとグローバル イメージ コンテキストの関係について推論し、最終セットを直接出力します。 並行して予想も。新しいモデルは概念的にシンプルであり、多くのモデルとは異なり、特殊なライブラリを必要としません。 他の最新の検出器。 DETR は、確立された、および同等の精度と実行時のパフォーマンスを実証します。 困難な COCO 物体検出データセットに基づく、高度に最適化された Faster RCNN ベースライン。さらに、DETR は簡単に実行できます。 統一された方法でパノプティック セグメンテーションを生成するために一般化されました。競合他社を大幅に上回るパフォーマンスを示しています ベースライン

このモデルは、nielsr によって提供されました。元のコードは こちら にあります。

How DETR works

DetrForObjectDetection がどのように機能するかを説明する TLDR は次のとおりです。

まず、事前にトレーニングされた畳み込みバックボーンを通じて画像が送信されます (論文では、著者らは次のように使用しています)。 ResNet-50/ResNet-101)。バッチ ディメンションも追加すると仮定します。これは、バックボーンへの入力が 画像に 3 つのカラー チャネル (RGB) があると仮定した場合の、形状 (batch_size, 3, height, width) のテンソル。 CNNのバックボーン 通常は (batch_size, 2048, height/32, width/32) の形状の、新しい低解像度の特徴マップを出力します。これは 次に、DETR の Transformer の隠れ次元 (デフォルトでは 256) に一致するように投影されます。 nn.Conv2D レイヤー。これで、形状 (batch_size, 256, height/32, width/32) のテンソルが完成しました。 特徴マップは平坦化および転置され、形状 (batch_size, seq_len, d_model) のテンソルを取得します = (batch_size, width/32*height/32, 256)。したがって、NLP モデルとの違いは、シーケンスの長さが実際には 通常よりも長くなりますが、「d_model」は小さくなります (NLP では通常 768 以上です)。

次に、これがエンコーダを介して送信され、同じ形状の encoder_hidden_​​states が出力されます (次のように考えることができます)。 これらは画像の特徴として）。次に、いわゆる オブジェクト クエリがデコーダを通じて送信されます。これは形状のテンソルです (batch_size, num_queries, d_model)。通常、num_queries は 100 に設定され、ゼロで初期化されます。 これらの入力埋め込みは学習された位置エンコーディングであり、作成者はこれをオブジェクト クエリと呼び、同様に エンコーダでは、それらは各アテンション層の入力に追加されます。各オブジェクト クエリは特定のオブジェクトを検索します。 画像では。デコーダは、複数のセルフ アテンション レイヤとエンコーダ デコーダ アテンション レイヤを通じてこれらの埋め込みを更新します。 同じ形状の decoder_hidden_​​states を出力します: (batch_size, num_queries, d_model)。次に頭が２つ オブジェクト検出のために上部に追加されます。各オブジェクト クエリをオブジェクトの 1 つに分類するための線形レイヤー、または「いいえ」 オブジェクト」、および各クエリの境界ボックスを予測する MLP。

モデルは 2 部マッチング損失を使用してトレーニングされます。つまり、実際に行うことは、予測されたクラスを比較することです + グラウンド トゥルース アノテーションに対する N = 100 個の各オブジェクト クエリの境界ボックス (同じ長さ N までパディング) (したがって、画像にオブジェクトが 4 つしか含まれていない場合、96 個の注釈にはクラスとして「オブジェクトなし」、およびクラスとして「境界ボックスなし」が含まれるだけになります。 境界ボックス)。 Hungarian matching algorithm は、検索に使用されます。 N 個のクエリのそれぞれから N 個の注釈のそれぞれへの最適な 1 対 1 のマッピング。次に、標準クロスエントロピー ( クラス)、および L1 と generalized IoU loss の線形結合 ( 境界ボックス) は、モデルのパラメーターを最適化するために使用されます。

DETR は、パノプティック セグメンテーション (セマンティック セグメンテーションとインスタンスを統合する) を実行するように自然に拡張できます。 セグメンテーション）。 DetrForSegmentation はセグメンテーション マスク ヘッドを上に追加します DetrForObjectDetection。マスク ヘッドは、共同でトレーニングすることも、2 段階のプロセスでトレーニングすることもできます。 ここで、最初に DetrForObjectDetection モデルをトレーニングして、両方の周囲の境界ボックスを検出します。 「もの」（インスタンス）と「もの」（木、道路、空などの背景のもの）をすべて凍結し、すべての重みをフリーズしてのみトレーニングします。 25 エポックのマスクヘッド。実験的には、これら 2 つのアプローチは同様の結果をもたらします。ボックスの予測は ハンガリー語のマッチングはボックス間の距離を使用して計算されるため、トレーニングを可能にするためにはこれが必要です。

