Download app.py from arthurpendragon/Gastrointestinal-Classification: direct link, hf CLI and curl.
- Browser
- Download file 3.23 kB
-
https://huggingface.co/spaces/arthurpendragon/Gastrointestinal-Classification/resolve/main/app.py
- Command line
-
hf download hf://spaces/arthurpendragon/Gastrointestinal-Classification/app.py
-
curl -L -o app.py https://huggingface.co/spaces/arthurpendragon/Gastrointestinal-Classification/resolve/main/app.py
3.23 kB
| import streamlit as st | |
| from PIL import Image, ImageOps | |
| import numpy as np | |
| import pandas as pd | |
| import tensorflow as tf # Use TensorFlow's Keras API | |
| # Load the TensorFlow Keras model | |
| model = tf.keras.models.load_model('gastrointestinal_model.h5', compile=False) | |
| # Load class names | |
| with open('labels.txt', 'r') as f: | |
| class_names = f.readlines() | |
| # Function to predict gastrointestinal conditions | |
| def predict_gastrointestinal(img): | |
| np.set_printoptions(suppress=True) | |
| data = np.ndarray(shape=(1, 224, 224, 3), dtype=np.float32) | |
| size = (224, 224) | |
| image_PIL = ImageOps.fit(img, size, Image.LANCZOS) | |
| image_array = np.asarray(image_PIL) | |
| normalized_image_array = (image_array.astype(np.float32) / 127.0) - 1 | |
| data[0] = normalized_image_array | |
| prediction = model.predict(data) | |
| index = np.argmax(prediction) | |
| class_name = class_names[index].strip() | |
| confidence_score = prediction[0][index] | |
| other_class = [name for i, name in enumerate(class_names) if i != index][0].strip() | |
| result = { | |
| "Labels": [class_name, other_class], | |
| "Confidence Score": [confidence_score * 100, (1 - confidence_score) * 100], | |
| "Total": 100 | |
| } | |
| if class_name == "Normal": | |
| prediction_text = "The image is classified as Normal." | |
| else: | |
| prediction_text = f"The image shows signs of {class_name}." | |
| return prediction_text | |
| # Streamlit app | |
| st.title("Gastrointestinal Classification Web App") | |
| st.write(""" | |
| Welcome to the Gastrointestinal Classification Web App! This tool allows you to upload images of gastrointestinal conditions and receive classification results. | |
| ### How to Use: | |
| 1. **Upload an Image**: Click the "Upload a gastrointestinal image..." button to select and upload an image file in JPG, JPEG, or PNG format. | |
| 2. **View Classification**: Once the image is uploaded, it will be processed, and the app will classify it into one of the gastrointestinal conditions: Normal, Ulcerative Colitis, Polyp, or Esophagitis. | |
| 3. **See Results**: The app will display the classification result along with a confidence score. | |
| ### Next Steps: | |
| - **For Medical Advice**: If the classification suggests a potential issue, we recommend consulting with a healthcare professional for a thorough examination and diagnosis. | |
| - **Upload More Images**: Feel free to upload additional images if you wish to check more samples. | |
| - **Contact Support**: If you encounter any issues or have questions about the app, please contact our support team for assistance. | |
| Thank you for using our Gastrointestinal Classification Web App! | |
| """) | |
| uploaded_file = st.file_uploader("Upload a gastrointestinal image...", type=["jpg", "jpeg", "png"]) | |
| if uploaded_file is not None: | |
| image = Image.open(uploaded_file) | |
| st.image(image, caption='Uploaded Image', use_column_width=True) | |
| st.write("Classifying...") | |
| prediction = predict_gastrointestinal(image) | |
| st.write(prediction) | |
| st.write(""" | |
| **Next Steps:** | |
| - If the result indicates a condition of concern, please seek advice from a healthcare professional. | |
| - You can upload more images for further classification. | |
| - For any issues or questions, reach out to our support team. | |
| """) | |