Plant_Disease_Detection_Classification.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Plant Disease Detection-Classification.ipynb",
      "provenance": [],
      "collapsed_sections": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "oirfISxsQC1R",
        "outputId": "e10c2b3b-dc17-4c4c-e212-cbe5e7b17a91"
      },
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/gdrive/')"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Mounted at /content/gdrive/\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "o3h-GdRkUkxn"
      },
      "source": [
        "root_path='gdrive/My Drive/PLANT DISEASE DETECTION/' \n",
        "# Proj Drive Folder \n",
        "# use print(root_path) / !ls proj_folder_path  to check"
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "resources": {
            "http://localhost:8080/nbextensions/google.colab/files.js": {
              "data": "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",
              "ok": true,
              "headers": [
                [
                  "content-type",
                  "application/javascript"
                ]
              ],
              "status": 200,
              "status_text": ""
            }
          },
          "base_uri": "https://localhost:8080/",
          "height": 72
        },
        "id": "57XorfM-Weuc",
        "outputId": "c0beb0b2-c04b-4a9f-d712-ad536a3c22c5"
      },
      "source": [
        "from google.colab import files\n",
        "files.upload()"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "\n",
              "     <input type=\"file\" id=\"files-89849ac0-5572-4045-96b2-52f2ad93303c\" name=\"files[]\" multiple disabled\n",
              "        style=\"border:none\" />\n",
              "     <output id=\"result-89849ac0-5572-4045-96b2-52f2ad93303c\">\n",
              "      Upload widget is only available when the cell has been executed in the\n",
              "      current browser session. Please rerun this cell to enable.\n",
              "      </output>\n",
              "      <script src=\"/nbextensions/google.colab/files.js\"></script> "
            ],
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "Saving kaggle.json to kaggle.json\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'kaggle.json': b'{\"username\":\"sahilthakur2708\",\"key\":\"dc166b893f6f1e7b70fb4f21b3ffbfd2\"}'}"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "TUfMDsMeXMjv",
        "outputId": "4f594980-54a1-4627-ce31-b08b8f553716"
      },
      "source": [
        "!pip install -q kaggle\n",
        "!mkdir -p ~/.kaggle\n",
        "!cp kaggle.json ~/.kaggle/\n",
        "!ls ~/.kaggle\n",
        "!chmod 600 /root/.kaggle/kaggle.json  # set permission"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "kaggle.json\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Fe2QBkKLXTTC",
        "outputId": "4742e523-7ce9-4040-cb03-31d21ba31e8c"
      },
      "source": [
        "!kaggle datasets download -d koheidozono/newplantvillage -p '/content/gdrive/My Drive/PLANT DISEASE DETECTION/'"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "newplantvillage.zip: Skipping, found more recently modified local copy (use --force to force download)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cQUhPIU2fg4t"
      },
      "source": [
        "import os\n",
        "import matplotlib.pyplot as plt\n",
        "import numpy as np\n",
        "import tensorflow as tf\n",
        "from tensorflow import keras"
      ],
      "execution_count": 6,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6k9VWXIegCfm",
        "outputId": "b06b4b1e-d981-45ce-da4e-de71bc41242e"
      },
      "source": [
        "from zipfile import ZipFile\n",
        "with ZipFile('/content/gdrive/MyDrive/PLANT DISEASE DETECTION/newplantvillage.zip', 'r') as zipObj:\n",
        "  zipObj.extractall()\n",
        "  print('Done')"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Done\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "NttA86B8rEte"
      },
      "source": [
        "classes_train = sorted(list(filter(lambda x: os.path.isdir('/content/newplantvillage/' + x), os.listdir('/content/newplantvillage'))))"
      ],
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "XuWR5kFcrYcP",
        "outputId": "acc73a72-819a-4115-a9fe-382302dff7d4"
      },
      "source": [
        "print(classes_train) #to show names of all classes"
      ],
