Rename app_py.py to app.py

app.py

@@ -0,0 +1,48 @@
+import tensorflow as tf
+import numpy as np
+import json
+import gradio as gr
+from PIL import Image
+
+# Load model
+model = tf.keras.models.load_model("food_vision_model.keras")
+
+# Load metadata
+with open("dermnet_disease_info.json", "r") as f:
+    disease_info = json.load(f)
+
+class_names = list(disease_info.keys())
+
+def load_and_prep_image(img, img_size=(224, 224)):
+    img = img.resize(img_size)
+    img_array = tf.keras.preprocessing.image.img_to_array(img)
+    img_array = tf.expand_dims(img_array, axis=0)
+    img_array = tf.keras.applications.efficientnet.preprocess_input(img_array)
+    return img_array
+
+def predict(img):
+    img_array = load_and_prep_image(img)
+    pred = model.predict(img_array)[0]
+    pred_class = class_names[np.argmax(pred)]
+    confidence = float(np.max(pred))
+    info = disease_info.get(pred_class, {})
+
+    result = f"🧬 **Disease Prediction:** {pred_class} ({confidence:.2%})\n\n"
+    result += f"📖 **Description:** {info['description']}\n\n"
+    result += f"🩺 **Symptoms:** {', '.join(info['symptoms'])}\n\n"
+    result += f"🧪 **Causes:** {', '.join(info['causes'])}\n\n"
+    result += f"💊 **Treatments:** {', '.join(info['treatments'])}\n\n"
+    result += f"🧍‍♂️ **Contagious:** {'Yes' if info['is_contagious'] else 'No'}"
+
+    return result
+
+# Gradio interface
+demo = gr.Interface(
+    fn=predict_disease,
+    inputs=gr.Image(type="pil"),
+    outputs="markdown",
+    title="🧪 Skin Disease Classifier",
+    description="Upload a skin image to classify and learn about the predicted skin condition.",
+    examples=None
+)
+demo.launch(debug=True)

app_py.py

@@ -1,60 +0,0 @@
-# -*- coding: utf-8 -*-
-"""app.py
-
-Automatically generated by Colab.
-
-Original file is located at
-    https://colab.research.google.com/drive/1izoc0P_UOwPr0z8UQvbf4s88qxqA-QTK
-"""
-
-from google.colab import drive
-drive.mount('/content/drive')
-
-from tensorflow.keras.models import load_model
-
-model = load_model('/content/drive/MyDrive/skin_disease_model.h5')
-
-import gradio as gr
-import tensorflow as tf
-import numpy as np
-from PIL import Image
-
-# Load model
-model = tf.keras.models.load_model('/content/drive/MyDrive/skin_disease_model.h5')  # or .keras
-
-# Define your class names
-class_names = ['Acne', 'Eczema', 'Fungal Infection', 'Psoriasis', 'Rosacea']  # replace with your actual classes
-
-# Preprocessing function
-def preprocess_image(image):
-    image = image.resize((180, 180))
-    image = np.array(image) / 255.0
-    image = np.expand_dims(image, axis=0)
-    return image
-
-# Prediction function
-def predict_skin_disease(img):
-    processed = preprocess_image(img)
-    pred = model.predict(processed)[0]
-    top_class = np.argmax(pred)
-    confidence = float(pred[top_class])
-    return {class_names[i]: float(pred[i]) for i in range(len(class_names))}
-
-# Gradio Interface
-interface = gr.Interface(
-    fn=predict_skin_disease,
-    inputs=gr.Image(type="pil"),
-    outputs=gr.Label(num_top_classes=3),
-    title="Skin Disease Classifier",
-    description="Upload a skin image to get a disease prediction."
-)
-
-interface.launch()
-
-import gradio as gr
-
-def classify(img):
-    return "Result"
-
-demo = gr.Interface(fn=classify, inputs="image", outputs="text")
-demo.launch()  # ✅ REQUIRED