pip install -q transformers

>>> from transformers import pipeline

>>> # Use any checkpoint from the hf.co/models?pipeline_tag=zero-shot-object-detection
>>> checkpoint = "iSEE-Laboratory/llmdet_large"
>>> detector = pipeline(model=checkpoint, task="zero-shot-object-detection")

>>> from transformers.image_utils import load_image

>>> url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/zero-sh-obj-detection_1.png"
>>> image = load_image(url)
>>> image

>>> predictions = detector(
...     image,
...     candidate_labels=["human face", "rocket", "nasa badge", "star-spangled banner"],
...     threshold=0.45,
... )
>>> predictions
[{'score': 0.8409242033958435,
  'label': 'human face',
  'box': {'xmin': 179, 'ymin': 74, 'xmax': 272, 'ymax': 179}},
 {'score': 0.7380027770996094,
  'label': 'rocket',
  'box': {'xmin': 353, 'ymin': 0, 'xmax': 466, 'ymax': 284}},
 {'score': 0.5850900411605835,
  'label': 'star-spangled banner',
  'box': {'xmin': 0, 'ymin': 0, 'xmax': 96, 'ymax': 511}},
 {'score': 0.5697067975997925,
  'label': 'human face',
  'box': {'xmin': 18, 'ymin': 15, 'xmax': 366, 'ymax': 511}},
 {'score': 0.47813931107521057,
  'label': 'star-spangled banner',
  'box': {'xmin': 353, 'ymin': 0, 'xmax': 459, 'ymax': 274}},
 {'score': 0.46597740054130554,
  'label': 'nasa badge',
  'box': {'xmin': 353, 'ymin': 0, 'xmax': 462, 'ymax': 279}},
 {'score': 0.4585932493209839,
  'label': 'nasa badge',
  'box': {'xmin': 132, 'ymin': 348, 'xmax': 208, 'ymax': 423}}]

>>> from PIL import ImageDraw

>>> draw = ImageDraw.Draw(image)

>>> for prediction in predictions:
...     box = prediction["box"]
...     label = prediction["label"]
...     score = prediction["score"]

...     xmin, ymin, xmax, ymax = box.values()
...     draw.rectangle((xmin, ymin, xmax, ymax), outline="red", width=1)
...     draw.text((xmin, ymin), f"{label}: {round(score,2)}", fill="white")

>>> image

>>> from transformers import AutoProcessor, AutoModelForZeroShotObjectDetection

>>> model = AutoModelForZeroShotObjectDetection.from_pretrained(checkpoint, device_map="auto")
>>> processor = AutoProcessor.from_pretrained(checkpoint)

>>> url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/zero-sh-obj-detection_3.png"
>>> image = load_image(url)
>>> image

>>> text_labels = ["hat", "book", "sunglasses", "camera"]
>>> inputs = processor(text=text_labels, images=image, return_tensors="pt").to(model.device)

>>> import torch

>>> with torch.inference_mode():
...     outputs = model(**inputs)

>>> results = processor.post_process_grounded_object_detection(
...    outputs, threshold=0.50, target_sizes=[(image.height, image.width)], text_labels=text_labels,
... )[0]

>>> draw = ImageDraw.Draw(image)

>>> scores = results["scores"]
>>> text_labels = results["text_labels"]
>>> boxes = results["boxes"]

>>> for box, score, text_label in zip(boxes, scores, text_labels):
...     xmin, ymin, xmax, ymax = box
...     draw.rectangle((xmin, ymin, xmax, ymax), outline="red", width=1)
...     draw.text((xmin, ymin), f"{text_label}: {round(score.item(),2)}", fill="white")

>>> image

>>> url1 = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/zero-sh-obj-detection_1.png"
>>> url2 = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/zero-sh-obj-detection_3.png"
>>> images = [load_image(url1), load_image(url2)]
>>> text_queries = [
...     ["human face", "rocket", "nasa badge", "star-spangled banner"],
...     ["hat", "book", "sunglasses", "camera", "can"],
... ]
>>> inputs = processor(text=text_queries, images=images, return_tensors="pt", padding=True)

>>> with torch.no_grad():
>>>     outputs = model(**inputs)

>>> target_sizes = [(image.height, image.width) for image in images]
>>> results = processor.post_process_grounded_object_detection(
...     outputs, threshold=0.3, target_sizes=target_sizes, text_labels=text_labels,
... )

>>> image_idx = 1
>>> draw = ImageDraw.Draw(images[image_idx])

>>> scores = results[image_idx]["scores"].tolist()
>>> text_labels = results[image_idx]["text_labels"]
>>> boxes = results[image_idx]["boxes"].tolist()

>>> for box, score, text_label in zip(boxes, scores, text_labels):
>>>     xmin, ymin, xmax, ymax = box
>>>     draw.rectangle((xmin, ymin, xmax, ymax), outline="red", width=1)
>>>     draw.text((xmin, ymin), f"{text_label}: {round(score,2)}", fill="white")

>>> images[image_idx]

>>> from transformers import AutoProcessor, AutoModelForZeroShotObjectDetection

>>> checkpoint = "google/owlv2-base-patch16-ensemble"
>>> model = AutoModelForZeroShotObjectDetection.from_pretrained(checkpoint, device_map="auto")
>>> processor = AutoProcessor.from_pretrained(checkpoint)

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

>>> query_url = "http://images.cocodataset.org/val2017/000000524280.jpg"
>>> query_image = Image.open(requests.get(query_url, stream=True).raw)

>>> import matplotlib.pyplot as plt

>>> fig, ax = plt.subplots(1, 2)
>>> ax[0].imshow(image_target)
>>> ax[1].imshow(query_image)
>>> fig.show()

>>> inputs = processor(images=image_target, query_images=query_image, return_tensors="pt")

>>> with torch.no_grad():
...     outputs = model.image_guided_detection(**inputs)
...     target_sizes = torch.tensor([image_target.size[::-1]])
...     results = processor.post_process_image_guided_detection(outputs=outputs, target_sizes=target_sizes)[0]

>>> draw = ImageDraw.Draw(image_target)

>>> scores = results["scores"].tolist()
>>> boxes = results["boxes"].tolist()

>>> for box, score in zip(boxes, scores):
...     xmin, ymin, xmax, ymax = box
...     draw.rectangle((xmin, ymin, xmax, ymax), outline="white", width=4)

>>> image_target