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "['Apple___Apple_scab', 'Apple___Black_rot', 'Apple___Cedar_apple_rust', 'Apple___healthy', 'Blueberry___healthy', 'Cherry_(including_sour)___Powdery_mildew', 'Cherry_(including_sour)___healthy', 'Grape___Black_rot', 'Grape___Esca_(Black_Measles)', 'Grape___Leaf_blight_(Isariopsis_Leaf_Spot)', 'Grape___healthy', 'Orange___Haunglongbing_(Citrus_greening)', 'Peach___Bacterial_spot', 'Peach___healthy', 'Pepper,_bell___Bacterial_spot', 'Pepper,_bell___healthy', 'Potato___Early_blight', 'Potato___Late_blight', 'Potato___healthy', 'Raspberry___healthy', 'Soybean___healthy', 'Squash___Powdery_mildew', 'Strawberry___Leaf_scorch', 'Strawberry___healthy', 'Tomato___Bacterial_spot', 'Tomato___Early_blight', 'Tomato___Late_blight', 'Tomato___Leaf_Mold', 'Tomato___Septoria_leaf_spot', 'Tomato___Spider_mites Two-spotted_spider_mite', 'Tomato___Target_Spot', 'Tomato___Tomato_Yellow_Leaf_Curl_Virus', 'Tomato___Tomato_mosaic_virus', 'Tomato___healthy']\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "tVUPQaQBrzzV",
        "outputId": "1eb98b00-2a1d-444d-b35a-feb7eab9726c"
      },
      "source": [
        "!pip install split_folders"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Collecting split_folders\n",
            "  Downloading https://files.pythonhosted.org/packages/b8/5f/3c2b2f7ea5e047c8cdc3bb00ae582c5438fcdbbedcc23b3cc1c2c7aae642/split_folders-0.4.3-py3-none-any.whl\n",
            "Installing collected packages: split-folders\n",
            "Successfully installed split-folders-0.4.3\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5V5ZQwOvsCQR",
        "outputId": "e5af6931-cf01-4293-9abb-00c44f8dfc4d"
      },
      "source": [
        "import splitfolders\n",
        "input_folder='/content/newplantvillage'\n",
        "splitfolders.ratio(input_folder, output=\"output\", seed=1337, ratio=(.8,.2)) #default values\""
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Copying files: 62979 files [00:09, 6900.01 files/s]\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2dXXrnBCtLBr",
        "outputId": "3a5dc70f-4385-48ae-d226-6d503bb20119"
      },
      "source": [
        "batch_size=128\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "train_datagen=ImageDataGenerator(rescale=1/255)\n",
        "train_generator=train_datagen.flow_from_directory(\n",
        "    '/content/output/train',\n",
        "    target_size=(200, 200),\n",
        "    batch_size=batch_size,\n",
        "    classes = classes_train,\n",
        "    class_mode='categorical'\n",
        ")\n",
        "val_datagen=ImageDataGenerator(rescale=1/255)\n",
        "val_generator=val_datagen.flow_from_directory(\n",
        "    '/content/output/val',\n",
        "    target_size=(200, 200),\n",
        "    batch_size=batch_size,\n",
        "    classes = classes_train,\n",
        "    class_mode='categorical'\n",
        ")"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Found 50368 images belonging to 34 classes.\n",
            "Found 12611 images belonging to 34 classes.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LRKPs97cwRVA",
        "outputId": "a06a6d2c-5d2b-412d-a696-8c6d3ed03bf5"
      },
      "source": [
        "import tensorflow as tf\n",
        "model = tf.keras.models.Sequential([\n",
        "    # Note the input shape is the desired size of the image 200x 200 with 3 bytes color\n",
        "    # The first convolution\n",
        "    tf.keras.layers.Conv2D(16, (3,3), activation='relu', input_shape=(200, 200, 3)),\n",
        "    tf.keras.layers.BatchNormalization(),\n",
        "    tf.keras.layers.MaxPooling2D(2, 2),\n",
        "    # The second convolution\n",
        "    tf.keras.layers.Conv2D(32, (3,3), activation='relu'),\n",
        "    tf.keras.layers.BatchNormalization(),    \n",
        "    tf.keras.layers.MaxPooling2D(2,2),\n",
        "    # The third convolution\n",
        "    tf.keras.layers.Conv2D(64, (3,3), activation='relu'),\n",
        "    tf.keras.layers.BatchNormalization(),\n",
        "    tf.keras.layers.MaxPooling2D(2,2),\n",
        "    # The fourth convolution\n",
        "    tf.keras.layers.Conv2D(64, (3,3), activation='relu'),\n",
        "    tf.keras.layers.BatchNormalization(),\n",
        "    tf.keras.layers.MaxPooling2D(2,2),\n",
        "    # The fifth convolution\n",
        "    tf.keras.layers.Conv2D(64, (3,3), activation='relu'),\n",
        "    tf.keras.layers.BatchNormalization(),\n",
        "    tf.keras.layers.MaxPooling2D(2,2),\n",
        "    # Flatten the results to feed into a dense layer\n",
        "    tf.keras.layers.Flatten(),\n",
        "    # 128 neuron in the fully-connected layer\n",
        "    tf.keras.layers.Dense(128, activation='relu'),\n",
        "    # 5 output neurons for 5 classes with the softmax activation\n",
        "    tf.keras.layers.Dense(34, activation='softmax')\n",
        "])\n",
        "model.summary()"
      ],
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Model: \"sequential\"\n",
            "_________________________________________________________________\n",
            "Layer (type)                 Output Shape              Param #   \n",
            "=================================================================\n",
