Add files via upload

Combined_Model.ipynb

@@ -0,0 +1,87 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ZELjx8qt4t3u"
+      },
+      "outputs": [],
+      "source": [
+        "#PALING BENER\n",
+        "\n",
+        "import os\n",
+        "import numpy as np\n",
+        "import tensorflow as tf\n",
+        "from tensorflow.keras.models import load_model\n",
+        "from tensorflow.keras.utils import load_img, img_to_array\n",
+        "import matplotlib.pyplot as plt\n",
+        "from google.colab import files\n",
+        "\n",
+        "# Load model gabungan\n",
+        "combined_model = load_model('/content/combined_model.h5')\n",
+        "\n",
+        "# Daftar class labels untuk model pertama\n",
+        "class_labels = ['Apel', 'Pisang', 'Paprika', 'Jeruk', 'Wortel', 'Timun']\n",
+        "\n",
+        "# Fungsi untuk prediksi jenis buah\n",
+        "def predict_jenis_buah(model, class_labels, file_name, target_size=(224, 224), confidence_threshold=0.6):\n",
+        "    img = load_img(file_name, target_size=target_size)\n",
+        "    img_array = img_to_array(img)\n",
+        "    img_array = np.expand_dims(img_array, axis=0) / 255.0\n",
+        "    prediction = model.predict([img_array, np.zeros((1, 150, 150, 3))])[0]\n",
+        "    confidence = np.max(prediction)\n",
+        "    print(f\"Predictions: {prediction}, Confidence: {confidence}\")  # Debugging output\n",
+        "    predicted_class_index = np.argmax(prediction)\n",
+        "    if predicted_class_index >= len(class_labels) or confidence < confidence_threshold:\n",
+        "        return \"Cannot be predicted\", confidence\n",
+        "    predicted_label = class_labels[predicted_class_index]\n",
+        "    return predicted_label, confidence\n",
+        "\n",
+        "# Fungsi untuk prediksi kesegaran buah\n",
+        "def predict_kesegaran(model, file_name, target_size=(150, 150)):\n",
+        "    img = load_img(file_name, target_size=target_size)\n",
+        "    img_array = img_to_array(img)\n",
+        "    img_array = np.expand_dims(img_array, axis=0) / 255.0\n",
+        "    prediction = model.predict([np.zeros((1, 224, 224, 3)), img_array])[1]\n",
+        "    print(f\"Kesegaran prediction: {prediction}\")  # Debugging output\n",
+        "    predicted_label = 'Segar' if prediction[0] > 0.01 else 'Tidak Segar'\n",
+        "    return predicted_label\n",
+        "\n",
+        "# Mengunggah dan memprediksi gambar baru\n",
+        "uploaded = files.upload()\n",
+        "for fn in uploaded.keys():\n",
+        "    file_path = fn\n",
+        "    jenis_buah, confidence = predict_jenis_buah(combined_model, class_labels, file_path)\n",
+        "    if jenis_buah == \"Cannot be predicted\":\n",
+        "        kesegaran_buah = \"Cannot be predicted\"\n",
+        "    else:\n",
+        "        kesegaran_buah = predict_kesegaran(combined_model, file_path)\n",
+        "\n",
+        "    # Menampilkan hasil prediksi\n",
+        "    img = load_img(file_path)\n",
+        "    plt.imshow(img)\n",
+        "    plt.title(f'Predicted: {jenis_buah} (Confidence: {confidence:.2f}), Kesegaran: {kesegaran_buah}')\n",
+        "    plt.axis('off')\n",
+        "    plt.show()\n",
+        "\n",
+        "    print(f'Gambar {fn} adalah {jenis_buah}, dan buah tersebut {kesegaran_buah}')\n",
+        "\n"
+      ]
+    }
+  ]
+}