pip install -q datasets transformers accelerate timm
pip install -q -U albumentations>=1.4.5 torchmetrics pycocotools

>>> from huggingface_hub import notebook_login

>>> notebook_login()

>>> MODEL_NAME = "microsoft/conditional-detr-resnet-50"  # or "facebook/detr-resnet-50"
>>> IMAGE_SIZE = 480

>>> from datasets import load_dataset

>>> cppe5 = load_dataset("cppe-5")

>>> if "validation" not in cppe5:
...     split = cppe5["train"].train_test_split(0.15, seed=1337)
...     cppe5["train"] = split["train"]
...     cppe5["validation"] = split["test"]

>>> cppe5
DatasetDict({
    train: Dataset({
        features: ['image_id', 'image', 'width', 'height', 'objects'],
        num_rows: 850
    })
    test: Dataset({
        features: ['image_id', 'image', 'width', 'height', 'objects'],
        num_rows: 29
    })
    validation: Dataset({
        features: ['image_id', 'image', 'width', 'height', 'objects'],
        num_rows: 150
    })
})

>>> cppe5["train"][0]
{
  'image_id': 366,
  'image': <PIL.PngImagePlugin.PngImageFile image mode=RGBA size=500x290>,
  'width': 500,
  'height': 500,
  'objects': {
    'id': [1932, 1933, 1934],
    'area': [27063, 34200, 32431],
    'bbox': [[29.0, 11.0, 97.0, 279.0],
      [201.0, 1.0, 120.0, 285.0],
      [382.0, 0.0, 113.0, 287.0]],
    'category': [0, 0, 0]
  }
}

>>> import numpy as np
>>> import os
>>> from PIL import Image, ImageDraw

>>> image = cppe5["train"][2]["image"]
>>> annotations = cppe5["train"][2]["objects"]
>>> draw = ImageDraw.Draw(image)

>>> categories = cppe5["train"].features["objects"].feature["category"].names

>>> id2label = {index: x for index, x in enumerate(categories, start=0)}
>>> label2id = {v: k for k, v in id2label.items()}

>>> for i in range(len(annotations["id"])):
...     box = annotations["bbox"][i]
...     class_idx = annotations["category"][i]
...     x, y, w, h = tuple(box)
...     # Check if coordinates are normalized or not
...     if max(box) > 1.0:
...         # Coordinates are un-normalized, no need to re-scale them
...         x1, y1 = int(x), int(y)
...         x2, y2 = int(x + w), int(y + h)
...     else:
...         # Coordinates are normalized, re-scale them
...         x1 = int(x * width)
...         y1 = int(y * height)
...         x2 = int((x + w) * width)
...         y2 = int((y + h) * height)
...     draw.rectangle((x, y, x + w, y + h), outline="red", width=1)
...     draw.text((x, y), id2label[class_idx], fill="white")

>>> image

>>> from transformers import AutoImageProcessor

>>> image_processor = AutoImageProcessor.from_pretrained(
...     MODEL_NAME,
...     # At this moment we recommend using external transform to pad and resize images.
...     # It`s faster and yields better results for object-detection models.
...     do_pad=False,
...     do_resize=False,
... )

>>> import albumentations as A

>>> max_size = IMAGE_SIZE

>>> # Resize image longest edge to 480 and then pad image to square 480x480.
>>> # This padding and resizing strategy give better results, see
>>> # https://github.com/huggingface/transformers/pull/30422#discussion_r1584647408
>>> basic_transforms = [
...     A.LongestMaxSize(max_size=max_size),
...     A.PadIfNeeded(max_size, max_size, border_mode=0, value=(128, 128, 128), position="top_left"),
... ]

>>> train_augment_and_transform = A.Compose(
...     [
...         A.Perspective(p=0.1),
...         A.HorizontalFlip(p=0.5),
...         A.RandomBrightnessContrast(p=0.5),
...         A.HueSaturationValue(p=0.1),
...         *basic_transforms,
...     ],
...     bbox_params=A.BboxParams(format="coco", label_fields=["category"], clip=True, min_area=25),
... )

>>> validation_transform = A.Compose(
...     basic_transforms,
...     bbox_params=A.BboxParams(format="coco", label_fields=["category"], clip=True),
... )

>>> def format_image_annotations_as_coco(image_id, categories, areas, bboxes):
...     """Format one set of image annotations to the COCO format

...     Args:
...         image_id (str): image id. e.g. "0001"
...         categories (List[int]): list of categories/class labels corresponding to provided bounding boxes
...         areas (List[float]): list of corresponding areas to provided bounding boxes
...         bboxes (List[Tuple[float]]): list of bounding boxes provided in COCO format
...             ([center_x, center_y, width, height] in absolute coordinates)

...     Returns:
...         dict: {
...             "image_id": image id,
...             "annotations": list of formatted annotations
...         }
...     """
...     annotations = []
...     for category, area, bbox in zip(categories, areas, bboxes):
...         formatted_annotation = {
...             "image_id": image_id,
...             "category_id": category,
...             "iscrowd": 0,
...             "area": area,
...             "bbox": list(bbox),
...         }
...         annotations.append(formatted_annotation)

...     return {
...         "image_id": image_id,
...         "annotations": annotations,
...     }

>>> def augment_and_transform_batch(examples, transform, image_processor):
...     """Apply augmentations and format annotations in COCO format for object detection task"""

...     images = []
...     annotations = []
...     for image_id, image, objects in zip(examples["image_id"], examples["image"], examples["objects"]):
...         image = np.array(image.convert("RGB"))

...         # apply augmentations
...         output = transform(image=image, bboxes=objects["bbox"], category=objects["category"])
...         images.append(output["image"])

...         # format annotations in COCO format
...         formatted_annotations = format_image_annotations_as_coco(
...             image_id, output["category"], objects["area"], output["bboxes"]
...         )
...         annotations.append(formatted_annotations)

...     # Apply the image processor transformations: resizing, rescaling, normalization
...     result = image_processor(images=images, annotations=annotations, return_tensors="pt")

...     return result

>>> from functools import partial

>>> # Make transform functions for batch and apply for dataset splits
>>> train_transform_batch = partial(
...     augment_and_transform_batch, transform=train_augment_and_transform, image_processor=image_processor
... )
>>> validation_transform_batch = partial(
...     augment_and_transform_batch, transform=validation_transform, image_processor=image_processor
... )

>>> cppe5["train"] = cppe5["train"].with_transform(train_transform_batch)
>>> cppe5["validation"] = cppe5["validation"].with_transform(validation_transform_batch)
>>> cppe5["test"] = cppe5["test"].with_transform(validation_transform_batch)

>>> cppe5["train"][15]
{'pixel_values': tensor([[[ 1.9235,  1.9407,  1.9749,  ..., -0.7822, -0.7479, -0.6965],
          [ 1.9578,  1.9749,  1.9920,  ..., -0.7993, -0.7650, -0.7308],
          [ 2.0092,  2.0092,  2.0263,  ..., -0.8507, -0.8164, -0.7822],
          ...,
          [ 0.0741,  0.0741,  0.0741,  ...,  0.0741,  0.0741,  0.0741],
          [ 0.0741,  0.0741,  0.0741,  ...,  0.0741,  0.0741,  0.0741],
          [ 0.0741,  0.0741,  0.0741,  ...,  0.0741,  0.0741,  0.0741]],
  
          [[ 1.6232,  1.6408,  1.6583,  ...,  0.8704,  1.0105,  1.1331],
          [ 1.6408,  1.6583,  1.6758,  ...,  0.8529,  0.9930,  1.0980],
          [ 1.6933,  1.6933,  1.7108,  ...,  0.8179,  0.9580,  1.0630],
          ...,
          [ 0.2052,  0.2052,  0.2052,  ...,  0.2052,  0.2052,  0.2052],
          [ 0.2052,  0.2052,  0.2052,  ...,  0.2052,  0.2052,  0.2052],
          [ 0.2052,  0.2052,  0.2052,  ...,  0.2052,  0.2052,  0.2052]],
  