            "conv2d (Conv2D)              (None, 198, 198, 16)      448       \n",
            "_________________________________________________________________\n",
            "batch_normalization (BatchNo (None, 198, 198, 16)      64        \n",
            "_________________________________________________________________\n",
            "max_pooling2d (MaxPooling2D) (None, 99, 99, 16)        0         \n",
            "_________________________________________________________________\n",
            "conv2d_1 (Conv2D)            (None, 97, 97, 32)        4640      \n",
            "_________________________________________________________________\n",
            "batch_normalization_1 (Batch (None, 97, 97, 32)        128       \n",
            "_________________________________________________________________\n",
            "max_pooling2d_1 (MaxPooling2 (None, 48, 48, 32)        0         \n",
            "_________________________________________________________________\n",
            "conv2d_2 (Conv2D)            (None, 46, 46, 64)        18496     \n",
            "_________________________________________________________________\n",
            "batch_normalization_2 (Batch (None, 46, 46, 64)        256       \n",
            "_________________________________________________________________\n",
            "max_pooling2d_2 (MaxPooling2 (None, 23, 23, 64)        0         \n",
            "_________________________________________________________________\n",
            "conv2d_3 (Conv2D)            (None, 21, 21, 64)        36928     \n",
            "_________________________________________________________________\n",
            "batch_normalization_3 (Batch (None, 21, 21, 64)        256       \n",
            "_________________________________________________________________\n",
            "max_pooling2d_3 (MaxPooling2 (None, 10, 10, 64)        0         \n",
            "_________________________________________________________________\n",
            "conv2d_4 (Conv2D)            (None, 8, 8, 64)          36928     \n",
            "_________________________________________________________________\n",
            "batch_normalization_4 (Batch (None, 8, 8, 64)          256       \n",
            "_________________________________________________________________\n",
            "max_pooling2d_4 (MaxPooling2 (None, 4, 4, 64)          0         \n",
            "_________________________________________________________________\n",
            "flatten (Flatten)            (None, 1024)              0         \n",
            "_________________________________________________________________\n",
            "dense (Dense)                (None, 128)               131200    \n",
            "_________________________________________________________________\n",
            "dense_1 (Dense)              (None, 34)                4386      \n",
            "=================================================================\n",
            "Total params: 233,986\n",
            "Trainable params: 233,506\n",
            "Non-trainable params: 480\n",
            "_________________________________________________________________\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-k_QMMop8StS"
      },
      "source": [
        "from tensorflow.keras.optimizers import Adam\n",
        "from tensorflow import keras\n",
        "\n",
        "model.compile(loss='categorical_crossentropy', optimizer=Adam(lr=0.0005), metrics=['accuracy'])"
      ],
      "execution_count": 15,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ujXHKOmE8zfE",
        "outputId": "1036ef63-2afa-4606-e3c9-f46ceb78a59b"
      },
      "source": [
        "epochs=12\n",
        "steps_per_epoch=train_generator.n//train_generator.batch_size\n",
        "validation_steps=val_generator.n//val_generator.batch_size\n",
        "\n",
        "checkpoint = keras.callbacks.ModelCheckpoint(\"/content/abc.h5\", monitor='val_loss', verbose=1, save_best_only=True, save_weights_only=False, mode='auto')\n",
        "\n",
        "history=model.fit(\n",
        "    x=train_generator,\n",
        "    y=None,\n",
        "    steps_per_epoch=steps_per_epoch,\n",
        "    epochs=epochs,\n",
        "    validation_data=val_generator,\n",
        "    validation_steps=validation_steps,\n",
        "    callbacks=[checkpoint]\n",
        ")"
      ],
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/12\n",
            "393/393 [==============================] - ETA: 0s - loss: 0.0599 - accuracy: 0.9807\n",
            "Epoch 00001: val_loss improved from inf to 0.82597, saving model to /content/abc.h5\n",
            "393/393 [==============================] - 114s 289ms/step - loss: 0.0599 - accuracy: 0.9807 - val_loss: 0.8260 - val_accuracy: 0.8014\n",
            "Epoch 2/12\n",
