Update app.py

app.py

@@ -379,7 +379,7 @@ from keras.optimizers import SGD
 from keras.regularizers import l1, l2, l1_l2
 from keras.callbacks import EarlyStopping
 from mlxtend.plotting import plot_decision_regions
-from tensorflow.keras.utils import plot_model
+from io import StringIO
 
 
 # ========== Custom CSS ==========
@@ -459,8 +459,8 @@ with st.sidebar:
     with col2:
         lr = st.selectbox("Learning Rate", [0.1, 0.01, 0.02, 0.2])
 
-    reg = st.selectbox("Regularizer", ["None", "L1", "L2", "ElasticNet"])
-    if reg != "None":
+    reg_choice = st.selectbox("Regularizer", ["None", "L1", "L2", "ElasticNet"])
+    if reg_choice != "None":
         reg_rate = st.slider("Regularization rate", 0.0, 0.1, 0.01)
 
     es = st.selectbox("Early Stopping", ["No", "Yes"], index=0)
@@ -504,14 +504,15 @@ x_train = std.fit_transform(x_train)
 x_test = std.transform(x_test)
 
 # Regularizer setup
-if reg == "L1":
+if reg_choice == "None":
+    reg = None
+elif reg == "L1":
     reg = l1(reg_rate)
 elif reg == "L2":
     reg = l2(reg_rate)
 elif reg == "ElasticNet":
     reg = l1_l2(l1=reg_rate, l2=reg_rate)
-else:
-    reg = None
+
 
 # Build model
 model = Sequential()
@@ -535,6 +536,23 @@ if st.sidebar.button("🚀 Train Model"):
     hist = model.fit(x_train, y_train, epochs=epochs, validation_data=(x_test, y_test),
                      batch_size=32, verbose=0, callbacks=callbacks)
 
+    # Neural Network
+    # Capture summary
+    stringlist = []
+    model.summary(print_fn=lambda x: stringlist.append(x))
+    summary_str = "\n".join(stringlist)
+    
+    # Process into a dataframe (split by whitespace properly)
+    data = []
+    for line in stringlist[2:-4]:  # skip the header and footer
+        parts = [p for p in line.split(" ") if p != ""]
+        data.append(parts)
+    
+    df = pd.DataFrame(data)
+    st.subheader("Neural Network Architecture")
+    st.table(df)
+
+
     # Decision boundary
     st.subheader("Decision Boundary")
     fig, ax = plt.subplots()
@@ -549,22 +567,4 @@ if st.sidebar.button("🚀 Train Model"):
     ax2.legend()
     st.pyplot(fig2)
 
-    # Neural network diagram
-    plot_model(model, to_file="model.png", show_shapes=True, show_layer_names=True)
-    st.image("model.png", caption="Neural Network Architecture")
-    # st.subheader("Neural Network Architecture")
-    # fig3, ax3 = plt.subplots()
-    # layer_sizes = [2] + nn + [1]
-    # for i, size in enumerate(layer_sizes):
-    #     for j in range(size):
-    #         ax3.scatter(i, j, s=800, color="skyblue", edgecolors="black")
-    #     if i < len(layer_sizes) - 1:
-    #         for j in range(size):
-    #             for k in range(layer_sizes[i + 1]):
-    #                 ax3.plot([i, i + 1], [j, k], color="gray", alpha=0.3)
-    # ax3.axis("off")
-    # st.pyplot(fig3)
-
-    
-
-    
+