Usage tips

  • DETR は、いわゆる オブジェクト クエリ を使用して、画像内のオブジェクトを検出します。クエリの数によって最大値が決まります 単一の画像内で検出できるオブジェクトの数。デフォルトでは 100 に設定されます (パラメーターを参照) DetrConfig の num_queries)。ある程度の余裕があるのは良いことです (COCO では、 著者は 100 を使用しましたが、COCO イメージ内のオブジェクトの最大数は約 70 です)。
  • DETR のデコーダーは、クエリの埋め込みを並行して更新します。これは GPT-2 のような言語モデルとは異なります。 並列ではなく自己回帰デコードを使用します。したがって、因果的注意マスクは使用されません。
  • DETR は、投影前に各セルフアテンション層とクロスアテンション層の隠れ状態に位置埋め込みを追加します。 クエリとキーに。画像の位置埋め込みについては、固定正弦波または学習済みのどちらかを選択できます。 絶対位置埋め込み。デフォルトでは、パラメータ position_embedding_type は DetrConfig は "sine" に設定されます。
  • DETR の作成者は、トレーニング中に、特にデコーダで補助損失を使用すると役立つことに気づきました。 モデルは各クラスの正しい数のオブジェクトを出力します。パラメータ auxiliary_loss を設定すると、 DetrConfig をTrueに設定し、フィードフォワード ニューラル ネットワークとハンガリー損失を予測します は各デコーダ層の後に追加されます (FFN がパラメータを共有する)。
  • 複数のノードにわたる分散環境でモデルをトレーニングする場合は、 modeling_detr.py の DetrLoss クラスの num_boxes 変数。複数のノードでトレーニングする場合、これは次のようにする必要があります 元の実装で見られるように、すべてのノードにわたるターゲット ボックスの平均数に設定されます こちら 。
  • DetrForObjectDetection および DetrForSegmentation は次のように初期化できます。 timm ライブラリ で利用可能な畳み込みバックボーン。 たとえば、MobileNet バックボーンを使用した初期化は、次の backbone 属性を設定することで実行できます。 DetrConfig を "tf_mobilenetv3_small_075" に設定し、それを使用してモデルを初期化します。 構成。
  • DETR は、最短辺が一定のピクセル数以上になり、最長辺が一定量以上になるように入力画像のサイズを変更します。 最大 1333 ピクセル。トレーニング時に、最短辺がランダムに に設定されるようにスケール拡張が使用されます。 最小 480、最大 800 ピクセル。推論時には、最短辺が 800 に設定されます。

使用できます DetrImageProcessor 用の画像 (およびオプションの COCO 形式の注釈) を準備します。 モデル。このサイズ変更により、バッチ内の画像のサイズが異なる場合があります。 DETR は、画像を最大までパディングすることでこの問題を解決します。 どのピクセルが実数でどのピクセルがパディングであるかを示すピクセル マスクを作成することによって、バッチ内の最大サイズを決定します。 あるいは、画像をバッチ処理するためにカスタムの collat​​e_fn を定義することもできます。 ~transformers.DetrImageProcessor.pad_and_create_pixel_mask。

  • 画像のサイズによって使用されるメモリの量が決まり、したがって「batch_size」も決まります。 GPU あたり 2 のバッチ サイズを使用することをお勧めします。詳細については、この Github スレッド を参照してください。

DETR モデルをインスタンス化するには 3 つの方法があります (好みに応じて)。

オプション 1: モデル全体の事前トレーニングされた重みを使用して DETR をインスタンス化する

>>> from transformers import DetrForObjectDetection

>>> model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")

オプション 2: Transformer についてはランダムに初期化された重みを使用して DETR をインスタンス化しますが、バックボーンについては事前にトレーニングされた重みを使用します

>>> from transformers import DetrConfig, DetrForObjectDetection

>>> config = DetrConfig()
>>> model = DetrForObjectDetection(config)