            "393/393 [==============================] - ETA: 0s - loss: 0.0461 - accuracy: 0.9862\n",
            "Epoch 00002: val_loss improved from 0.82597 to 0.24825, saving model to /content/abc.h5\n",
            "393/393 [==============================] - 113s 288ms/step - loss: 0.0461 - accuracy: 0.9862 - val_loss: 0.2483 - val_accuracy: 0.9244\n",
            "Epoch 3/12\n",
            "393/393 [==============================] - ETA: 0s - loss: 0.0333 - accuracy: 0.9897\n",
            "Epoch 00003: val_loss did not improve from 0.24825\n",
            "393/393 [==============================] - 112s 286ms/step - loss: 0.0333 - accuracy: 0.9897 - val_loss: 0.3699 - val_accuracy: 0.8968\n",
            "Epoch 4/12\n",
            "393/393 [==============================] - ETA: 0s - loss: 0.0368 - accuracy: 0.9884\n",
            "Epoch 00004: val_loss improved from 0.24825 to 0.16709, saving model to /content/abc.h5\n",
            "393/393 [==============================] - 112s 285ms/step - loss: 0.0368 - accuracy: 0.9884 - val_loss: 0.1671 - val_accuracy: 0.9510\n",
            "Epoch 5/12\n",
            "393/393 [==============================] - ETA: 0s - loss: 0.0355 - accuracy: 0.9883\n",
            "Epoch 00005: val_loss did not improve from 0.16709\n",
            "393/393 [==============================] - 113s 287ms/step - loss: 0.0355 - accuracy: 0.9883 - val_loss: 0.3466 - val_accuracy: 0.9038\n",
            "Epoch 6/12\n",
            "393/393 [==============================] - ETA: 0s - loss: 0.0287 - accuracy: 0.9904\n",
            "Epoch 00006: val_loss did not improve from 0.16709\n",
            "393/393 [==============================] - 113s 286ms/step - loss: 0.0287 - accuracy: 0.9904 - val_loss: 0.4631 - val_accuracy: 0.8921\n",
            "Epoch 7/12\n",
            "393/393 [==============================] - ETA: 0s - loss: 0.0265 - accuracy: 0.9911\n",
            "Epoch 00007: val_loss did not improve from 0.16709\n",
            "393/393 [==============================] - 112s 286ms/step - loss: 0.0265 - accuracy: 0.9911 - val_loss: 0.1899 - val_accuracy: 0.9473\n",
            "Epoch 8/12\n",
            "393/393 [==============================] - ETA: 0s - loss: 0.0280 - accuracy: 0.9902\n",
            "Epoch 00008: val_loss did not improve from 0.16709\n",
            "393/393 [==============================] - 113s 286ms/step - loss: 0.0280 - accuracy: 0.9902 - val_loss: 0.3658 - val_accuracy: 0.9061\n",
            "Epoch 9/12\n",
            "393/393 [==============================] - ETA: 0s - loss: 0.0217 - accuracy: 0.9930\n",
            "Epoch 00009: val_loss did not improve from 0.16709\n",
            "393/393 [==============================] - 112s 285ms/step - loss: 0.0217 - accuracy: 0.9930 - val_loss: 0.2033 - val_accuracy: 0.9425\n",
            "Epoch 10/12\n",
            "393/393 [==============================] - ETA: 0s - loss: 0.0225 - accuracy: 0.9921\n",
            "Epoch 00010: val_loss did not improve from 0.16709\n",
            "393/393 [==============================] - 112s 286ms/step - loss: 0.0225 - accuracy: 0.9921 - val_loss: 0.2887 - val_accuracy: 0.9227\n",
            "Epoch 11/12\n",
            "393/393 [==============================] - ETA: 0s - loss: 0.0219 - accuracy: 0.9925\n",
            "Epoch 00011: val_loss did not improve from 0.16709\n",
            "393/393 [==============================] - 112s 286ms/step - loss: 0.0219 - accuracy: 0.9925 - val_loss: 0.3949 - val_accuracy: 0.9093\n",
            "Epoch 12/12\n",
            "393/393 [==============================] - ETA: 0s - loss: 0.0216 - accuracy: 0.9930\n",
            "Epoch 00012: val_loss improved from 0.16709 to 0.16215, saving model to /content/abc.h5\n",
            "393/393 [==============================] - 115s 291ms/step - loss: 0.0216 - accuracy: 0.9930 - val_loss: 0.1621 - val_accuracy: 0.9583\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_gmYx9f9MbIZ"
      },
      "source": [
        "from tensorflow import keras\n",
        "keras.models.save_model(model, \"model.h5\")"
      ],
      "execution_count": 19,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "N5XK_aORMqql",
        "outputId": "e640c2f6-2133-4737-b26f-1d8443aca9a6"
      },
      "source": [
        "model = tf.keras.models.load_model('/content/abc.h5')\n",
        "model.evaluate(val_generator)"
      ],
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "99/99 [==============================] - 22s 220ms/step - loss: 0.1617 - accuracy: 0.9584\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[0.16170307993888855, 0.9583696722984314]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Ok7IkLqhNmdl",
        "outputId": "91d5df26-102f-48d8-85d5-fb7cde022c1f"
      },
      "source": [
        "##-------START OF TESTING CODE----------\n",
