metadata
tags:
- image-to-text
- image-captioning
license: apache-2.0
widget:
- src: >-
https://huggingface.co/datasets/mishig/sample_images/resolve/main/savanna.jpg
example_title: Savanna
- src: >-
https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg
example_title: Football Match
- src: >-
https://huggingface.co/datasets/mishig/sample_images/resolve/main/airport.jpg
example_title: Airport
This is an image captioning model training by Zayn
from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTokenizer
model = VisionEncoderDecoderModel.from_pretrained("Zayn/vit2distilgpt2")
feature_extractor = ViTFeatureExtractor.from_pretrained("Zayn/vit2distilgpt2")
tokenizer = AutoTokenizer.from_pretrained("Zayn/vit2distilgpt2")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
max_length = 16
num_beams = 4
gen_kwargs = {"max_length": max_length, "num_beams": num_beams}
def predict_step(image_paths):
images = []
for image_path in image_paths:
i_image = Image.open(image_path)
if i_image.mode != "RGB":
i_image = i_image.convert(mode="RGB")
images.append(i_image)
pixel_values = feature_extractor(images=images, return_tensors="pt").pixel_values
pixel_values = pixel_values.to(device)
output_ids = model.generate(pixel_values, **gen_kwargs)
preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
preds = [pred.strip() for pred in preds]
return preds
predict_step(['Image URL.jpg'])