オプション 3: バックボーン + トランスフォーマーのランダムに初期化された重みを使用して DETR をインスタンス化します。

>>> config = DetrConfig(use_pretrained_backbone=False)
>>> model = DetrForObjectDetection(config)
Task Object detection Instance segmentation Panoptic segmentation
Description 画像内のオブジェクトの周囲の境界ボックスとクラス ラベルを予測する 画像内のオブジェクト (つまりインスタンス) の周囲のマスクを予測する 画像内のオブジェクト (インスタンス) と「もの」 (木や道路などの背景) の両方の周囲のマスクを予測します
Model DetrForObjectDetection DetrForSegmentation DetrForSegmentation
Example dataset COCO detection COCO detection, COCO panoptic COCO panoptic
Format of annotations to provide to DetrImageProcessor {‘image_id’: int, ‘annotations’: List[Dict]} each Dict being a COCO object annotation {‘image_id’: int, ‘annotations’: List[Dict]} (in case of COCO detection) or {‘file_name’: str, ‘image_id’: int, ‘segments_info’: List[Dict]} (in case of COCO panoptic) {‘file_name’: str, ‘image_id’: int, ‘segments_info’: List[Dict]} and masks_path (path to directory containing PNG files of the masks)
Postprocessing (i.e. converting the output of the model to Pascal VOC format) post_process() post_process_segmentation() post_process_segmentation(), post_process_panoptic()
evaluators CocoEvaluator with iou_types="bbox" CocoEvaluator with iou_types="bbox" or "segm" CocoEvaluator with iou_tupes="bbox" or "segm", PanopticEvaluator

つまり、COCO 検出または COCO パノプティック形式でデータを準備してから、次を使用する必要があります。 DetrImageProcessor pixel_values、pixel_mask、およびオプションを作成します。 「ラベル」。これを使用してモデルをトレーニング (または微調整) できます。評価するには、まず、 DetrImageProcessor の後処理メソッドの 1 つを使用したモデルの出力。これらはできます CocoEvaluator または PanopticEvaluator のいずれかに提供され、次のようなメトリクスを計算できます。 平均平均精度 (mAP) とパノラマ品質 (PQ)。後者のオブジェクトは 元のリポジトリ に実装されています。評価の詳細については、サンプル ノートブック を参照してください。

Resources

DETR の使用を開始するのに役立つ公式 Hugging Face およびコミュニティ (🌎 で示されている) リソースのリスト。

Object Detection

ここに含めるリソースの送信に興味がある場合は、お気軽にプル リクエストを開いてください。審査させていただきます。リソースは、既存のリソースを複製するのではなく、何か新しいものを示すことが理想的です。

DetrConfig

class transformers.DetrConfig

< >

( use_timm_backbone = True backbone_config = None num_channels = 3 num_queries = 100 encoder_layers = 6 encoder_ffn_dim = 2048 encoder_attention_heads = 8 decoder_layers = 6 decoder_ffn_dim = 2048 decoder_attention_heads = 8 encoder_layerdrop = 0.0 decoder_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 auxiliary_loss = False position_embedding_type = 'sine' backbone = 'resnet50' use_pretrained_backbone = True backbone_kwargs = None dilation = False 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 **kwargs )

Parameters

  • use_timm_backbone (bool, optional, defaults to True) — Whether or not to use the timm library for the backbone. If set to False, will use the AutoBackbone API.
  • backbone_config (PretrainedConfig or dict, optional) — The configuration of the backbone model. Only used in case use_timm_backbone is set to False in which case it will default to ResNetConfig().
  • num_channels (int, optional, defaults to 3) — The number of input channels.
  • num_queries (int, optional, defaults to 100) — Number of object queries, i.e. detection slots. This is the maximal number of objects DetrModel can detect in a single image. For COCO, we recommend 100 queries.
  • 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.
  • decoder_layerdrop (float, optional, defaults to 0.0) — The LayerDrop probability for the decoder. 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".
  • backbone (str, optional, defaults to "resnet50") — Name of backbone to use when backbone_config is None. If use_pretrained_backbone is True, this will load the corresponding pretrained weights from the timm or transformers library. If use_pretrained_backbone is False, this loads the backbone’s config and uses that to initialize the backbone with random weights.
  • use_pretrained_backbone (bool, optional, True) — Whether to use pretrained weights for the backbone.
  • backbone_kwargs (dict, optional) — Keyword arguments to be passed to AutoBackbone when loading from a checkpoint e.g. {'out_indices': (0, 1, 2, 3)}. Cannot be specified if backbone_config is set.
  • dilation (bool, optional, defaults to False) — Whether to replace stride with dilation in the last convolutional block (DC5). Only supported when use_timm_backbone = True.
  • 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.