        "## run this cell for testing purpose only & after folder name add the test image path.\n",
        "# ex: '/.../.../test_imgs/'+file_name ....just replace the file_name with your image file name.\n",
        "## only for testing single files / images\n",
        "\n",
        "test_images = [f for f in os.listdir('/content/test_imgs')]\n",
        "dataset = np.ndarray(shape=(len(test_images), 200, 200, 3))\n",
        "\n",
        "import cv2\n",
        "\n",
        "for i, file_name in enumerate(test_images):\n",
        "  try:\n",
        "    img=cv2.imread('/content/test_imgs/' + file_name)\n",
        "    img_resize=cv2.resize(img,(200,200))\n",
        "    dataset[i]=np.array(img_resize)/255.0\n",
        "  except:\n",
        "    print(file_name)\n",
        "dataset.shape"
      ],
      "execution_count": 42,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Tomato___Bacterial_spot\n",
            "Grape___healthy\n",
            "Orange___Haunglongbing_(Citrus_greening)\n",
            "Pepper,_bell___healthy\n",
            "Apple___Cedar_apple_rust\n",
            "Cherry_(including_sour)___Powdery_mildew\n",
            "Strawberry___healthy\n",
            "Tomato___Late_blight\n",
            "Tomato___Target_Spot\n",
            "Apple___healthy\n",
            "Grape___Esca_(Black_Measles)\n",
            "Squash___Powdery_mildew\n",
            "Peach___healthy\n",
            "Peach___Bacterial_spot\n",
            "Raspberry___healthy\n",
            "Soybean___healthy\n",
            "Tomato___Early_blight\n",
            "Strawberry___Leaf_scorch\n",
            "Tomato___Tomato_mosaic_virus\n",
            "Tomato___Spider_mites Two-spotted_spider_mite\n",
            "Pepper,_bell___Bacterial_spot\n",
            "Tomato___Leaf_Mold\n",
            "Cherry_(including_sour)___healthy\n",
            "Blueberry___healthy\n",
            "Potato___Late_blight\n",
            "Apple___Apple_scab\n",
            "Potato___healthy\n",
            "Tomato___Tomato_Yellow_Leaf_Curl_Virus\n",
            "Potato___Early_blight\n",
            "Grape___Leaf_blight_(Isariopsis_Leaf_Spot)\n",
            "Apple___Black_rot\n",
            "Tomato___healthy\n",
            "Tomato___Septoria_leaf_spot\n",
            "Grape___Black_rot\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(34, 200, 200, 3)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 42
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ygkxsCVeVGqY"
      },
      "source": [
        "results = model.predict_classes(dataset)\n",
        "final_json = {}\n",
        "for file_name, result in zip(test_images, results):\n",
        "  final_json[file_name] = classes_train[result]\n",
        "\n",
        "\n",
        "import json\n",
        "with open('prediction.json', 'w') as outfile:\n",
        "  json.dump(final_json, outfile)\n",
        "\n"
      ],
      "execution_count": 44,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 16
        },
        "id": "D9g_yfXFXxjb",
        "outputId": "02e086a1-6e85-4bbd-cebd-7df7eedd662e"
      },
      "source": [
        "from google.colab import files\n",
        "files.download('/content/prediction.json')\n",
        "\n",
        "##-------END OF TESTING CODE----------"
      ],
      "execution_count": 48,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "application/javascript": [
              "\n",
              "    async function download(id, filename, size) {\n",
              "      if (!google.colab.kernel.accessAllowed) {\n",
              "        return;\n",
              "      }\n",
              "      const div = document.createElement('div');\n",
              "      const label = document.createElement('label');\n",
              "      label.textContent = `Downloading \"${filename}\": `;\n",
              "      div.appendChild(label);\n",
              "      const progress = document.createElement('progress');\n",
              "      progress.max = size;\n",
              "      div.appendChild(progress);\n",
              "      document.body.appendChild(div);\n",
              "\n",
              "      const buffers = [];\n",
              "      let downloaded = 0;\n",
              "\n",
              "      const channel = await google.colab.kernel.comms.open(id);\n",
              "      // Send a message to notify the kernel that we're ready.\n",
              "      channel.send({})\n",
              "\n",
              "      for await (const message of channel.messages) {\n",
              "        // Send a message to notify the kernel that we're ready.\n",
              "        channel.send({})\n",
              "        if (message.buffers) {\n",
              "          for (const buffer of message.buffers) {\n",
              "            buffers.push(buffer);\n",
