license: mit license_link: https://huggingface.co/microsoft/Florence-2-large/resolve/main/LICENSE pipeline_tag: image-text-to-text tags:

• vision

Florence-2 (without flash-attn): Advancing a Unified Representation for a Variety of Vision Tasks

⚠️ This is a modified version of Florence 2 that modifies the custom modeling_florence2.py file to remove the need for installing flash-attn package (by hijacking the flash-attn methods and replacing with regular attention). It probably has impact in performance.

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

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

import torch
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-large", torch_dtype=torch_dtype, trust_remote_code=True).to(device)
processor = AutoProcessor.from_pretrained("microsoft/Florence-2-large", trust_remote_code=True)

prompt = "<OD>"

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,
    num_beams=3,
    do_sample=False
)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]

parsed_answer = processor.post_process_generation(generated_text, task="<OD>", 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

import torch
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-large", torch_dtype=torch_dtype, trust_remote_code=True).to(device)
processor = AutoProcessor.from_pretrained("microsoft/Florence-2-large", 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:

prompt = "<CAPTION>"
run_example(prompt)

prompt = "<DETAILED_CAPTION>"
run_example(prompt)

prompt = "<MORE_DETAILED_CAPTION>"
run_example(prompt)

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

prompt = "<OD>"
run_example(prompt)

prompt = "<DENSE_REGION_CAPTION>"
run_example(prompt)

prompt = "<REGION_PROPOSAL>"
run_example(prompt)

prompt = "<OCR>"
run_example(prompt)

prompt = "<OCR_WITH_REGION>"
run_example(prompt)

Benchmarks

Florence-2 Zero-shot performance

The following table presents the zero-shot performance of generalist vision foundation models on image captioning and object detection evaluation tasks. These models have not been exposed to the training data of the evaluation tasks during their training phase.

The following table continues the comparison with performance on other vision-language evaluation tasks.

Florence-2 finetuned performance

We finetune Florence-2 models with a collection of downstream tasks, resulting two generalist models Florence-2-base-ft and Florence-2-large-ft that can conduct a wide range of downstream tasks.

The table below compares the performance of specialist and generalist models on various captioning and Visual Question Answering (VQA) tasks. Specialist models are fine-tuned specifically for each task, whereas generalist models are fine-tuned in a task-agnostic manner across all tasks. The symbol "▲" indicates the usage of external OCR as input.

BibTex and citation info

@article{xiao2023florence,
  title={Florence-2: Advancing a unified representation for a variety of vision tasks},
  author={Xiao, Bin and Wu, Haiping and Xu, Weijian and Dai, Xiyang and Hu, Houdong and Lu, Yumao and Zeng, Michael and Liu, Ce and Yuan, Lu},
  journal={arXiv preprint arXiv:2311.06242},
  year={2023}
}