import requests

from PIL import Image
from transformers import AutoProcessor, AutoModelForCausalLM 

model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-large-ft", trust_remote_code=True)
processor = AutoProcessor.from_pretrained("microsoft/Florence-2-large-ft", trust_remote_code=True)

url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
image = Image.open(requests.get(url, stream=True).raw)

def run_example(task_prompt, text_input=None):
    if text_input is None:
        prompt = task_prompt
    else:
        prompt = task_prompt + text_input
    inputs = processor(text=prompt, images=image, return_tensors="pt")
    generated_ids = model.generate(
      input_ids=inputs["input_ids"],
      pixel_values=inputs["pixel_values"],
      max_new_tokens=1024,
      num_beams=3
    )
    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]

    parsed_answer = processor.post_process_generation(generated_text, task=task_prompt, image_size=(image.width, image.height))

    print(parsed_answer)

图像描述

prompt = "<CAPTION>"
run_example(prompt)

详细图像描述

prompt = "<DETAILED_CAPTION>"
run_example(prompt)

更详细图像描述

prompt = "<MORE_DETAILED_CAPTION>"
run_example(prompt)

图像描述到短语定位

图像描述到短语定位任务需要额外的文本输入，即图像描述。 图像描述到短语定位结果格式： {'<CAPTION_TO_PHRASE_GROUNDING>': {'bboxes': [[x1, y1, x2, y2], ...], 'labels': ['', '', ...]}}

task_prompt = "<CAPTION_TO_PHRASE_GROUNDING>"
results = run_example(task_prompt, text_input="A green car parked in front of a yellow building.")

目标检测

目标检测结果格式： {'': {'bboxes': [[x1, y1, x2, y2], ...], 'labels': ['label1', 'label2', ...]} }

prompt = "<OD>"
run_example(prompt)

密集区域描述

密集区域描述结果格式： {'<DENSE_REGION_CAPTION>' : {'bboxes': [[x1, y1, x2, y2], ...], 'labels': ['label1', 'label2', ...]} }

prompt = "<DENSE_REGION_CAPTION>"
run_example(prompt)

区域提议

密集区域描述结果格式： {'<REGION_PROPOSAL>': {'bboxes': [[x1, y1, x2, y2], ...], 'labels': ['', '', ...]}}

prompt = "<REGION_PROPOSAL>"
run_example(prompt)

OCR

prompt = "<OCR>"
run_example(prompt)

带区域的 OCR

带区域的 OCR 输出格式： {'<OCR_WITH_REGION>': {'quad_boxes': [[x1, y1, x2, y2, x3, y3, x4, y4], ...], 'labels': ['text1', ...]}}

prompt = "<OCR_WITH_REGION>"
run_example(prompt)

更多详细示例，请参考 notebook