              "            downloaded += buffer.byteLength;\n",
              "            progress.value = downloaded;\n",
              "          }\n",
              "        }\n",
              "      }\n",
              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
              "      const a = document.createElement('a');\n",
              "      a.href = window.URL.createObjectURL(blob);\n",
              "      a.download = filename;\n",
              "      div.appendChild(a);\n",
              "      a.click();\n",
              "      div.remove();\n",
              "    }\n",
              "  "
            ],
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "application/javascript": [
              "download(\"download_f64dc978-388f-45c1-8620-56d66f812f2c\", \"prediction.json\", 1764)"
            ],
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "n6ugfrwZoaiX",
        "outputId": "c20057e6-79f2-4bc0-b1c4-14bc997c53b0"
      },
      "source": [
        "import tensorflow as tf\n",
        "model = tf.keras.models.load_model('/content/model.h5')\n",
        "## For TFLite model\n",
        "converter=tf.lite.TFLiteConverter.from_keras_model(model)\n",
        "tflite_model=converter.convert()\n",
        "open('model.tflite', 'wb').write(tflite_model)\n",
        "## For TFLite optimized model\n",
        "converter.optimizations=[tf.lite.Optimize.OPTIMIZE_FOR_SIZE]\n",
        "tflite_opt_model=converter.convert()\n",
        "open('model_opt.tflite', 'wb').write(tflite_opt_model)"
      ],
      "execution_count": 63,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:Assets written to: /tmp/tmp987zu5q8/assets\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:Assets written to: /tmp/tmp987zu5q8/assets\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:Assets written to: /tmp/tmpyx7l0fv6/assets\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "INFO:tensorflow:Assets written to: /tmp/tmpyx7l0fv6/assets\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "246176"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 63
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 16
        },
        "id": "tWE0Vkoiu8Wy",
        "outputId": "c95c9856-b8d4-4292-a185-e15a948168f2"
      },
      "source": [
        "from google.colab import files\n",
        "files.download('model.h5')  ##generated model file\n",
        "files.download('model.tflite') ##generated model tflite converted file\n",
        "files.download('model_opt.tflite') ##generated model tflite converted file"
      ],
      "execution_count": 64,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "application/javascript": [
              "\n",
              "    async function download(id, filename, size) {\n",
              "      if (!google.colab.kernel.accessAllowed) {\n",
              "        return;\n",
              "      }\n",
              "      const div = document.createElement('div');\n",
              "      const label = document.createElement('label');\n",
              "      label.textContent = `Downloading \"${filename}\": `;\n",
              "      div.appendChild(label);\n",
              "      const progress = document.createElement('progress');\n",
              "      progress.max = size;\n",
              "      div.appendChild(progress);\n",
              "      document.body.appendChild(div);\n",
              "\n",
              "      const buffers = [];\n",
              "      let downloaded = 0;\n",
              "\n",
              "      const channel = await google.colab.kernel.comms.open(id);\n",
              "      // Send a message to notify the kernel that we're ready.\n",
              "      channel.send({})\n",
              "\n",
              "      for await (const message of channel.messages) {\n",
              "        // Send a message to notify the kernel that we're ready.\n",
              "        channel.send({})\n",
              "        if (message.buffers) {\n",
              "          for (const buffer of message.buffers) {\n",
              "            buffers.push(buffer);\n",
              "            downloaded += buffer.byteLength;\n",
              "            progress.value = downloaded;\n",
              "          }\n",
              "        }\n",
              "      }\n",
              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
              "      const a = document.createElement('a');\n",
              "      a.href = window.URL.createObjectURL(blob);\n",
              "      a.download = filename;\n",
              "      div.appendChild(a);\n",
              "      a.click();\n",
              "      div.remove();\n",
              "    }\n",
              "  "
            ],
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "application/javascript": [
