ai-models/Florence-2-large
2
0
Fork 0
mirror of https://www.modelscope.cn/AI-ModelScope/Florence-2-large.git synced 2026-04-02 21:52:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Cherrytest
2024-06-29 00:59:04 +00:00
parent bdfe4cb6aa
commit 92117d39db
1 changed files with 19 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
README.md
View File

@ -77,31 +77,32 @@ import requests
from PIL import Image from PIL import Image
from transformers import AutoProcessor, AutoModelForCausalLM from transformers import AutoProcessor, AutoModelForCausalLM
from modelscope import snapshot_download
model_dir = snapshot_download("AI-ModelScope/Florence-2-large")
model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-large", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained(model_dir, trust_remote_code=True)
processor = AutoProcessor.from_pretrained("microsoft/Florence-2-large", trust_remote_code=True) processor = AutoProcessor.from_pretrained(model_dir, trust_remote_code=True)
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true" prompt = "<OD>"
url = "https://modelscope.oss-cn-beijing.aliyuncs.com/resource/car.jpg"
image = Image.open(requests.get(url, stream=True).raw) image = Image.open(requests.get(url, stream=True).raw)
def run_example(task_prompt, text_input=None): inputs = processor(text=prompt, images=image, return_tensors="pt")
if text_input is None:
prompt = task_prompt generated_ids = model.generate(
else:
prompt = task_prompt + text_input
inputs = processor(text=prompt, images=image, return_tensors="pt")
generated_ids = model.generate(
input_ids=inputs["input_ids"], input_ids=inputs["input_ids"],
pixel_values=inputs["pixel_values"], pixel_values=inputs["pixel_values"],
max_new_tokens=1024, max_new_tokens=1024,
num_beams=3 num_beams=3,
) do_sample=False
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0] )
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> </details>