| import streamlit as st | |
| import pytesseract | |
| import torch | |
| from PIL import Image | |
| from transformers import AutoTokenizer, AutoModelForSequenceClassification | |
| st.title(':blue[_SnapCode_]') | |
| st.markdown("_Extract code blocks out of Screenshots and Images_") | |
| with st.spinner('Code vs Natuaral language - Classification model is loading'): | |
| model_id = "vishnun/codenlbert-tiny" | |
| tokenizer = AutoTokenizer.from_pretrained(model_id) | |
| model = AutoModelForSequenceClassification.from_pretrained(model_id) | |
| st.success('Model loaded') | |
| def classify_text(text): | |
| input_ids = tokenizer(text, return_tensors="pt") | |
| with torch.no_grad(): | |
| logits = model(**input_ids).logits | |
| predicted_class_id = logits.argmax().item() | |
| return model.config.id2label[predicted_class_id] | |
| uploaded_file = st.file_uploader("Upload Image from which code needs to be extracted", type= ['png', 'jpeg', 'jpg']) | |
| if uploaded_file is not None: | |
| img = Image.open(uploaded_file) | |
| ocr_list = [x for x in pytesseract.image_to_string(img).split("\n") if x != ''] | |
| ocr_class = [classify_text(x) for x in ocr_list] | |
| idx = [] | |
| for i in range(len(ocr_class)): | |
| if ocr_class[i].upper() == 'CODE': | |
| idx.append(ocr_list[i]) | |
| st.markdown('**Uploaded Image**') | |
| st.image(img, caption='Uploaded Image') | |
| st.markdown("**Retrieved Code Block**") | |
| st.code(("\n").join(idx), language="python", line_numbers=False) |