          [[ 1.8905,  1.9080,  1.9428,  ..., -0.1487, -0.0964, -0.0615],
          [ 1.9254,  1.9428,  1.9603,  ..., -0.1661, -0.1138, -0.0790],
          [ 1.9777,  1.9777,  1.9951,  ..., -0.2010, -0.1138, -0.0790],
          ...,
          [ 0.4265,  0.4265,  0.4265,  ...,  0.4265,  0.4265,  0.4265],
          [ 0.4265,  0.4265,  0.4265,  ...,  0.4265,  0.4265,  0.4265],
          [ 0.4265,  0.4265,  0.4265,  ...,  0.4265,  0.4265,  0.4265]]]),
  'labels': {'image_id': tensor([688]), 'class_labels': tensor([3, 4, 2, 0, 0]), 'boxes': tensor([[0.4700, 0.1933, 0.1467, 0.0767],
          [0.4858, 0.2600, 0.1150, 0.1000],
          [0.4042, 0.4517, 0.1217, 0.1300],
          [0.4242, 0.3217, 0.3617, 0.5567],
          [0.6617, 0.4033, 0.5400, 0.4533]]), 'area': tensor([ 4048.,  4140.,  5694., 72478., 88128.]), 'iscrowd': tensor([0, 0, 0, 0, 0]), 'orig_size': tensor([480, 480])}}

>>> import torch

>>> def collate_fn(batch):
...     data = {}
...     data["pixel_values"] = torch.stack([x["pixel_values"] for x in batch])
...     data["labels"] = [x["labels"] for x in batch]
...     if "pixel_mask" in batch[0]:
...         data["pixel_mask"] = torch.stack([x["pixel_mask"] for x in batch])
...     return data

>>> from transformers.image_transforms import center_to_corners_format

>>> def convert_bbox_yolo_to_pascal(boxes, image_size):
...     """
...     Convert bounding boxes from YOLO format (x_center, y_center, width, height) in range [0, 1]
...     to Pascal VOC format (x_min, y_min, x_max, y_max) in absolute coordinates.

...     Args:
...         boxes (torch.Tensor): Bounding boxes in YOLO format
...         image_size (Tuple[int, int]): Image size in format (height, width)

...     Returns:
...         torch.Tensor: Bounding boxes in Pascal VOC format (x_min, y_min, x_max, y_max)
...     """
...     # convert center to corners format
...     boxes = center_to_corners_format(boxes)

...     # convert to absolute coordinates
...     height, width = image_size
...     boxes = boxes * torch.tensor([[width, height, width, height]])

...     return boxes

>>> import numpy as np
>>> from dataclasses import dataclass
>>> from torchmetrics.detection.mean_ap import MeanAveragePrecision


>>> @dataclass
>>> class ModelOutput:
...     logits: torch.Tensor
...     pred_boxes: torch.Tensor


>>> @torch.no_grad()
>>> def compute_metrics(evaluation_results, image_processor, threshold=0.0, id2label=None):
...     """
...     Compute mean average mAP, mAR and their variants for the object detection task.

...     Args:
...         evaluation_results (EvalPrediction): Predictions and targets from evaluation.
...         threshold (float, optional): Threshold to filter predicted boxes by confidence. Defaults to 0.0.
...         id2label (Optional[dict], optional): Mapping from class id to class name. Defaults to None.

