initial commit

Prediction.py

@@ -0,0 +1,42 @@
+import streamlit as st
+from tensorflow.keras.models import load_model
+import numpy as np
+import cv2
+
+
+# Load the Models
+
+model = load_model('cancer_model.h5')
+class_names= ['adenocarcinoma', 'large cell carcinoma', 'normal', 'squamous cell carcinoma']
+
+def predict(image):
+    # Preprocess the image
+    image = cv2.resize(image, (460, 460))
+    image = image.astype('float32') / 255.0
+    image = image[np.newaxis, :]
+    
+    # Make predictions
+    predictions = model.predict(image)
+    
+    # Get the predicted class name
+    predicted_class_index = np.argmax(predictions[0])
+    predicted_class_name = class_names[predicted_class_index]
+    
+    return predicted_class_name
+
+
+def app():
+    st.title('CNN Image Classifier')
+
+    uploaded_file = st.file_uploader("Choose an image...", type="jpg")
+
+    if uploaded_file is not None:
+        # Read the uploaded image
+        image = cv2.imdecode(np.frombuffer(uploaded_file.read(), np.uint8), 1)
+
+        # Display the uploaded image
+        st.image(image, caption='Uploaded Image', use_column_width=True)
+
+        # Make predictions and display the result
+        prediction = predict(image)
+        st.write('Prediction:', prediction)

app.py

@@ -0,0 +1,17 @@
+import streamlit as st
+from Prediction import app as prediction_app
+
+
+# Define the Streamlit app
+st.set_page_config(page_title='Image Classifier', page_icon='🔍')
+
+PAGES = {
+    'Prediction': prediction_app,
+}
+
+st.sidebar.title('Navigation')
+selection = st.sidebar.radio('Go to', list(PAGES.keys()))
+
+# Display the selected page with the session state
+page = PAGES[selection]
+page()

cancer_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f8965e5dbb3f99babbad7ceb54a8ec630d9b1918f1a16bb2651cdafeb73369
+size 217814528