Update app.py

app.py

@@ -5,29 +5,29 @@ from keras.models import Model
 import matplotlib.pyplot as plt
 import numpy as np
 from tensorflow import keras
-from keras.layers import Conv2D, AveragePooling2D
 from PIL import Image
 
 m = MinMaxScaler()
-model = keras.models.load_model('cnn_lenet.keras')
-
-# Sidebar
-option = st.sidebar.selectbox("Datasets", ["Select dataset", "Hand Written Digit Dataset"])
+model = keras.models.load_model("cnn_lenet.keras")
 
+# Sidebar upload
 uploaded_file = st.sidebar.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
 
-if option == "Hand Written Digit Dataset":
-    (x_train, y_train), (x_test, y_test) = mnist.load_data()
-    st.write("✅ Successfully Loaded the MNIST Dataset")
+# Load MNIST for fallback
+(x_train, y_train), (x_test, y_test) = mnist.load_data()
 
-# Preprocess uploaded image or use MNIST sample
+# Preprocess uploaded image or fallback
 if uploaded_file is not None:
     image = Image.open(uploaded_file).convert("L")   # grayscale
     image = image.resize((28, 28))                   # resize to model input
     img_array = np.array(image) / 255.0
     img_array = img_array.reshape(1, 28, 28, 1)      # reshape for CNN
+    st.success("✅ Successfully uploaded image")
+    st.image(image, caption="Uploaded Image (28x28)", use_column_width=True)
 else:
-    img_array = x_train[0:1].reshape(1, 28, 28, 1)   # fallback to MNIST sample
+    img_array = x_train[0:1].reshape(1, 28, 28, 1)
+    st.info("ℹ️ No image uploaded, using MNIST sample instead")
+    st.image(x_train[0], caption="MNIST Sample", use_column_width=True)
 
 # Button to visualize
 if st.button("Visualize Layers"):
@@ -37,7 +37,10 @@ if st.button("Visualize Layers"):
         st.write("Filters")
         fig, axs = plt.subplots(6, 1, figsize=(8, 6))
         for i in range(6):
-            axs[i].imshow(m.fit_transform(model.layers[0].weights[0][:, :, :, i][:, :, 0]), cmap="gray")
+            axs[i].imshow(
+                m.fit_transform(model.layers[0].weights[0][:, :, :, i][:, :, 0]),
+                cmap="gray"
+            )
             axs[i].axis("off")
         st.pyplot(fig)