This is the configuration class to store the configuration of a DetrModel. It is used to instantiate a DETR 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 DETR facebook/detr-resnet-50 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 DetrConfig, DetrModel

>>> # Initializing a DETR facebook/detr-resnet-50 style configuration
>>> configuration = DetrConfig()

>>> # Initializing a model (with random weights) from the facebook/detr-resnet-50 style configuration
>>> model = DetrModel(configuration)

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

from_backbone_config

< >

( backbone_config: PretrainedConfig **kwargs ) → DetrConfig

Parameters

Returns

DetrConfig

An instance of a configuration object

Instantiate a DetrConfig (or a derived class) from a pre-trained backbone model configuration.

DetrImageProcessor

class transformers.DetrImageProcessor

< >

( format: Union = <AnnotationFormat.COCO_DETECTION: 'coco_detection'> do_resize: bool = True size: Dict = None resample: Resampling = <Resampling.BILINEAR: 2> do_rescale: bool = True rescale_factor: Union = 0.00392156862745098 do_normalize: bool = True image_mean: Union = None image_std: Union = None do_convert_annotations: Optional = 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 (bool, optional, defaults to True) — 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_convert_annotations (bool, optional, defaults to True) — Controls whether to convert the annotations to the format expected by the DETR model. Converts the bounding boxes to the format (center_x, center_y, width, height) and in the range [0, 1]. Can be overridden by the do_convert_annotations parameter in the preprocess method.
  • do_pad (bool, optional, defaults to True) — Controls whether to pad the image. Can be overridden by the do_pad parameter in the preprocess method. If True will pad the images in the batch to the largest height and width in the batch. Padding will be applied to the bottom and right of the image with zeros.

Constructs a Detr image processor.

preprocess

< >

( images: Union annotations: Union = None return_segmentation_masks: bool = None masks_path: Union = None do_resize: Optional = None size: Optional = None resample = None do_rescale: Optional = None rescale_factor: Union = None do_normalize: Optional = None do_convert_annotations: Optional = None image_mean: Union = None image_std: Union = None do_pad: Optional = None format: Union = None return_tensors: Union = None data_format: Union = <ChannelDimension.FIRST: 'channels_first'> input_data_format: Union = 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 (AnnotationType or List[AnnotationType], optional) — List of annotations associated with the image or batch of images. If annotation 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 annotation 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.
  • do_convert_annotations (bool, optional, defaults to self.do_convert_annotations) — Whether to convert the annotations to the format expected by the model. Converts the bounding boxes from the format (top_left_x, top_left_y, width, height) to (center_x, center_y, width, height) and in relative coordinates.
  • 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. If True will pad the images in the batch to the largest image in the batch and create a pixel mask. Padding will be applied to the bottom and right of the image with zeros.
  • format (str or AnnotationFormat, 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: Union = None ) → List[Dict]

Parameters

  • outputs (DetrObjectDetectionOutput) — Raw outputs of the model.
  • threshold (float, optional) — 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 unset, predictions will not be resized.

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 raw output of DetrForObjectDetection into final bounding boxes in (top_left_x, top_left_y, bottom_right_x, bottom_right_y) format. Only supports PyTorch.

post_process_semantic_segmentation

< >

( outputs target_sizes: List = None ) → List[torch.Tensor]

Parameters

  • outputs (DetrForSegmentation) — Raw outputs of the model.
  • target_sizes (List[Tuple[int, int]], optional) — A list of tuples (Tuple[int, int]) containing the target size (height, width) of each image in the batch. If unset, predictions will not be resized.

Returns

List[torch.Tensor]

A list of length batch_size, where each item is a semantic segmentation map of shape (height, width) corresponding to the target_sizes entry (if target_sizes is specified). Each entry of each torch.Tensor correspond to a semantic class id.

Converts the output of DetrForSegmentation into semantic segmentation maps. Only supports PyTorch.

post_process_instance_segmentation

< >

( outputs threshold: float = 0.5 mask_threshold: float = 0.5 overlap_mask_area_threshold: float = 0.8 target_sizes: Optional = None return_coco_annotation: Optional = False ) → List[Dict]

Parameters

  • outputs (DetrForSegmentation) — Raw outputs of the model.
  • threshold (float, optional, defaults to 0.5) — The probability score threshold to keep predicted instance masks.
  • mask_threshold (float, optional, defaults to 0.5) — Threshold to use when turning the predicted masks into binary values.
  • overlap_mask_area_threshold (float, optional, defaults to 0.8) — The overlap mask area threshold to merge or discard small disconnected parts within each binary instance mask.
  • target_sizes (List[Tuple], optional) — List of length (batch_size), where each list item (Tuple[int, int]]) corresponds to the requested final size (height, width) of each prediction. If unset, predictions will not be resized.
  • return_coco_annotation (bool, optional) — Defaults to False. If set to True, segmentation maps are returned in COCO run-length encoding (RLE) format.

