dopopull

src/streamlit_app.py

@@ -9,6 +9,7 @@ from tensorflow.keras.layers import Dense, Flatten
 from tensorflow.keras.models import Model, load_model
 from datasets import load_dataset
 import matplotlib.pyplot as plt
+from sklearn.model_selection import train_test_split
 from sklearn.metrics import confusion_matrix, classification_report
 import seaborn as sns
 from huggingface_hub import HfApi
@@ -41,10 +42,14 @@ for i, sample in enumerate(dataset):
     image_list.append(image.numpy())
     label_list.append(np.array(sample["label"]))  
 
-X_train = np.array(image_list)
-y_train = np.array(label_list)
+X = np.array(image_list)
+y = np.array(label_list)
 
-st.write(f"✅ Scaricate e preprocessate {len(X_train)} immagini da `tiny-imagenet/64x64`!")
+# 📌 Suddivisione dataset: 80% training, 20% validation
+X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=0.2, random_state=42)
+
+st.write(f"📊 **Training:** {X_train.shape[0]} immagini")
+st.write(f"📊 **Validation:** {X_val.shape[0]} immagini")
 
 # 📌 Caricamento del modello
 if os.path.exists("Silva.h5"):
@@ -65,12 +70,8 @@ else:
     model = Model(inputs=base_model.input, outputs=output)
     model.compile(optimizer="adam", loss="sparse_categorical_crossentropy", metrics=["accuracy"])
 
-    # 📌 Training con barra di progresso
-    progress_bar = st.progress(0)
-    status_text = st.empty()
-    start_time = time.time()
-
-    history = model.fit(X_train, y_train, epochs=10)
+    # 📌 Training con monitoraggio validazione
+    history = model.fit(X_train, y_train, epochs=10, validation_data=(X_val, y_val))
 
     st.write("✅ Addestramento completato!")
 
@@ -78,36 +79,38 @@ else:
     model.save("Silva.h5")
     st.write("✅ Modello salvato come `Silva.h5`!")
 
-# 📌 Calcolo delle metriche
-y_pred = np.argmax(model.predict(X_train), axis=1)
-accuracy = np.mean(y_pred == y_train)
-rmse = np.sqrt(np.mean((y_pred - y_train) ** 2))
-report = classification_report(y_train, y_pred, output_dict=True)
-
-recall = report["weighted avg"]["recall"]
-precision = report["weighted avg"]["precision"]
-f1_score = report["weighted avg"]["f1-score"]
-
-st.write(f"📊 **Accuracy:** {accuracy:.4f}")
-st.write(f"📊 **RMSE:** {rmse:.4f}")
-st.write(f"📊 **Precision:** {precision:.4f}")
-st.write(f"📊 **Recall:** {recall:.4f}")
-st.write(f"📊 **F1-Score:** {f1_score:.4f}")
-
-# 📌 Bottone per generare la matrice di confusione
-if st.button("🔎 Genera matrice di confusione"):
-    conf_matrix = confusion_matrix(y_train, y_pred)
+# 📌 Calcolo delle metriche sulla validazione
+y_pred_val = np.argmax(model.predict(X_val), axis=1)
+accuracy_val = np.mean(y_pred_val == y_val)
+rmse_val = np.sqrt(np.mean((y_pred_val - y_val) ** 2))
+report_val = classification_report(y_val, y_pred_val, output_dict=True)
+
+recall_val = report_val["weighted avg"]["recall"]
+precision_val = report_val["weighted avg"]["precision"]
+f1_score_val = report_val["weighted avg"]["f1-score"]
+
+st.write(f"📊 **Validation Accuracy:** {accuracy_val:.4f}")
+st.write(f"📊 **Validation RMSE:** {rmse_val:.4f}")
+st.write(f"📊 **Validation Precision:** {precision_val:.4f}")
+st.write(f"📊 **Validation Recall:** {recall_val:.4f}")
+st.write(f"📊 **Validation F1-Score:** {f1_score_val:.4f}")
+
+# 📌 Bottone per generare la matrice di confusione sulla validazione
+if st.button("🔎 Genera matrice di confusione per validazione"):
+    conf_matrix_val = confusion_matrix(y_val, y_pred_val)
     fig, ax = plt.subplots(figsize=(10, 7))
-    sns.heatmap(conf_matrix, annot=True, cmap="Blues", fmt="d", ax=ax)
+    sns.heatmap(conf_matrix_val, annot=True, cmap="Blues", fmt="d", ax=ax)
     st.pyplot(fig)
     st.write("✅ Matrice di confusione generata!")
 
-# 📌 Grafico per Loss e Accuracy
+# 📌 Grafico per Loss e Accuracy con validazione
 fig, ax = plt.subplots(1, 2, figsize=(12, 5))
-ax[0].plot(history.history["loss"], label="Loss")
-ax[1].plot(history.history["accuracy"], label="Accuracy")
-ax[0].set_title("Loss durante il training")
-ax[1].set_title("Accuracy durante il training")
+ax[0].plot(history.history["loss"], label="Training Loss")
+ax[0].plot(history.history["val_loss"], label="Validation Loss")
+ax[1].plot(history.history["accuracy"], label="Training Accuracy")
+ax[1].plot(history.history["val_accuracy"], label="Validation Accuracy")
+ax[0].set_title("Loss durante il training e validazione")
+ax[1].set_title("Accuracy durante il training e validazione")
 ax[0].legend()
 ax[1].legend()
 st.pyplot(fig)