              "download(\"download_43936423-3124-49d9-9cf0-3b433558b044\", \"model.h5\", 2922528)"
            ],
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "application/javascript": [
              "\n",
              "    async function download(id, filename, size) {\n",
              "      if (!google.colab.kernel.accessAllowed) {\n",
              "        return;\n",
              "      }\n",
              "      const div = document.createElement('div');\n",
              "      const label = document.createElement('label');\n",
              "      label.textContent = `Downloading \"${filename}\": `;\n",
              "      div.appendChild(label);\n",
              "      const progress = document.createElement('progress');\n",
              "      progress.max = size;\n",
              "      div.appendChild(progress);\n",
              "      document.body.appendChild(div);\n",
              "\n",
              "      const buffers = [];\n",
              "      let downloaded = 0;\n",
              "\n",
              "      const channel = await google.colab.kernel.comms.open(id);\n",
              "      // Send a message to notify the kernel that we're ready.\n",
              "      channel.send({})\n",
              "\n",
              "      for await (const message of channel.messages) {\n",
              "        // Send a message to notify the kernel that we're ready.\n",
              "        channel.send({})\n",
              "        if (message.buffers) {\n",
              "          for (const buffer of message.buffers) {\n",
              "            buffers.push(buffer);\n",
              "            downloaded += buffer.byteLength;\n",
              "            progress.value = downloaded;\n",
              "          }\n",
              "        }\n",
              "      }\n",
              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
              "      const a = document.createElement('a');\n",
              "      a.href = window.URL.createObjectURL(blob);\n",
              "      a.download = filename;\n",
              "      div.appendChild(a);\n",
              "      a.click();\n",
              "      div.remove();\n",
              "    }\n",
              "  "
            ],
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "application/javascript": [
              "download(\"download_86a3a636-75c8-407f-a933-4ed2458efc3c\", \"model.tflite\", 942024)"
            ],
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "application/javascript": [
              "\n",
              "    async function download(id, filename, size) {\n",
              "      if (!google.colab.kernel.accessAllowed) {\n",
              "        return;\n",
              "      }\n",
              "      const div = document.createElement('div');\n",
              "      const label = document.createElement('label');\n",
              "      label.textContent = `Downloading \"${filename}\": `;\n",
              "      div.appendChild(label);\n",
              "      const progress = document.createElement('progress');\n",
              "      progress.max = size;\n",
              "      div.appendChild(progress);\n",
              "      document.body.appendChild(div);\n",
              "\n",
              "      const buffers = [];\n",
              "      let downloaded = 0;\n",
              "\n",
              "      const channel = await google.colab.kernel.comms.open(id);\n",
              "      // Send a message to notify the kernel that we're ready.\n",
              "      channel.send({})\n",
              "\n",
              "      for await (const message of channel.messages) {\n",
              "        // Send a message to notify the kernel that we're ready.\n",
              "        channel.send({})\n",
              "        if (message.buffers) {\n",
              "          for (const buffer of message.buffers) {\n",
              "            buffers.push(buffer);\n",
              "            downloaded += buffer.byteLength;\n",
              "            progress.value = downloaded;\n",
              "          }\n",
              "        }\n",
              "      }\n",
              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
              "      const a = document.createElement('a');\n",
              "      a.href = window.URL.createObjectURL(blob);\n",
              "      a.download = filename;\n",
              "      div.appendChild(a);\n",
              "      a.click();\n",
              "      div.remove();\n",
              "    }\n",
              "  "
            ],
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "application/javascript": [
              "download(\"download_227d621e-8957-47b9-822e-36c065dab623\", \"model_opt.tflite\", 246176)"
            ],
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    }
  ]
}