mirror of
https://www.modelscope.cn/AI-ModelScope/Florence-2-large.git
synced 2026-04-02 13:42:53 +08:00
initial tuned 4k context length model (#84)
- add 4k context length model (43013a8f5eccffac1f83ec7d00e94b9ecb218380) Co-authored-by: Haiping Wu <haipingwu@users.noreply.huggingface.co>
This commit is contained in:
ai-modelscope
95
README.md
95
README.md
@ -1,8 +1,7 @@
|
||||
---
|
||||
license: mit
|
||||
license_link: https://huggingface.co/microsoft/Florence-2-large/resolve/main/LICENSE
|
||||
|
||||
pipeline_tag: image-to-text
|
||||
pipeline_tag: image-text-to-text
|
||||
tags:
|
||||
- vision
|
||||
---
|
||||
@ -11,6 +10,8 @@ tags:
|
||||
|
||||
## Model Summary
|
||||
|
||||
**This is a continued pretrained version of Florence-2-large model with 4k context length, only 0.1B samples are used for continue pretraining, thus it might not be trained well. In addition, OCR task has been updated with line separator ('\n'). COCO OD AP 39.8**
|
||||
|
||||
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.
|
||||
@ -28,16 +29,20 @@ Resources and Technical Documentation:
|
||||
|
||||
## How to Get Started with the Model
|
||||
|
||||
Use the code below to get started with the model.
|
||||
Use the code below to get started with the model. All models are trained with float16.
|
||||
|
||||
```python
|
||||
import requests
|
||||
|
||||
import torch
|
||||
from PIL import Image
|
||||
from transformers import AutoProcessor, AutoModelForCausalLM
|
||||
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-large", trust_remote_code=True)
|
||||
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>"
|
||||
@ -45,12 +50,12 @@ 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")
|
||||
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,
|
||||
max_new_tokens=4096,
|
||||
num_beams=3,
|
||||
do_sample=False
|
||||
)
|
||||
@ -75,34 +80,36 @@ First, let's define a function to run a prompt.
|
||||
```python
|
||||
import requests
|
||||
|
||||
import torch
|
||||
from PIL import Image
|
||||
from transformers import AutoProcessor, AutoModelForCausalLM
|
||||
from modelscope import snapshot_download
|
||||
|
||||
model_dir = snapshot_download("AI-ModelScope/Florence-2-large")
|
||||
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(model_dir, trust_remote_code=True)
|
||||
processor = AutoProcessor.from_pretrained(model_dir, trust_remote_code=True)
|
||||
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://modelscope.oss-cn-beijing.aliyuncs.com/resource/car.jpg"
|
||||
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")
|
||||
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]
|
||||
|
||||
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=task_prompt, image_size=(image.width, image.height))
|
||||
|
||||
parsed_answer = processor.post_process_generation(generated_text, task="<OD>", image_size=(image.width, image.height))
|
||||
|
||||
print(parsed_answer)
|
||||
print(parsed_answer)
|
||||
```
|
||||
</details>
|
||||
|
||||
@ -185,6 +192,44 @@ prompt = "<OCR_WITH_REGION>"
|
||||
run_example(prompt)
|
||||
```
|
||||
|
||||
### Output confidence score with Object Detection
|
||||
```python
|
||||
|
||||
def run_example_with_score(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,
|
||||
return_dict_in_generate=True,
|
||||
output_scores=True,
|
||||
)
|
||||
generated_text = processor.batch_decode(generated_ids.sequences, skip_special_tokens=False)[0]
|
||||
|
||||
prediction, scores, beam_indices = generated_ids.sequences, generated_ids.scores, generated_ids.beam_indices
|
||||
transition_beam_scores = model.compute_transition_scores(
|
||||
sequences=prediction,
|
||||
scores=scores,
|
||||
beam_indices=beam_indices,
|
||||
)
|
||||
|
||||
parsed_answer = processor.post_process_generation(sequence=generated_ids.sequences[0],
|
||||
transition_beam_score=transition_beam_scores[0],
|
||||
task=task_prompt, image_size=(image.width, image.height)
|
||||
)
|
||||
|
||||
print(parsed_answer)
|
||||
|
||||
prompt = "<OD>"
|
||||
run_example_with_score(prompt)
|
||||
|
||||
```
|
||||
|
||||
for More detailed examples, please refer to [notebook](https://huggingface.co/microsoft/Florence-2-large/blob/main/sample_inference.ipynb)
|
||||
</details>
|
||||
|
||||
|
||||
Reference in New Issue
Block a user