Delete app.py

app.py

@@ -1,126 +0,0 @@
-import os
-from typing import List
-import numpy as np
-import pandas as pd
-from PIL import Image
-import tensorflow as tf
-from tensorflow.keras.models import load_model
-from tensorflow.keras.preprocessing import image
-from flask import Flask, request
-import gradio as gr
-from backend.models.skin_tone.skin_tone_knn import identify_skin_tone
-from backend.models.recommender.rec import recs_essentials, makeup_recommendation
-import base64
-from io import BytesIO
-
-# Initialize Flask app
-app = Flask(__name__)
-
-# Model variables and loading
-class_names1 = ['Dry_skin', 'Normal_skin', 'Oil_skin']
-class_names2 = ['Low', 'Moderate', 'Severe']
-skin_tone_dataset = 'models/skin_tone/skin_tone_dataset.csv'
-
-
-def get_model():
-    global model1, model2
-    model1 = load_model('./models/skin_model')
-    print('Model 1 loaded')
-    model2 = load_model('./models/acne_model')
-    print("Model 2 loaded!")
-
-get_model()
-
-# Load and preprocess the image
-def load_image(img_path):
-    img = image.load_img(img_path, target_size=(224, 224))
-    img_tensor = image.img_to_array(img)
-    img_tensor = np.expand_dims(img_tensor, axis=0)  # Add a batch dimension
-    img_tensor /= 255.  # Normalize image
-    return img_tensor
-
-# Prediction for skin type
-def prediction_skin(img_path):
-    new_image = load_image(img_path)
-    pred1 = model1.predict(new_image)
-    if len(pred1[0]) > 1:
-        pred_class1 = class_names1[tf.argmax(pred1[0])]
-    else:
-        pred_class1 = class_names1[int(tf.round(pred1[0]))]
-    return pred_class1
-
-# Prediction for acne severity
-def prediction_acne(img_path):
-    new_image = load_image(img_path)
-    pred2 = model2.predict(new_image)
-    if len(pred2[0]) > 1:
-        pred_class2 = class_names2[tf.argmax(pred2[0])]
-    else:
-        pred_class2 = class_names2[int(tf.round(pred2[0]))]
-    return pred_class2
-
-# Gradio function for handling image input
-def process_image(image_data):
-    image_data = bytes(image_data, encoding="ascii")
-    im = Image.open(BytesIO(base64.b64decode(image_data + '==')))
-    file_path = './static/image.png'
-    im.save(file_path)  # Save the image locally
-    skin_type = prediction_skin(file_path).split('_')[0]  # Get skin type prediction
-    acne_type = prediction_acne(file_path)  # Get acne severity prediction
-    tone = identify_skin_tone(file_path, dataset=skin_tone_dataset)  # Get skin tone prediction
-    return {'type': skin_type, 'tone': str(tone), 'acne': acne_type}
-
-# Gradio Interface
-iface = gr.Interface(fn=process_image, 
-                     inputs=gr.Image(type="base64", label="Upload Face Image"), 
-                     outputs="json",
-                     live=True)
-
-# Flask routes for API endpoints
-@app.route('/')
-def home():
-    return "API is running. Use the Gradio interface for testing."
-
-# Recommendation API endpoint
-@app.route('/recommend', methods=['PUT'])
-def recommend():
-    args = request.get_json()  # Getting JSON data from the frontend
-    features = args['features']
-    tone = args['tone']
-    skin_type = args['type'].lower()
-    skin_tone = 'light to medium'
-    if tone <= 2:
-        skin_tone = 'fair to light'
-    elif tone >= 4:
-        skin_tone = 'medium to dark'
-
-    fv = [int(value) for key, value in features.items()]  # Converting feature values to integers
-
-    general = recs_essentials(fv, None)  # Recommendation essentials
-    makeup = makeup_recommendation(skin_tone, skin_type)  # Makeup recommendations
-
-    return {'general': general, 'makeup': makeup}
-
-# Skin Metrics API endpoint
-@app.route('/upload', methods=['PUT'])
-def upload():
-    args = request.get_json()  # Get the uploaded image data
-    file_data = args['file']
-    starter = file_data.find(',')
-    image_data = file_data[starter+1:]  # Extract the base64-encoded image
-
-    image_data = bytes(image_data, encoding="ascii")
-    im = Image.open(BytesIO(base64.b64decode(image_data + '==')))
-    file_path = './static/image.png'
-    im.save(file_path)  # Save image locally
-
-    skin_type = prediction_skin(file_path).split('_')[0]
-    acne_type = prediction_acne(file_path)
-    tone = identify_skin_tone(file_path, dataset=skin_tone_dataset)
-
-    return {'type': skin_type, 'tone': str(tone), 'acne': acne_type}, 200  # Return predictions
-
-if __name__ == "__main__":
-    # Launch Gradio interface and Flask app simultaneously
-    iface.launch(server_name="0.0.0.0", server_port=8080)  # Launch Gradio UI
-    app.run(debug=False, use_reloader=False)  # Run Flask app