Florence-2

Model Summary

This Hub repository contains a HuggingFace's transformers implementation of Florence-2 model from Microsoft.

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks. Florence-2 can interpret simple text prompts to perform tasks like captioning, object detection, and segmentation. It leverages our FLD-5B dataset, containing 5.4 billion annotations across 126 million images, to master multi-task learning. The model's sequence-to-sequence architecture enables it to excel in both zero-shot and fine-tuned settings, proving to be a competitive vision foundation model.

Resources and Technical Documentation:

• Florence-2 technical report.
• Jupyter Notebook for inference and visualization of Florence-2-large model

How to Get Started with the Model

Use the code below to get started with the model. All models are trained with float16.

import requests

from PIL import Image
from transformers import AutoProcessor, AutoModelForCausalLM

device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-base", torch_dtype=torch_dtype, trust_remote_code=True).to(device)
processor = AutoProcessor.from_pretrained("microsoft/Florence-2-base", trust_remote_code=True)

prompt = ""

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)

inputs = processor(text=prompt, images=image, return_tensors="pt").to(device, torch_dtype)

generated_ids = model.generate(
    input_ids=inputs["input_ids"],
    pixel_values=inputs["pixel_values"],
    max_new_tokens=1024,
    do_sample=False,
    num_beams=3,
)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]

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

print(parsed_answer)

Tasks

This model is capable of performing different tasks through changing the prompts.

First, let's define a function to run a prompt.

import requests

from PIL import Image
from transformers import AutoProcessor, AutoModelForCausalLM

device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-base", torch_dtype=torch_dtype, trust_remote_code=True).to(device)
processor = AutoProcessor.from_pretrained("microsoft/Florence-2-base", 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").to(device, torch_dtype)
    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)

Here are the tasks Florence-2 could perform:

Caption

prompt = ""
run_example(prompt)

Detailed Caption

prompt = ""
run_example(prompt)

More Detailed Caption

prompt = ""
run_example(prompt)

Caption to Phrase Grounding

caption to phrase grounding task requires additional text input, i.e. caption.

Caption to phrase grounding results format: {'': {'bboxes': [[x1, y1, x2, y2], ...], 'labels': ['', '', ...]}}

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

Object Detection

OD results format: {'': {'bboxes': [[x1, y1, x2, y2], ...], 'labels': ['label1', 'label2', ...]} }

prompt = ""
run_example(prompt)

Dense Region Caption

Dense region caption results format: {'' : {'bboxes': [[x1, y1, x2, y2], ...], 'labels': ['label1', 'label2', ...]} }

prompt = ""
run_example(prompt)

Region proposal

Dense region caption results format: {'': {'bboxes': [[x1, y1, x2, y2], ...], 'labels': ['', '', ...]}}

prompt = ""
run_example(prompt)

OCR

prompt = ""
run_example(prompt)

OCR with Region

OCR with region output format: {'': {'quad_boxes': [[x1, y1, x2, y2, x3, y3, x4, y4], ...], 'labels': ['text1', ...]}}

prompt = ""
run_example(prompt)

for More detailed examples, please refer to notebook

Benchmarks

Florence-2 Zero-shot performance

The following table presents the zero-shot performance of generalist vision foundation models on image captioning