Update app.py

app.py

@@ -1,31 +1,14 @@
 import torch 
 import re 
 import gradio as gr
-# import streamlit as st
 from PIL import Image
 
-# st.title("Image Caption Generator")
 from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel 
 import os
 import tensorflow as tf
 os.environ['TF_ENABLE_ONEDNN_OPTS'] = '0'
 
 device='cpu'
-# encoder_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
-# decoder_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
-# model_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
-
-# feature_extractor = ViTFeatureExtractor.from_pretrained(encoder_checkpoint)
-# tokenizer = AutoTokenizer.from_pretrained(decoder_checkpoint)
-# model = VisionEncoderDecoderModel.from_pretrained(model_checkpoint).to(device)
-
-# def predict(image, max_length=64, num_beams=4):
-#   image = image.convert('RGB')
-#   image = feature_extractor(image, return_tensors="pt").pixel_values.to(device)
-#   clean_text = lambda x: x.replace('<|endoftext|>','').split('\n')[0]
-#   caption_ids = model.generate(image, max_length = max_length)[0]
-#   caption_text = clean_text(tokenizer.decode(caption_ids))
-#   return caption_text 
 
 model_id = "nttdataspain/vit-gpt2-coco-lora"
 model = VisionEncoderDecoderModel.from_pretrained(model_id)