Upload 9 files

app.py

@@ -3,8 +3,91 @@ import tensorflow as tf
 import numpy as np
 from PIL import Image
 
-# Load the saved ResNet model
-model_resnet = []#tf.keras.models.load_model("path_to_your_saved_model/resnet_model.h5")
+# Load the saved models
+model_vgg = tf.keras.models.load_model("best_model.h5")
+classes_vgg = ["No Tumor detected", "Tumor detected"]
+
+model_resnet = tf.keras.models.load_model("Tumor_GliMeninPitu_model.h5")
+classes_resnet = ["Glioma", "Meningioma", "No Tumor", "Pituitary"]
+
+# Function to preprocess image
+def preprocess_image(uploaded_image, target_size):
+    img = Image.open(uploaded_image)
+
+    # Check if the image is grayscale
+    if img.mode == 'L':
+        # Convert grayscale to RGB by repeating the single channel
+        img = img.convert('RGB')
+        st.info("Gray scale image has been converted to three channels.")
+
+    # Resize the image
+    img = img.resize(target_size)
+
+    # Convert image to numpy array and preprocess
+    img_array = np.array(img)
+
+    # Ensure the image has three channels
+    if img_array.shape[-1] == 4:
+        img_array = img_array[:, :, :3]
+
+    img_array = tf.keras.applications.vgg16.preprocess_input(img_array)
+
+    # Add batch dimension
+    img_array = np.expand_dims(img_array, axis=0)
+
+    return img_array
+
+# Function to analyze binary classification
+def analyze_binary(uploaded_image, model, classes):
+    if uploaded_image is not None:
+        # Preprocess the uploaded image
+        img_array = preprocess_image(uploaded_image, (224, 224))
+        if img_array is not None:
+            # Make predictions using the loaded model
+            predictions = model.predict(img_array)
+
+            # Get the class label with the highest probability
+            class_label = np.argmax(predictions)
+            pred_class = classes[class_label]
+            confidence = predictions[0][class_label]
+
+            # Display prediction and confidence with stylish colors
+            st.markdown(
+                f"<div class='results-text' style='color: #009688;'>Prediction: <span class='results-values'>{pred_class}</span></div>",
+                unsafe_allow_html=True,
+            )
+            st.markdown(
+                f"<div class='results-text' style='color: #E91E63;'>Confidence Level: <span class='results-values'>{confidence:.2%}</span></div>",
+                unsafe_allow_html=True,
+            )
+    else:
+        st.warning("Please upload an image before clicking 'Analyze Binary'.")
+
+# Function to analyze multiclass classification
+def analyze_multiclass(uploaded_image, model, classes):
+    if uploaded_image is not None:
+        # Preprocess the uploaded image
+        img_array = preprocess_image(uploaded_image, (224, 224))
+        if img_array is not None:
+            # Make predictions using the loaded model
+            predictions = model.predict(img_array)
+
+            # Get the class label with the highest probability
+            class_label = np.argmax(predictions)
+            pred_class = classes[class_label]
+            confidence = predictions[0][class_label]
+
+            # Display prediction and confidence with stylish colors
+            st.markdown(
+                f"<div class='results-text' style='color: #4CAF50;'>Prediction: <span class='results-values'>{pred_class}</span></div>",
+                unsafe_allow_html=True,
+            )
+            st.markdown(
+                f"<div class='results-text' style='color: #FFC107;'>Confidence Level: <span class='results-values'>{confidence:.2%}</span></div>",
+                unsafe_allow_html=True,
+            )
+    else:
+        st.warning("Please upload an image before clicking 'Analyze Multiclass'.")
 
 # Set page configuration and layout
 st.set_page_config(
@@ -13,8 +96,27 @@ st.set_page_config(
     layout="wide",
 )
 
-# Header logo
+# Header logo with a colorful border
+st.markdown(
+    """
+    <style>
+    .header-logo {
+        display: flex;
+        justify-content: center;
+        align-items: center;
+        margin-bottom: 20px;
+        padding: 20px;
+        background-color: #2196F3;
+        border-radius: 10px;
+        color: white;
+    }
+    </style>
+    """,
+    unsafe_allow_html=True,
+)
+st.markdown("<div class='header-logos'>", unsafe_allow_html=True)
 st.image("RCAIoT_logo.png", use_column_width=False)
+st.markdown("</div>", unsafe_allow_html=True)
 
 # Main content
 col1, col2 = st.columns([1, 1])
@@ -23,18 +125,8 @@ with col1:
     st.header("Upload Image")
     uploaded_image = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"], key="upload_image")
     if uploaded_image is not None:
-        # Display the uploaded image with fixed initial height and width using HTML/CSS
+        # Display the uploaded image with fixed initial height and width
         st.image(uploaded_image, caption="Uploaded Image", use_column_width=False, width=300)
-        st.markdown(
-            """
-            <style>
-            img {
-                max-height: 300px;
-            }
-            </style>
-            """,
-            unsafe_allow_html=True,
-        )
 
 with col2:
     st.header("Results")
@@ -47,12 +139,13 @@ with col2:
             display: flex;
             justify-content: space-between;
             align-items: center;
+            margin-top: 20px;
         }
         .analyze-reset-buttons button {
             flex: 1;
             margin: 10px;
             padding: 10px;
-            background-color: #3366ff;
+            background-color: #2196F3;
             color: white;
             font-size: 16px;
             text-align: center;
@@ -62,19 +155,17 @@ with col2:
             transition: background-color 0.3s ease;
         }
         .analyze-reset-buttons button:hover {
-            background-color: #2353b4;
+            background-color: #1565C0;
         }
         .results-text {
             font-size: 24px;
             font-weight: bold;
             margin-top: 20px;
-            color: #000;
         }
         .results-values {
             font-size: 18px;
             font-weight: bold;
             margin-top: 10px;
-            color: blue;
         }
         </style>
         """,
@@ -82,35 +173,9 @@ with col2:
     )
 
     st.markdown("<div class='analyze-reset-buttons'>", unsafe_allow_html=True)
-    if st.button("Analyze", key="analyze_button"):
-        if uploaded_image is not None:
-            # Preprocess the uploaded image
-            img = Image.open(uploaded_image)
-            img = img.resize((64, 64))  # Resize the image to match the model input size
-            img = np.array(img)
-            img = tf.keras.applications.resnet50.preprocess_input(img)
-            img = np.expand_dims(img, axis=0)  # Add batch dimension
-
-            # Make predictions using the loaded model
-            predictions = model_resnet.predict(img)
-
-            # Get the class label with the highest probability
-            class_label = np.argmax(predictions)
-            confidence = predictions[0][class_label]
-
-            # Display prediction and confidence
-            st.markdown(
-                f"<div class='results-text'>Predicted Class: <span class='results-values'>{class_label}</span></div>",
-                unsafe_allow_html=True,
-            )
-            st.markdown(
-                f"<div class='results-text'>Confidence Level: <span class='results-values'>{confidence:.2f}</span></div>",
-                unsafe_allow_html=True,
-            )
-        else:
-            st.warning("Please upload an image before clicking 'Analyze'.")
-    if st.button("Reset", key="reset_button"):
-        st.session_state.uploaded_image = None
-        uploaded_image = None
-        st.empty()  # Clear the results container
-    st.markdown("</div>", unsafe_allow_html=True)
+    
+    if st.button("Analyze Binary", key="analyze_binary_button"):
+        analyze_binary(uploaded_image, model_vgg, classes_vgg)
+        
+    if st.button("Analyze Multiclass", key="analyze_multiclass_button"):
+        analyze_multiclass(uploaded_image, model_resnet, classes_resnet)