vision-encoder-decoder-vit-gpt2-coco-ko huggingface.co api & ddobokki vision-encoder-decoder-vit-gpt2-coco-ko github AI Model

Introduction of vision-encoder-decoder-vit-gpt2-coco-ko

Model Details of vision-encoder-decoder-vit-gpt2-coco-ko

EXAMPLE

import requests
import torch
from PIL import Image
from transformers import (
    VisionEncoderDecoderModel, 
    ViTFeatureExtractor, 
    PreTrainedTokenizerFast,
)

# device setting
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

# load feature extractor and tokenizer
encoder_model_name_or_path = "ddobokki/vision-encoder-decoder-vit-gpt2-coco-ko"
feature_extractor = ViTFeatureExtractor.from_pretrained(encoder_model_name_or_path)
tokenizer = PreTrainedTokenizerFast.from_pretrained(encoder_model_name_or_path)

# load model
model = VisionEncoderDecoderModel.from_pretrained(encoder_model_name_or_path)
model.to(device)

# inference
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
with Image.open(requests.get(url, stream=True).raw) as img:
    pixel_values = feature_extractor(images=img, return_tensors="pt").pixel_values

generated_ids = model.generate(pixel_values.to(device),num_beams=5)
generated_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)

>> ['고양이 두마리가 담요 위에 누워 있다.']

Runs of ddobokki vision-encoder-decoder-vit-gpt2-coco-ko on huggingface.co

Total runs

24-hour runs

3-day runs

7-day runs

30-day runs

More Information About vision-encoder-decoder-vit-gpt2-coco-ko huggingface.co Model

vision-encoder-decoder-vit-gpt2-coco-ko huggingface.co

vision-encoder-decoder-vit-gpt2-coco-ko huggingface.co is an AI model on huggingface.co that provides vision-encoder-decoder-vit-gpt2-coco-ko's model effect (), which can be used instantly with this ddobokki vision-encoder-decoder-vit-gpt2-coco-ko model. huggingface.co supports a free trial of the vision-encoder-decoder-vit-gpt2-coco-ko model, and also provides paid use of the vision-encoder-decoder-vit-gpt2-coco-ko. Support call vision-encoder-decoder-vit-gpt2-coco-ko model through api, including Node.js, Python, http.

vision-encoder-decoder-vit-gpt2-coco-ko huggingface.co Url

https://huggingface.co/ddobokki/vision-encoder-decoder-vit-gpt2-coco-ko

ddobokki vision-encoder-decoder-vit-gpt2-coco-ko online free

vision-encoder-decoder-vit-gpt2-coco-ko huggingface.co is an online trial and call api platform, which integrates vision-encoder-decoder-vit-gpt2-coco-ko's modeling effects, including api services, and provides a free online trial of vision-encoder-decoder-vit-gpt2-coco-ko, you can try vision-encoder-decoder-vit-gpt2-coco-ko online for free by clicking the link below.

ddobokki vision-encoder-decoder-vit-gpt2-coco-ko online free url in huggingface.co:

https://huggingface.co/ddobokki/vision-encoder-decoder-vit-gpt2-coco-ko

vision-encoder-decoder-vit-gpt2-coco-ko install

vision-encoder-decoder-vit-gpt2-coco-ko is an open source model from GitHub that offers a free installation service, and any user can find vision-encoder-decoder-vit-gpt2-coco-ko on GitHub to install. At the same time, huggingface.co provides the effect of vision-encoder-decoder-vit-gpt2-coco-ko install, users can directly use vision-encoder-decoder-vit-gpt2-coco-ko installed effect in huggingface.co for debugging and trial. It also supports api for free installation.