...     Returns:
...         Mapping[str, float]: Metrics in a form of dictionary {<metric_name>: <metric_value>}
...     """

...     predictions, targets = evaluation_results.predictions, evaluation_results.label_ids

...     # For metric computation we need to provide:
...     #  - targets in a form of list of dictionaries with keys "boxes", "labels"
...     #  - predictions in a form of list of dictionaries with keys "boxes", "scores", "labels"

...     image_sizes = []
...     post_processed_targets = []
...     post_processed_predictions = []

...     # Collect targets in the required format for metric computation
...     for batch in targets:
...         # collect image sizes, we will need them for predictions post processing
...         batch_image_sizes = torch.tensor(np.array([x["orig_size"] for x in batch]))
...         image_sizes.append(batch_image_sizes)
...         # collect targets in the required format for metric computation
...         # boxes were converted to YOLO format needed for model training
...         # here we will convert them to Pascal VOC format (x_min, y_min, x_max, y_max)
...         for image_target in batch:
...             boxes = torch.tensor(image_target["boxes"])
...             boxes = convert_bbox_yolo_to_pascal(boxes, image_target["orig_size"])
...             labels = torch.tensor(image_target["class_labels"])
...             post_processed_targets.append({"boxes": boxes, "labels": labels})

...     # Collect predictions in the required format for metric computation,
...     # model produce boxes in YOLO format, then image_processor convert them to Pascal VOC format
...     for batch, target_sizes in zip(predictions, image_sizes):
...         batch_logits, batch_boxes = batch[1], batch[2]
...         output = ModelOutput(logits=torch.tensor(batch_logits), pred_boxes=torch.tensor(batch_boxes))
...         post_processed_output = image_processor.post_process_object_detection(
...             output, threshold=threshold, target_sizes=target_sizes
...         )
...         post_processed_predictions.extend(post_processed_output)

...     # Compute metrics
...     metric = MeanAveragePrecision(box_format="xyxy", class_metrics=True)
...     metric.update(post_processed_predictions, post_processed_targets)
...     metrics = metric.compute()

...     # Replace list of per class metrics with separate metric for each class
...     classes = metrics.pop("classes")
...     map_per_class = metrics.pop("map_per_class")
...     mar_100_per_class = metrics.pop("mar_100_per_class")
...     for class_id, class_map, class_mar in zip(classes, map_per_class, mar_100_per_class):
...         class_name = id2label[class_id.item()] if id2label is not None else class_id.item()
...         metrics[f"map_{class_name}"] = class_map
...         metrics[f"mar_100_{class_name}"] = class_mar

...     metrics = {k: round(v.item(), 4) for k, v in metrics.items()}

...     return metrics


>>> eval_compute_metrics_fn = partial(
...     compute_metrics, image_processor=image_processor, id2label=id2label, threshold=0.0
... )

>>> from transformers import AutoModelForObjectDetection

>>> model = AutoModelForObjectDetection.from_pretrained(
...     MODEL_NAME,
...     id2label=id2label,
...     label2id=label2id,
...     ignore_mismatched_sizes=True,
... )

>>> from transformers import TrainingArguments

>>> training_args = TrainingArguments(
...     output_dir="detr_finetuned_cppe5",
...     num_train_epochs=30,
...     fp16=False,
...     per_device_train_batch_size=8,
...     dataloader_num_workers=4,
...     learning_rate=5e-5,
...     lr_scheduler_type="cosine",
...     weight_decay=1e-4,
...     max_grad_norm=0.01,
...     metric_for_best_model="eval_map",
...     greater_is_better=True,
...     load_best_model_at_end=True,
...     eval_strategy="epoch",
...     save_strategy="epoch",
...     save_total_limit=2,
...     remove_unused_columns=False,
...     eval_do_concat_batches=False,
...     push_to_hub=True,
... )

>>> from transformers import Trainer

>>> trainer = Trainer(
...     model=model,
...     args=training_args,
...     train_dataset=cppe5["train"],
...     eval_dataset=cppe5["validation"],
...     tokenizer=image_processor,
...     data_collator=collate_fn,
...     compute_metrics=eval_compute_metrics_fn,
... )

