Update app.py

app.py

@@ -1,18 +1,35 @@
 import streamlit as st 
 import  numpy as np 
-import matplotlib.pyplot as plt 
+import matplotlib.pyplot as plt
 import keras
-from io import StringIO
-import sys
+from sklearn.preprocessing import MinMaxScaler
 
 model = keras.models.load_model("model.keras")
 
-old_stdout = sys.stdout  # Save the current stdout so we can restore it later
-sys.stdout = StringIO()  # Redirect stdout to StringIO object
-model.summary()  # This will now be written to the StringIO object
-model_summary = sys.stdout.getvalue()  # Get the value from StringIO
-sys.stdout = old_stdout  # Restore original stdout
+uploaded_img = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
+
+options = ['1st Convolution', '2nd Convolution', '3rd Convolution']
+
+# Create the selectbox
+selected_option = st.selectbox(
+    'Choose an option:',  
+     options             
+)
+
+conv_layers = [layer for layer in model.layers if isinstance(layer, Conv2D)]
+
+plt.figure(figsize=(12, 4))
+scaler = MinMaxScaler()
+
+# for i in range(3):
+for j in range(6):
+    layer=conv_layers[0]
+    weights=layer.get_weights()[0][:,:,0,j]
+    norm_weights = scaler.fit_transform(weights)
+    plt.subplot(2,3,j+1)
+    plt.imshow(norm_weights,cmap='gray')
+    plt.title(f"Conv Layer")
+    plt.axis('off')
+plt.tight_layout()
+plt.show();
 
-# Display model summary using Streamlit
-st.write("### Model Summary:")
-st.text(model_summary)