Returns

List[Dict]

A list of dictionaries, one per image, each dictionary containing two keys:

  • segmentation — A tensor of shape (height, width) where each pixel represents a segment_id or List[List] run-length encoding (RLE) of the segmentation map if return_coco_annotation is set to True. Set to None if no mask if found above threshold.
  • segments_info — A dictionary that contains additional information on each segment.
    • id — An integer representing the segment_id.
    • label_id — An integer representing the label / semantic class id corresponding to segment_id.
    • score — Prediction score of segment with segment_id.

Converts the output of DetrForSegmentation into instance segmentation predictions. Only supports PyTorch.

post_process_panoptic_segmentation

< >

( outputs threshold: float = 0.5 mask_threshold: float = 0.5 overlap_mask_area_threshold: float = 0.8 label_ids_to_fuse: Optional = None target_sizes: Optional = None ) → List[Dict]

Parameters

  • outputs (DetrForSegmentation) — The outputs from DetrForSegmentation.
  • threshold (float, optional, defaults to 0.5) — The probability score threshold to keep predicted instance masks.
  • mask_threshold (float, optional, defaults to 0.5) — Threshold to use when turning the predicted masks into binary values.
  • overlap_mask_area_threshold (float, optional, defaults to 0.8) — The overlap mask area threshold to merge or discard small disconnected parts within each binary instance mask.
  • label_ids_to_fuse (Set[int], optional) — The labels in this state will have all their instances be fused together. For instance we could say there can only be one sky in an image, but several persons, so the label ID for sky would be in that set, but not the one for person.
  • target_sizes (List[Tuple], optional) — List of length (batch_size), where each list item (Tuple[int, int]]) corresponds to the requested final size (height, width) of each prediction in batch. If unset, predictions will not be resized.

Returns

List[Dict]

A list of dictionaries, one per image, each dictionary containing two keys:

  • segmentation — a tensor of shape (height, width) where each pixel represents a segment_id or None if no mask if found above threshold. If target_sizes is specified, segmentation is resized to the corresponding target_sizes entry.
  • segments_info — A dictionary that contains additional information on each segment.
    • id — an integer representing the segment_id.
    • label_id — An integer representing the label / semantic class id corresponding to segment_id.
    • was_fused — a boolean, True if label_id was in label_ids_to_fuse, False otherwise. Multiple instances of the same class / label were fused and assigned a single segment_id.
    • score — Prediction score of segment with segment_id.

Converts the output of DetrForSegmentation into image panoptic segmentation predictions. Only supports PyTorch.

DetrFeatureExtractor

class transformers.DetrFeatureExtractor

< >

( *args **kwargs )

__call__

< >

( images **kwargs )

Preprocess an image or a batch of images.

post_process_object_detection

< >

( outputs threshold: float = 0.5 target_sizes: Union = None ) → List[Dict]

Parameters

  • outputs (DetrObjectDetectionOutput) — Raw outputs of the model.
  • threshold (float, optional) — 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 unset, predictions will not be resized.

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 raw output of DetrForObjectDetection into final bounding boxes in (top_left_x, top_left_y, bottom_right_x, bottom_right_y) format. Only supports PyTorch.

post_process_semantic_segmentation

< >

( outputs target_sizes: List = None ) → List[torch.Tensor]

Parameters

  • outputs (DetrForSegmentation) — Raw outputs of the model.
  • target_sizes (List[Tuple[int, int]], optional) — A list of tuples (Tuple[int, int]) containing the target size (height, width) of each image in the batch. If unset, predictions will not be resized.

Returns

List[torch.Tensor]

A list of length batch_size, where each item is a semantic segmentation map of shape (height, width) corresponding to the target_sizes entry (if target_sizes is specified). Each entry of each torch.Tensor correspond to a semantic class id.

