Upload 3 files

app.py

@@ -0,0 +1,108 @@
+# app.py
+
+import streamlit as st
+import tensorflow as tf
+from tensorflow.keras.preprocessing import image
+import numpy as np
+from PIL import Image
+import cv2 # OpenCV for easy image processing (Make sure it's in requirements.txt)
+
+# --- CONFIGURATION ---
+MODEL_PATH = 'model.keras' # Aapka saved model file
+IMAGE_SIZE = (224, 224)
+CLASS_NAMES = ['No Tumor', 'Tumor'] # 0: No Tumor, 1: Tumor
+
+# --- Helper Function: Load Model ---
+# Streamlit mein model ko sirf ek baar load karna chahiye
+@st.cache_resource
+def load_model():
+    try:
+        model = tf.keras.models.load_model(MODEL_PATH)
+        return model
+    except Exception as e:
+        st.error(f"Error loading model: {e}")
+        return None
+
+# --- Helper Function: Preprocess Image ---
+def preprocess_image(img):
+    """Uploaded image ko model input ke liye ready karna."""
+    # Convert PIL image to OpenCV format (numpy array)
+    img_array = np.array(img.convert('RGB'))
+    
+    # Resize and Rescale (Jaisa training mein kiya tha)
+    img_resized = cv2.resize(img_array, IMAGE_SIZE)
+    img_normalized = img_resized / 255.0  # Normalize to 0-1
+    
+    # Add batch dimension: (224, 224, 3) -> (1, 224, 224, 3)
+    img_batch = np.expand_dims(img_normalized, axis=0)
+    
+    return img_batch
+
+# --- Streamlit UI Start ---
+
+# 1. Page Title (Requirement a)
+st.title("🧠 Brain Tumor Detection System (AI Powered)")
+
+# Load the model
+model = load_model()
+
+if model is None:
+    st.warning("Model file 'model.keras' not found. Please run 'train_model.py' first and place the file here.")
+else:
+    # 2. Image Upload Section (Requirement b)
+    uploaded_file = st.file_uploader(
+        "Upload a Brain MRI Image (.jpg, .png) for Classification:",
+        type=["jpg", "png", "jpeg"]
+    )
+
+    if uploaded_file is not None:
+        # Display image preview (Requirement b)
+        image_preview = Image.open(uploaded_file)
+        st.image(image_preview, caption='Uploaded MRI Image', use_column_width=True)
+        st.write("")
+        
+        # 3. Prediction Button (Requirement c)
+        if st.button("🔬 Detect Tumor"):
+            st.write("Processing...")
+
+            # --- Prediction Logic ---
+            try:
+                # 1. Preprocess the image
+                processed_img = preprocess_image(image_preview)
+                
+                # 2. Predict
+                prediction = model.predict(processed_img)
+                
+                # 3. Interpret the result
+                # Output is a single value, e.g., [0.98] or [0.02]
+                confidence_score = prediction[0][0] * 100 
+                
+                if confidence_score > 50:
+                    # Confidence is high for Tumor (Class 1)
+                    result_index = 1 
+                else:
+                    # Confidence is high for No Tumor (Class 0)
+                    result_index = 0
+                    # For 'No Tumor', confidence is 100 - (Model's confidence for Tumor)
+                    confidence_score = 100 - confidence_score
+                
+                predicted_class = CLASS_NAMES[result_index]
+                
+                # 4. Output Section (Requirement d)
+                st.subheader("✅ Prediction Results")
+                
+                if predicted_class == 'Tumor':
+                    st.error(f"**Prediction:** **{predicted_class}** - Immediate medical consultation is advised.")
+                else:
+                    st.success(f"**Prediction:** **{predicted_class}** - Looks clear.")
+                
+                # Display Confidence Score
+                st.info(f"**Confidence Score:** **{confidence_score:.2f}%**")
+
+            except Exception as e:
+                st.error(f"An error occurred during prediction: {e}")
+
+    else:
+        st.info("Please upload an image file to begin detection.")
+
+# --- End of Streamlit App ---

requirements.txt

@@ -0,0 +1,6 @@
+tensorflow
+keras
+streamlit
+numpy
+Pillow
+opencv-python

train_model.py

@@ -0,0 +1,92 @@
+# train_model.py
+
+import tensorflow as tf
+from tensorflow.keras.applications import VGG16
+from tensorflow.keras.preprocessing.image import ImageDataGenerator
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Flatten, Dense, Dropout
+
+# --- Step 1: Define Data Paths and Parameters ---
+IMAGE_SIZE = (224, 224) # VGG16 needs 224x224 input
+BATCH_SIZE = 32
+EPOCHS = 5 # Aap isko 10 ya 15 kar sakte hain acche results ke liye
+
+# Update this path to your dataset folder
+DATA_DIR = 'dataset' 
+
+# --- Step 2: Data Augmentation and Loading ---
+# Data Augmentation se model better seekhta hai
+train_datagen = ImageDataGenerator(
+    rescale=1./255, # Normalize pixels to 0-1
+    shear_range=0.2,
+    zoom_range=0.2,
+    horizontal_flip=True,
+    validation_split=0.2 # Validation data ke liye 20% data use hoga
+)
+
+train_generator = train_datagen.flow_from_directory(
+    DATA_DIR,
+    target_size=IMAGE_SIZE,
+    batch_size=BATCH_SIZE,
+    class_mode='binary', # Tumour (0) or No Tumour (1) - Binary classification
+    subset='training'
+)
+
+validation_generator = train_datagen.flow_from_directory(
+    DATA_DIR,
+    target_size=IMAGE_SIZE,
+    batch_size=BATCH_SIZE,
+    class_mode='binary',
+    subset='validation' # Yeh validation data hai
+)
+
+print("Data Generators Ready!")
+
+# --- Step 3: Build the Transfer Learning Model (VGG16) ---
+
+# Load Pre-trained VGG16 model (without the top classification layers)
+base_model = VGG16(
+    weights='imagenet', 
+    include_top=False, # Top classification layers ko nahi lena hai
+    input_shape=(224, 224, 3)
+)
+
+# Freeze Base Layers (Requirement: Don't train VGG16 weights)
+base_model.trainable = False
+
+# Create the Sequential Model
+model = Sequential([
+    base_model, # VGG16 base
+    Flatten(), # Flatten the output from VGG16
+    Dense(512, activation='relu'), # Custom layer 1
+    Dropout(0.5), # Regularization to prevent overfitting
+    Dense(1, activation='sigmoid') # Output layer: 1 neuron for binary classification (Tumor/No Tumor)
+])
+
+# --- Step 4: Compile and Train the Model ---
+model.compile(
+    optimizer='adam',
+    loss='binary_crossentropy', # Use binary_crossentropy for 2 classes
+    metrics=['accuracy']
+)
+
+model.summary()
+
+print("Model Training Started...")
+history = model.fit(
+    train_generator,
+    steps_per_epoch=train_generator.samples // BATCH_SIZE,
+    epochs=EPOCHS,
+    validation_data=validation_generator,
+    validation_steps=validation_generator.samples // BATCH_SIZE
+)
+
+print("Model Training Complete!")
+
+# --- Step 5: Save the Model (Requirement) ---
+MODEL_FILE_NAME = 'model.keras'
+model.save(MODEL_FILE_NAME) 
+print(f"Model saved as: {MODEL_FILE_NAME}")
+
+# Optional: Print final accuracy
+print(f"Final Validation Accuracy: {history.history['val_accuracy'][-1]:.4f}")