>>> trainer.train()

>>> trainer.push_to_hub()

>>> from pprint import pprint

>>> metrics = trainer.evaluate(eval_dataset=cppe5["test"], metric_key_prefix="test")
>>> pprint(metrics)
{'epoch': 30.0,
  'test_loss': 1.0877351760864258,
  'test_map': 0.4116,
  'test_map_50': 0.741,
  'test_map_75': 0.3663,
  'test_map_Coverall': 0.5937,
  'test_map_Face_Shield': 0.5863,
  'test_map_Gloves': 0.3416,
  'test_map_Goggles': 0.1468,
  'test_map_Mask': 0.3894,
  'test_map_large': 0.5637,
  'test_map_medium': 0.3257,
  'test_map_small': 0.3589,
  'test_mar_1': 0.323,
  'test_mar_10': 0.5237,
  'test_mar_100': 0.5587,
  'test_mar_100_Coverall': 0.6756,
  'test_mar_100_Face_Shield': 0.7294,
  'test_mar_100_Gloves': 0.4721,
  'test_mar_100_Goggles': 0.4125,
  'test_mar_100_Mask': 0.5038,
  'test_mar_large': 0.7283,
  'test_mar_medium': 0.4901,
  'test_mar_small': 0.4469,
  'test_runtime': 1.6526,
  'test_samples_per_second': 17.548,
  'test_steps_per_second': 2.42}

>>> import torch
>>> import requests
>>> import numpy as np
>>> import albumentations as A

>>> from PIL import Image
>>> from transformers import AutoImageProcessor, AutoModelForObjectDetection

>>> url = "https://images.pexels.com/photos/8413299/pexels-photo-8413299.jpeg?auto=compress&cs=tinysrgb&w=630&h=375&dpr=2"
>>> image = Image.open(requests.get(url, stream=True).raw)

>>> # Define transformations for inference
>>> resize_and_pad = A.Compose([
...     A.LongestMaxSize(max_size=max_size),
...     A.PadIfNeeded(max_size, max_size, border_mode=0, value=(128, 128, 128), position="top_left"),
... ])

>>> # This one is for visualization with no padding
>>> resize_only = A.Compose([
...     A.LongestMaxSize(max_size=max_size),
... ])

>>> device = "cuda"
>>> model_repo = "qubvel-hf/detr_finetuned_cppe5"

>>> image_processor = AutoImageProcessor.from_pretrained(model_repo)
>>> model = AutoModelForObjectDetection.from_pretrained(model_repo)
>>> model = model.to(device)

>>> np_preprocessed_image = resize_and_pad(image=np.array(image))["image"]

>>> with torch.no_grad():
...     inputs = image_processor(images=[np_preprocessed_image], return_tensors="pt")
...     outputs = model(inputs["pixel_values"].to(device))
...     target_sizes = torch.tensor([np_preprocessed_image.shape[:2]])
...     results = image_processor.post_process_object_detection(outputs, threshold=0.3, 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 Gloves with confidence 0.683 at location [244.58, 124.33, 300.35, 185.13]
Detected Mask with confidence 0.517 at location [143.73, 64.58, 219.57, 125.89]
Detected Gloves with confidence 0.425 at location [179.15, 155.57, 262.4, 226.35]
Detected Coverall with confidence 0.407 at location [307.13, -1.18, 477.82, 318.06]
Detected Coverall with confidence 0.391 at location [68.61, 126.66, 309.03, 318.89]

>>> resized_image = resize_only(image=np.array(image))["image"]
>>> resized_image = Image.fromarray(resized_image)
>>> draw = ImageDraw.Draw(resized_image)

>>> for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
...     box = [round(i, 2) for i in box.tolist()]
...     x, y, x2, y2 = tuple(box)
...     draw.rectangle((x, y, x2, y2), outline="red", width=1)
...     draw.text((x, y), model.config.id2label[label.item()], fill="white")

>>> resized_image