Converts the output of DetrForSegmentation into semantic segmentation maps. Only supports PyTorch.

post_process_instance_segmentation

< >

( outputs threshold: float = 0.5 mask_threshold: float = 0.5 overlap_mask_area_threshold: float = 0.8 target_sizes: Optional = None return_coco_annotation: Optional = False ) → List[Dict]

Parameters

  • outputs (DetrForSegmentation) — Raw outputs of the model.
  • threshold (float, optional, defaults to 0.5) — The probability score threshold to keep predicted instance masks.
  • mask_threshold (float, optional, defaults to 0.5) — Threshold to use when turning the predicted masks into binary values.
  • overlap_mask_area_threshold (float, optional, defaults to 0.8) — The overlap mask area threshold to merge or discard small disconnected parts within each binary instance mask.
  • target_sizes (List[Tuple], optional) — List of length (batch_size), where each list item (Tuple[int, int]]) corresponds to the requested final size (height, width) of each prediction. If unset, predictions will not be resized.
  • return_coco_annotation (bool, optional) — Defaults to False. If set to True, segmentation maps are returned in COCO run-length encoding (RLE) format.

Returns

List[Dict]

A list of dictionaries, one per image, each dictionary containing two keys:

  • segmentation — A tensor of shape (height, width) where each pixel represents a segment_id or List[List] run-length encoding (RLE) of the segmentation map if return_coco_annotation is set to True. Set to None if no mask if found above threshold.
  • segments_info — A dictionary that contains additional information on each segment.
    • id — An integer representing the segment_id.
    • label_id — An integer representing the label / semantic class id corresponding to segment_id.
    • score — Prediction score of segment with segment_id.

Converts the output of DetrForSegmentation into instance segmentation predictions. Only supports PyTorch.

post_process_panoptic_segmentation

< >

( outputs threshold: float = 0.5 mask_threshold: float = 0.5 overlap_mask_area_threshold: float = 0.8 label_ids_to_fuse: Optional = None target_sizes: Optional = None ) → List[Dict]

Parameters

  • outputs (DetrForSegmentation) — The outputs from DetrForSegmentation.
  • threshold (float, optional, defaults to 0.5) — The probability score threshold to keep predicted instance masks.
  • mask_threshold (float, optional, defaults to 0.5) — Threshold to use when turning the predicted masks into binary values.
  • overlap_mask_area_threshold (float, optional, defaults to 0.8) — The overlap mask area threshold to merge or discard small disconnected parts within each binary instance mask.
  • label_ids_to_fuse (Set[int], optional) — The labels in this state will have all their instances be fused together. For instance we could say there can only be one sky in an image, but several persons, so the label ID for sky would be in that set, but not the one for person.
  • target_sizes (List[Tuple], optional) — List of length (batch_size), where each list item (Tuple[int, int]]) corresponds to the requested final size (height, width) of each prediction in batch. If unset, predictions will not be resized.

Returns

List[Dict]

A list of dictionaries, one per image, each dictionary containing two keys:

  • segmentation — a tensor of shape (height, width) where each pixel represents a segment_id or None if no mask if found above threshold. If target_sizes is specified, segmentation is resized to the corresponding target_sizes entry.
  • segments_info — A dictionary that contains additional information on each segment.
    • id — an integer representing the segment_id.
    • label_id — An integer representing the label / semantic class id corresponding to segment_id.
    • was_fused — a boolean, True if label_id was in label_ids_to_fuse, False otherwise. Multiple instances of the same class / label were fused and assigned a single segment_id.
    • score — Prediction score of segment with segment_id.

Converts the output of DetrForSegmentation into image panoptic segmentation predictions. Only supports PyTorch.

DETR specific outputs

class transformers.models.detr.modeling_detr.DetrModelOutput

< >

( last_hidden_state: FloatTensor = None past_key_values: Optional = None decoder_hidden_states: Optional = None decoder_attentions: Optional = None cross_attentions: Optional = None encoder_last_hidden_state: Optional = None encoder_hidden_states: Optional = None encoder_attentions: Optional = None intermediate_hidden_states: Optional = None )

Parameters

  • last_hidden_state (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the 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, sequence_length, 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, sequence_length, sequence_length). 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_heads, sequence_length, sequence_length). 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_heads, sequence_length, sequence_length). 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 (config.decoder_layers, batch_size, sequence_length, hidden_size), optional, returned when config.auxiliary_loss=True) — Intermediate decoder activations, i.e. the output of each decoder layer, each of them gone through a layernorm.

