app.py

from transformers import VisionEncoderDecoderModel, ViTImageProcessor, AutoTokenizer
import torch
from PIL import Image
import gradio as gr
import numpy as np

model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
feature_extractor = ViTImageProcessor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")

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):
    i_image = Image.fromarray(np.uint8(image))
    if i_image.mode != "RGB":
        i_image = i_image.convert(mode="RGB")
    pixel_values = feature_extractor(images=i_image, 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

iface = gr.Interface(fn=predict_step, 
                     inputs=gr.inputs.Image(shape=(224, 224)),
                     outputs=gr.outputs.Textbox(label="Generated Caption"))

iface.launch()