confusion matrix

Author: Sayed-Hossein-Hosseini

Audio_Classification_Using_CNNs.ipynb

@@ -255,6 +255,7 @@
     {
       "cell_type": "code",
       "source": [
+        "## Complected...Done!\n",
         "## Load each directory's images and label\n",
         "\n",
         "class_mapping = {\n",
@@ -294,6 +295,7 @@
     {
       "cell_type": "code",
       "source": [
+        "## Complected...Done!\n",
         "## because your data is in list, convert them to np.array\n",
         "\n",
         "from tensorflow.keras.utils import to_categorical\n",
@@ -377,6 +379,8 @@
     {
       "cell_type": "code",
       "source": [
+        "## Complected...Done!\n",
+        "\n",
         "from keras.models import Sequential\n",
         "from keras.layers import Conv2D, MaxPooling2D, Flatten, Dense\n",
         "from keras.optimizers import Adam\n",
@@ -430,6 +434,8 @@
     {
       "cell_type": "code",
       "source": [
+        "## Complected...Done!\n",
+        "\n",
         "hist = model.fit(\n",
         "    x_train_norm, y_train_encoded,\n",
         "    epochs=100,\n",
@@ -455,6 +461,8 @@
     {
       "cell_type": "code",
       "source": [
+        "## Complected...Done!\n",
+        "\n",
         "acc = hist.history['accuracy']\n",
         "val_acc = hist.history['val_accuracy']\n",
         "epochs = range(1, len(acc) + 1)\n",
@@ -487,15 +495,18 @@
     {
       "cell_type": "code",
       "source": [
+        "## Complected...Done!\n",
+        "\n",
         "from sklearn.metrics import confusion_matrix\n",
         "import seaborn as sns\n",
         "sns.set()\n",
         "\n",
-        "##############################################\n",
-        "############# YOUR CODES GO HERE #############\n",
-        "y_predicted = ....\n",
-        "mat = confusion_matrix(..., ...)\n",
-        "##############################################\n",
+        "# Predict class indices\n",
+        "y_predicted = np.argmax(model.predict(x_test_norm), axis=1)\n",
+        "y_true = np.argmax(y_test_encoded, axis=1)\n",
+        "\n",
+        "# Compute confusion matrix\n",
+        "mat = confusion_matrix(y_true, y_predicted)\n",
         "\n",
         "class_labels = ['background', 'chainsaw', 'engine', 'storm']\n",
         "\n",
@@ -504,7 +515,7 @@
         "            yticklabels=class_labels)\n",
         "\n",
         "plt.xlabel('Predicted label')\n",
-        "plt.ylabel('Actual label')"
+        "plt.ylabel('Actual label')\n"
       ],
       "metadata": {
         "id": "LQKAXBpkVBd-"