Upload 3 files

BraintumorClassifier.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1541bc63bbe75ad6a456db0c977f3d28e14eab117ee3d01149907648b4625542
+size 231299440

app.py

@@ -0,0 +1,49 @@
+import streamlit as st
+import tensorflow as tf
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing import image
+import numpy as np
+from PIL import Image
+import json
+
+# Load the CNN model
+model = load_model('BraintumorClassifier.h5')
+
+# Load the meta data (containing class names or other metadata)
+with open('meta_data.json', 'r') as f:
+    meta_data = json.load(f)
+
+# Extract class names from the meta data (assuming they are stored under "class_names")
+class_names = meta_data.get('classes', ['glioma', 'meningioma', 'pituitary_tumor'])
+
+# Function to preprocess the image for prediction
+def preprocess_image(img):
+    img = img.resize((224, 224))  # Resize to the input shape of the model
+    img_array = np.array(img) / 255.0  # Normalize the image
+    img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
+    return img_array
+
+# Streamlit UI
+st.title('Brain Tumor Classification')
+
+# Upload image
+uploaded_image = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+
+if uploaded_image is not None:
+    # Display the image
+    img = Image.open(uploaded_image)
+    st.image(img, caption="Uploaded Image", use_column_width=True)
+
+    # Preprocess the image for the model
+    img_array = preprocess_image(img)
+
+    # Button to classify the image
+    if st.button('Classify'):
+        prediction = model.predict(img_array)
+        predicted_class = np.argmax(prediction, axis=1)
+        class_name = class_names[predicted_class[0]]
+        st.write(f"Prediction: {class_name}")
+
+    # Button to clear the output
+    if st.button('Clear'):
+        st.experimental_rerun()

model_metadata.json

@@ -0,0 +1,58 @@
+{
+  "training_date": "20241203_163951",
+  "dataset_info": {
+    "total_images": 6000,
+    "real_images": 4500,
+    "synthetic_images": 1500,
+    "synthetic_ratio": 0.3,
+    "class_distribution": {
+      "glioma": 2000,
+      "meningioma": 2000,
+      "pituitary_tumor": 2000
+    }
+  },
+  "model_performance": {
+    "glioma": {
+      "precision": 0.9473684210526315,
+      "recall": 0.96,
+      "f1-score": 0.9536423841059603,
+      "support": 300
+    },
+    "meningioma": {
+      "precision": 0.962457337883959,
+      "recall": 0.94,
+      "f1-score": 0.9510961214165261,
+      "support": 300
+    },
+    "pituitary_tumor": {
+      "precision": 0.9867986798679867,
+      "recall": 0.9966666666666667,
+      "f1-score": 0.9917081260364843,
+      "support": 300
+    },
+    "accuracy": 0.9655555555555555,
+    "macro avg": {
+      "precision": 0.9655414796015257,
+      "recall": 0.9655555555555555,
+      "f1-score": 0.9654822105196569,
+      "support": 900
+    },
+    "weighted avg": {
+      "precision": 0.9655414796015258,
+      "recall": 0.9655555555555555,
+      "f1-score": 0.9654822105196569,
+      "support": 900
+    }
+  },
+  "input_shape": [
+    null,
+    224,
+    224,
+    1
+  ],
+  "classes": [
+    "glioma",
+    "meningioma",
+    "pituitary_tumor"
+  ]
+}