Base class for outputs of the DETR encoder-decoder model. This class adds one attribute to Seq2SeqModelOutput, namely an optional stack of intermediate decoder activations, i.e. the output of each decoder layer, each of them gone through a layernorm. This is useful when training the model with auxiliary decoding losses.

class transformers.models.detr.modeling_detr.DetrObjectDetectionOutput

< >

( loss: Optional = None loss_dict: Optional = None logits: FloatTensor = None pred_boxes: FloatTensor = None auxiliary_outputs: Optional = None last_hidden_state: Optional = None decoder_hidden_states: Optional = None decoder_attentions: Optional = None cross_attentions: Optional = None encoder_last_hidden_state: Optional = None encoder_hidden_states: Optional = None encoder_attentions: Optional = None )

Parameters

  • 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 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, sequence_length, 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, sequence_length, 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, sequence_length, sequence_length). 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_heads, sequence_length, sequence_length). 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_heads, sequence_length, sequence_length). Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

Output type of DetrForObjectDetection.

class transformers.models.detr.modeling_detr.DetrSegmentationOutput

< >

( loss: Optional = None loss_dict: Optional = None logits: FloatTensor = None pred_boxes: FloatTensor = None pred_masks: FloatTensor = None auxiliary_outputs: Optional = None last_hidden_state: Optional = None decoder_hidden_states: Optional = None decoder_attentions: Optional = None cross_attentions: Optional = None encoder_last_hidden_state: Optional = None encoder_hidden_states: Optional = None encoder_attentions: Optional = None )

Parameters

  • 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 post_process_object_detection() to retrieve the unnormalized bounding boxes.
  • pred_masks (torch.FloatTensor of shape (batch_size, num_queries, height/4, width/4)) — Segmentation masks logits for all queries. See also post_process_semantic_segmentation() or post_process_instance_segmentation() post_process_panoptic_segmentation() to evaluate semantic, instance and panoptic segmentation masks respectively.
  • auxiliary_outputs (list[Dict], optional) — Optional, only returned when auxiliary 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, sequence_length, 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, sequence_length, 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, sequence_length, sequence_length). 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_heads, sequence_length, sequence_length). 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_heads, sequence_length, sequence_length). Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

Output type of DetrForSegmentation.

DetrModel

class transformers.DetrModel

< >

( config: DetrConfig )

Parameters

  • config (DetrConfig) — 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 DETR 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: Optional = None decoder_attention_mask: Optional = None encoder_outputs: Optional = None inputs_embeds: Optional = None decoder_inputs_embeds: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None return_dict: Optional = None ) → transformers.models.detr.modeling_detr.DetrModelOutput 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 DetrImageProcessor.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.detr.modeling_detr.DetrModelOutput or tuple(torch.FloatTensor)

A transformers.models.detr.modeling_detr.DetrModelOutput 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 (DetrConfig) and inputs.

  • last_hidden_state (torch.FloatTensor of shape (batch_size, sequence_length, hidden_size)) — Sequence of hidden-states at the output of the last layer of the 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, sequence_length, 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, sequence_length, sequence_length). 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_heads, sequence_length, sequence_length). 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_heads, sequence_length, sequence_length). 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 (config.decoder_layers, batch_size, sequence_length, hidden_size), optional, returned when config.auxiliary_loss=True) — Intermediate decoder activations, i.e. the output of each decoder layer, each of them gone through a layernorm.

The DetrModel 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, DetrModel
>>> 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("facebook/detr-resnet-50")
>>> model = DetrModel.from_pretrained("facebook/detr-resnet-50")

>>> # prepare image for the model
>>> inputs = image_processor(images=image, return_tensors="pt")

>>> # forward pass
>>> outputs = model(**inputs)

>>> # the last hidden states are the final query embeddings of the Transformer decoder
>>> # these are of shape (batch_size, num_queries, hidden_size)
>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 100, 256]

DetrForObjectDetection

class transformers.DetrForObjectDetection

< >

( config: DetrConfig )

Parameters

  • config (DetrConfig) — 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.

