metadata
{}
How to Get Started with the Model
Use the code below to get started with the model.
import requests
from PIL import Image
from transformers import AutoProcessor, AutoModelForVision2Seq
model = AutoModelForVision2Seq.from_pretrained("ydshieh/kosmos-2-patch14-224", trust_remote_code=True)
processor = AutoProcessor.from_pretrained("ydshieh/kosmos-2-patch14-224", trust_remote_code=True)
prompt = "<grounding>An image of"
url = "https://huggingface.co/ydshieh/kosmos-2-patch14-224/resolve/main/snowman.jpg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(text=prompt, images=image, return_tensors="pt")
generated_ids = model.generate(
pixel_values=inputs["pixel_values"],
input_ids=inputs["input_ids"][:, :-1],
attention_mask=inputs["attention_mask"][:, :-1],
img_features=None,
img_attn_mask=inputs["img_attn_mask"][:, :-1],
use_cache=True,
max_new_tokens=64,
)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
# Specify `cleanup_and_extract=False` in order to see the raw model generation.
processed_text = processor.post_processor_generation(generated_text, cleanup_and_extract=False)
print(processed_text)
# `<grounding> An image of<phrase> a snowman</phrase><object><patch_index_0044><patch_index_0863></object> warming himself by<phrase> a fire</phrase><object><patch_index_0005><patch_index_0911></object>.`
# By default, the generated text is cleanup and the entities are extracted.
processed_text, entities = processor.post_processor_generation(generated_text)
print(processed_text)
# `An image of a snowman warming himself by a fire.`
print(entities)
# `[('a snowman', (12, 21), [(0.390625, 0.046875, 0.984375, 0.828125)]), ('a fire', (41, 47), [(0.171875, 0.015625, 0.484375, 0.890625)])]`