Spaces:
Runtime error
Runtime error
| import gradio as gr | |
| import pandas as pd | |
| import tensorflow as tf | |
| from keras.models import load_model | |
| import numpy as np | |
| import PIL | |
| from PIL import Image, ImageOps | |
| import cv2 | |
| import pytesseract | |
| import os | |
| from transformers import TrOCRProcessor, VisionEncoderDecoderModel | |
| import requests | |
| langs = [] | |
| choices = os.popen('tesseract --list-langs').read().split('\n')[1:-1] | |
| # Load the TROCR model and processor | |
| trocr_processor = TrOCRProcessor.from_pretrained('microsoft/trocr-large-handwritten') | |
| trocr_model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-large-handwritten') | |
| def trocr_predict(image): | |
| # Process image for TROCR | |
| pixel_values = trocr_processor(images=image, return_tensors="pt").pixel_values | |
| # Perform OCR using TROCR | |
| generated_ids = trocr_model.generate(pixel_values) | |
| decoded_text = trocr_processor.batch_decode(generated_ids, skip_special_tokens=True)[0] | |
| return decoded_text | |
| def run(image, lang=None): | |
| result = pytesseract.image_to_string( | |
| image, lang=None if lang == [] else lang) | |
| return result | |
| # Loading different models | |
| mnist_cnn_model = load_model('./models/mnist_cnn_model.h5') | |
| mnist_mcdnn_model = load_model('./models/mnist_mcdnn_model.h5') | |
| # Data Preprocessing | |
| def pre_process(image, model_name): | |
| img = image.convert("L") | |
| # Select model based on the dropdown selection | |
| if model_name == "Simple CNN": | |
| model = mnist_cnn_model | |
| img = img.resize((28, 28)) | |
| img = np.array(img) / 255.0 | |
| final_img = np.expand_dims(img, axis=0) # Add batch dimension | |
| pred = model.predict(final_img) | |
| result = np.argmax(pred) | |
| return str(result) | |
| elif model_name == "MCDNN": | |
| model = mnist_mcdnn_model | |
| img = img.resize((28, 28)) | |
| img = np.array(img) / 255.0 | |
| final_img = np.expand_dims(img, axis=0) # Add batch dimension | |
| pred = model.predict(final_img) | |
| result = np.argmax(pred) | |
| return str(result) | |
| elif model_name == "OCR": | |
| pred = run(image) | |
| return pred | |
| elif model_name == "CNN BI-LSTM": | |
| return trocr_predict(image) | |
| else: | |
| return "Invalid model selection" | |
| # Defining model options for dropdown | |
| model_options = ["Simple CNN", "MCDNN", "OCR", "CNN BI-LSTM"] | |
| with gr.Blocks() as demo: | |
| with gr.Row(): | |
| gr.Label("ScriptSense", container=False) | |
| with gr.Row(): | |
| with gr.Column(): | |
| image_file = gr.inputs.Image(type="pil", label="Upload an image") | |
| model_select = gr.components.Dropdown(choices=model_options, label="Select Model") | |
| with gr.Row(): | |
| predict_btn = gr.Button(value="Predict") | |
| with gr.Row(): | |
| Answer = gr.Label("👋 Hello, Let us predict the Result 💁♂️", container=False) | |
| predict_btn.click( | |
| pre_process, | |
| inputs=[ | |
| image_file, model_select | |
| ], | |
| outputs=[Answer], | |
| ) | |
| demo.launch() | |