DETR 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: Optional = None decoder_attention_mask: Optional = None encoder_outputs: Optional = None inputs_embeds: Optional = None decoder_inputs_embeds: Optional = None labels: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None return_dict: Optional = None ) → transformers.models.detr.modeling_detr.DetrObjectDetectionOutput 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 DetrImageProcessor.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.detr.modeling_detr.DetrObjectDetectionOutput or tuple(torch.FloatTensor)

A transformers.models.detr.modeling_detr.DetrObjectDetectionOutput 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 (DetrConfig) 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 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, sequence_length, 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, sequence_length, 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, sequence_length, sequence_length). 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_heads, sequence_length, sequence_length). 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_heads, sequence_length, sequence_length). Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

The DetrForObjectDetection 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, DetrForObjectDetection
>>> import torch
>>> 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("facebook/detr-resnet-50")
>>> model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")

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

>>> # convert outputs (bounding boxes and class logits) to Pascal VOC format (xmin, ymin, xmax, ymax)
>>> target_sizes = torch.tensor([image.size[::-1]])
>>> results = image_processor.post_process_object_detection(outputs, threshold=0.9, 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 remote with confidence 0.998 at location [40.16, 70.81, 175.55, 117.98]
Detected remote with confidence 0.996 at location [333.24, 72.55, 368.33, 187.66]
Detected couch with confidence 0.995 at location [-0.02, 1.15, 639.73, 473.76]
Detected cat with confidence 0.999 at location [13.24, 52.05, 314.02, 470.93]
Detected cat with confidence 0.999 at location [345.4, 23.85, 640.37, 368.72]

DetrForSegmentation

class transformers.DetrForSegmentation

< >

( config: DetrConfig )

Parameters

  • config (DetrConfig) — 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.

DETR Model (consisting of a backbone and encoder-decoder Transformer) with a segmentation head on top, for tasks such as COCO panoptic.

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: Optional = None decoder_attention_mask: Optional = None encoder_outputs: Optional = None inputs_embeds: Optional = None decoder_inputs_embeds: Optional = None labels: Optional = None output_attentions: Optional = None output_hidden_states: Optional = None return_dict: Optional = None ) → transformers.models.detr.modeling_detr.DetrSegmentationOutput 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 DetrImageProcessor.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, DICE/F-1 loss and Focal loss. List of dicts, each dictionary containing at least the following 3 keys: ‘class_labels’, ‘boxes’ and ‘masks’ (the class labels, bounding boxes and segmentation masks 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,), the boxes a torch.FloatTensor of shape (number of bounding boxes in the image, 4) and the masks a torch.FloatTensor of shape (number of bounding boxes in the image, height, width).

Returns

transformers.models.detr.modeling_detr.DetrSegmentationOutput or tuple(torch.FloatTensor)

A transformers.models.detr.modeling_detr.DetrSegmentationOutput 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 (DetrConfig) 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 post_process_object_detection() to retrieve the unnormalized bounding boxes.
  • pred_masks (torch.FloatTensor of shape (batch_size, num_queries, height/4, width/4)) — Segmentation masks logits for all queries. See also post_process_semantic_segmentation() or post_process_instance_segmentation() post_process_panoptic_segmentation() to evaluate semantic, instance and panoptic segmentation masks respectively.
  • auxiliary_outputs (list[Dict], optional) — Optional, only returned when auxiliary 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, sequence_length, 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, sequence_length, 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, sequence_length, sequence_length). 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_heads, sequence_length, sequence_length). 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_heads, sequence_length, sequence_length). Attentions weights of the encoder, after the attention softmax, used to compute the weighted average in the self-attention heads.

The DetrForSegmentation forward method, overrides the __call__ special method.

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

Examples:

>>> import io
>>> import requests
>>> from PIL import Image
>>> import torch
>>> import numpy

>>> from transformers import AutoImageProcessor, DetrForSegmentation
>>> from transformers.image_transforms import rgb_to_id

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

>>> image_processor = AutoImageProcessor.from_pretrained("facebook/detr-resnet-50-panoptic")
>>> model = DetrForSegmentation.from_pretrained("facebook/detr-resnet-50-panoptic")

>>> # prepare image for the model
>>> inputs = image_processor(images=image, return_tensors="pt")

>>> # forward pass
>>> outputs = model(**inputs)

>>> # Use the `post_process_panoptic_segmentation` method of the `image_processor` to retrieve post-processed panoptic segmentation maps
>>> # Segmentation results are returned as a list of dictionaries
>>> result = image_processor.post_process_panoptic_segmentation(outputs, target_sizes=[(300, 500)])

>>> # A tensor of shape (height, width) where each value denotes a segment id, filled with -1 if no segment is found
>>> panoptic_seg = result[0]["segmentation"]
>>> # Get prediction score and segment_id to class_id mapping of each segment
>>> panoptic_segments_info = result[0]["segments_info"]

←DETA DiNAT→