Introduction of flax-vision-encoder-decoder-vit-gpt2-coco-en
Model Details of flax-vision-encoder-decoder-vit-gpt2-coco-en
Example
The model is by no means a state-of-the-art model, but nevertheless
produces reasonable image captioning results. It was mainly fine-tuned
as a proof-of-concept for the 🤗 FlaxVisionEncoderDecoder Framework.
The model can be used as follows:
import requests
from PIL import Image
from transformers import ViTFeatureExtractor, AutoTokenizer, FlaxVisionEncoderDecoderModel
loc = "ydshieh/flax-vit-gpt2-coco-en"
feature_extractor = ViTFeatureExtractor.from_pretrained(loc)
tokenizer = AutoTokenizer.from_pretrained(loc)
model = FlaxVisionEncoderDecoderModel.from_pretrained(loc)
# We will verify our results on an image of cute cats
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="np").pixel_values
defgenerate_step(pixel_values):
output_ids = model.generate(pixel_values, max_length=16, num_beams=4).sequences
preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
preds = [pred.strip() for pred in preds]
return preds
preds = generate_step(pixel_values)
print(preds)
# should produce# ['a cat laying on top of a couch next to another cat']
Runs of ydshieh flax-vision-encoder-decoder-vit-gpt2-coco-en on huggingface.co
0
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About flax-vision-encoder-decoder-vit-gpt2-coco-en huggingface.co Model
flax-vision-encoder-decoder-vit-gpt2-coco-en huggingface.co is an AI model on huggingface.co that provides flax-vision-encoder-decoder-vit-gpt2-coco-en's model effect (), which can be used instantly with this ydshieh flax-vision-encoder-decoder-vit-gpt2-coco-en model. huggingface.co supports a free trial of the flax-vision-encoder-decoder-vit-gpt2-coco-en model, and also provides paid use of the flax-vision-encoder-decoder-vit-gpt2-coco-en. Support call flax-vision-encoder-decoder-vit-gpt2-coco-en model through api, including Node.js, Python, http.
flax-vision-encoder-decoder-vit-gpt2-coco-en huggingface.co is an online trial and call api platform, which integrates flax-vision-encoder-decoder-vit-gpt2-coco-en's modeling effects, including api services, and provides a free online trial of flax-vision-encoder-decoder-vit-gpt2-coco-en, you can try flax-vision-encoder-decoder-vit-gpt2-coco-en online for free by clicking the link below.
ydshieh flax-vision-encoder-decoder-vit-gpt2-coco-en online free url in huggingface.co:
flax-vision-encoder-decoder-vit-gpt2-coco-en is an open source model from GitHub that offers a free installation service, and any user can find flax-vision-encoder-decoder-vit-gpt2-coco-en on GitHub to install. At the same time, huggingface.co provides the effect of flax-vision-encoder-decoder-vit-gpt2-coco-en install, users can directly use flax-vision-encoder-decoder-vit-gpt2-coco-en installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
flax-vision-encoder-decoder-vit-gpt2-coco-en install url in huggingface.co: