side-by-side FFN vs CNN comparison on every prediction

src/streamlit_app.py

@@ -4,8 +4,8 @@ import numpy as np
 import pandas as pd
 
 # Paths anchored to the repo root regardless of working directory
-_SRC_DIR = os.path.dirname(os.path.abspath(__file__))   # /app/src
-_REPO_ROOT = os.path.dirname(_SRC_DIR)                  # /app
+_SRC_DIR = os.path.dirname(os.path.abspath(__file__))
+_REPO_ROOT = os.path.dirname(_SRC_DIR)
 _SAMPLES_PATH = os.path.join(_REPO_ROOT, "data", "samples.csv")
 
 # ── Constants ──────────────────────────────────────────────────────────────
@@ -28,11 +28,6 @@ EXPLANATIONS = {
     "WALKING_UPSTAIRS": "Elevated vertical acceleration effort with upward body displacement — consistent with climbing stairs.",
 }
 
-MODEL_FILES = {
-    "FFN  (512→256→128)": "model.keras",
-    "CNN  (Conv1D×3)":    "har_cnn.keras",
-}
-
 # ── Model loader ────────────────────────────────────────────────────────────
 
 @st.cache_resource
@@ -40,7 +35,7 @@ def load_model(filename: str):
     try:
         from huggingface_hub import hf_hub_download
         import tensorflow as tf
-        from model_def import FeedForwardNetwork, Conv1DNetwork  # noqa: F401 — registers both classes
+        from model_def import FeedForwardNetwork, Conv1DNetwork  # noqa: F401
 
         model_path = hf_hub_download(
             repo_id="Group3DActRecog/actRecog",
@@ -63,7 +58,7 @@ def load_model(filename: str):
 st.set_page_config(
     page_title="Human Activity Recognition",
     page_icon="🏃",
-    layout="centered"
+    layout="wide",
 )
 
 st.title("Human Activity Recognition")
@@ -86,21 +81,29 @@ with st.sidebar:
     **Classes:** 6 activities of daily living
     """)
     st.markdown("---")
-    st.markdown("**Select model**")
-    model_choice = st.radio(
-        label="model",
-        options=list(MODEL_FILES.keys()),
-        label_visibility="collapsed",
-    )
+    st.markdown("**Models**")
+    st.markdown("""
+    **FFN** — Feedforward Network
+    Dense(512) → Dense(256) → Dense(128)
+    BatchNorm + Dropout(0.3) per layer
+
+    **CNN** — 1D Convolutional Network
+    Conv1D(64) → Conv1D(128) → Conv1D(256)
+    GlobalAvgPool → Dense(128)
+    """)
     st.markdown("---")
     st.caption("DAT606 Group Assignment · Pan-Atlantic University")
 
-# ── Load selected model ───────────────────────────────────────────────────────
+# ── Load both models at startup ───────────────────────────────────────────────
 
-model, model_status = load_model(MODEL_FILES[model_choice])
+ffn_model, ffn_status = load_model("model.keras")
+cnn_model, cnn_status = load_model("har_cnn.keras")
 
-if model_status != "ready":
-    st.warning(f"Model not loaded — {model_status}")
+if ffn_status != "ready" or cnn_status != "ready":
+    if ffn_status != "ready":
+        st.warning(f"FFN not loaded — {ffn_status}")
+    if cnn_status != "ready":
+        st.warning(f"CNN not loaded — {cnn_status}")
 
 # ── Tabs ─────────────────────────────────────────────────────────────────────
 
@@ -117,10 +120,7 @@ with tab1:
 
     try:
         samples_df = pd.read_csv(_SAMPLES_PATH)
-        feature_cols = [
-            c for c in samples_df.columns
-            if c not in ["Activity", "subject"]
-        ]
+        feature_cols = [c for c in samples_df.columns if c not in ["Activity", "subject"]]
 
         sample_labels = [
             f"Sample {i+1}  —  {row['Activity']}"
@@ -140,39 +140,55 @@ with tab1:
             st.metric("Feature count", len(feature_vector))
 
         if st.button("Classify this sample", type="primary"):
-            if model_status != "ready":
-                st.error("Model not loaded — cannot predict yet.")
+            if ffn_status != "ready" or cnn_status != "ready":
+                st.error("One or both models not loaded — cannot predict yet.")
             else:
                 arr = feature_vector.reshape(1, -1)
-                probs = model.predict(arr, verbose=0)[0]
-                pred_idx = int(np.argmax(probs))
-                pred_label = LABEL_MAP[pred_idx]
-                confidence = float(probs[pred_idx]) * 100
-                correct = pred_label == true_label
+
+                ffn_probs = ffn_model.predict(arr, verbose=0)[0]
+                cnn_probs = cnn_model.predict(arr, verbose=0)[0]
+
+                ffn_idx   = int(np.argmax(ffn_probs))
+                cnn_idx   = int(np.argmax(cnn_probs))
+                ffn_label = LABEL_MAP[ffn_idx]
+                cnn_label = LABEL_MAP[cnn_idx]
+                ffn_conf  = float(ffn_probs[ffn_idx]) * 100
+                cnn_conf  = float(cnn_probs[cnn_idx]) * 100
 
                 st.markdown("---")
-                st.subheader("Result")
-
-                if correct:
-                    st.success(
-                        f"**{pred_label}** · {confidence:.1f}% confidence · ✓ Correct"
-                    )
-                else:
-                    st.error(
-                        f"**{pred_label}** · {confidence:.1f}% confidence · "
-                        f"✗ Incorrect (true: {true_label})"
-                    )
-
-                st.markdown(f"_{EXPLANATIONS[pred_label]}_")
-                st.markdown("**Confidence across all classes**")
-
-                chart_data = pd.DataFrame({
-                    "Confidence (%)": [
-                        float(probs[i]) * 100 for i in range(6)
-                    ]
-                }, index=[LABEL_MAP[i] for i in range(6)])
-
-                st.bar_chart(chart_data)
+                st.subheader("Model comparison")
+
+                left, right = st.columns(2)
+
+                # ── FFN column ──────────────────────────────────────────────
+                with left:
+                    st.markdown("#### Feedforward Network")
+                    if ffn_label == true_label:
+                        st.success(f"**{ffn_label}** · {ffn_conf:.1f}% confidence · ✓ Correct")
+                    else:
+                        st.error(f"**{ffn_label}** · {ffn_conf:.1f}% confidence · ✗ Incorrect (true: {true_label})")
+
+                    st.markdown(f"_{EXPLANATIONS[ffn_label]}_")
+                    st.markdown("**Confidence across all classes**")
+                    st.bar_chart(pd.DataFrame(
+                        {"Confidence (%)": [float(ffn_probs[i]) * 100 for i in range(6)]},
+                        index=[LABEL_MAP[i] for i in range(6)]
+                    ))
+
+                # ── CNN column ──────────────────────────────────────────────
+                with right:
+                    st.markdown("#### 1D Convolutional Network")
+                    if cnn_label == true_label:
+                        st.success(f"**{cnn_label}** · {cnn_conf:.1f}% confidence · ✓ Correct")
+                    else:
+                        st.error(f"**{cnn_label}** · {cnn_conf:.1f}% confidence · ✗ Incorrect (true: {true_label})")
+
+                    st.markdown(f"_{EXPLANATIONS[cnn_label]}_")
+                    st.markdown("**Confidence across all classes**")
+                    st.bar_chart(pd.DataFrame(
+                        {"Confidence (%)": [float(cnn_probs[i]) * 100 for i in range(6)]},
+                        index=[LABEL_MAP[i] for i in range(6)]
+                    ))
 
     except FileNotFoundError:
         st.error("Sample data file not found. Add `data/samples.csv` to the repo.")