plant-disease-detection-using-keras.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "_uuid": "1020827e241ac87ffdf8e0f8762a6885bdc28fbc"
   },
   "source": [
    "Import neccessary packages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5"
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pickle\n",
    "import cv2\n",
    "from os import listdir\n",
    "from sklearn.preprocessing import LabelBinarizer\n",
    "from keras.models import Sequential\n",
    "from keras.layers.normalization import BatchNormalization\n",
    "from keras.layers.convolutional import Conv2D\n",
    "from keras.layers.convolutional import MaxPooling2D\n",
    "from keras.layers.core import Activation, Flatten, Dropout, Dense\n",
    "from keras import backend as K\n",
    "from keras.preprocessing.image import ImageDataGenerator\n",
    "from keras.optimizers import Adam\n",
    "from keras.preprocessing import image\n",
    "from keras.preprocessing.image import img_to_array\n",
    "from sklearn.preprocessing import MultiLabelBinarizer\n",
    "from sklearn.model_selection import train_test_split\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "_uuid": "7c3354a78e21a1a62ad0c4689d0ab3238fb760d4"
   },
   "outputs": [],
   "source": [
    "EPOCHS = 25\n",
    "INIT_LR = 1e-3\n",
    "BS = 32\n",
    "default_image_size = tuple((256, 256))\n",
    "image_size = 0\n",
    "directory_root = 'plantdisease'\n",
    "width=256\n",
    "height=256\n",
    "depth=3"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_uuid": "2bf7ac0a0b805946f844a48e55d5281403e53f57"
   },
   "source": [
    "Function to convert images to array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "_uuid": "c9c3e60b13ace6c8f3e54336e12f9970fde438a3"
   },
   "outputs": [],
   "source": [
    "def convert_image_to_array(image_dir):\n",
    "    try:\n",
    "        image = cv2.imread(image_dir)\n",
    "        if image is not None :\n",
    "            image = cv2.resize(image, default_image_size)   \n",
    "            return img_to_array(image)\n",
    "        else :\n",
    "            return np.array([])\n",
    "    except Exception as e:\n",
    "        print(f\"Error : {e}\")\n",
    "        return None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['PlantVillage']"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "listdir(directory_root)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_uuid": "24d42b87fad54a9556f78357ce673cc5152468c1"
   },
   "source": [
    "Fetch images from directory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "_uuid": "bb8d4c343314028f52ae3c3a840478a834a16c95"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[INFO] Loading images ...\n",
      "[INFO] Processing Pepper__bell___Bacterial_spot ...\n",
      "[INFO] Processing Pepper__bell___healthy ...\n",
      "[INFO] Processing Potato___Early_blight ...\n",
      "[INFO] Processing Potato___healthy ...\n",
      "[INFO] Processing Potato___Late_blight ...\n",
      "[INFO] Processing Tomato_Bacterial_spot ...\n",
      "[INFO] Processing Tomato_Early_blight ...\n",
      "[INFO] Processing Tomato_healthy ...\n",
      "[INFO] Processing Tomato_Late_blight ...\n",
      "[INFO] Processing Tomato_Leaf_Mold ...\n",
      "[INFO] Processing Tomato_Septoria_leaf_spot ...\n",
      "[INFO] Processing Tomato_Spider_mites_Two_spotted_spider_mite ...\n",
      "[INFO] Processing Tomato__Target_Spot ...\n",
      "[INFO] Processing Tomato__Tomato_mosaic_virus ...\n",
      "[INFO] Processing Tomato__Tomato_YellowLeaf__Curl_Virus ...\n",
      "[INFO] Image loading completed\n"
     ]
    }
   ],
   "source": [
    "image_list, label_list = [], []\n",
    "try:\n",
    "    print(\"[INFO] Loading images ...\")\n",
    "    root_dir = listdir(directory_root)\n",
    "    for directory in root_dir :\n",
    "        # remove .DS_Store from list\n",
    "        if directory == \".DS_Store\" :\n",
    "            root_dir.remove(directory)\n",
    "\n",
    "    for plant_folder in root_dir :\n",
    "        plant_disease_folder_list = listdir(f\"{directory_root}/{plant_folder}\")\n",
    "        \n",
    "        for disease_folder in plant_disease_folder_list :\n",
    "            # remove .DS_Store from list\n",
    "            if disease_folder == \".DS_Store\" :\n",
    "                plant_disease_folder_list.remove(disease_folder)\n",
    "\n",
    "        for plant_disease_folder in plant_disease_folder_list:\n",
    "            print(f\"[INFO] Processing {plant_disease_folder} ...\")\n",
    "            plant_disease_image_list = listdir(f\"{directory_root}/{plant_folder}/{plant_disease_folder}\")\n",
    "           \n",
    "                \n",
    "            for single_plant_disease_image in plant_disease_image_list :\n",
    "                if single_plant_disease_image == \".DS_Store\" :\n",
    "                    plant_disease_image_list.remove(single_plant_disease_image)\n",
    "\n",
    "            for image in plant_disease_image_list[:200]:\n",
    "                image_directory = f\"{directory_root}/{plant_folder}/{plant_disease_folder}/{image}\"\n",
    "                if image_directory.endswith(\".jpg\") == True or image_directory.endswith(\".JPG\") == True:\n",
    "                    image_list.append(convert_image_to_array(image_directory))\n",
    "                    label_list.append(plant_disease_folder)\n",
    "    print(\"[INFO] Image loading completed\")  \n",
    "except Exception as e:\n",
    "    print(f\"Error : {e}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_uuid": "35c4b76d33e0263523e479657580104532f81d6e"
   },
   "source": [
    "Get Size of Processed Image"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "_uuid": "6ee1ad9c422f112ec2862699b5c0f68b8d658123"
   },
   "outputs": [],
   "source": [
    "image_size = len(image_list)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_uuid": "905b41b226f3fd82a88e67821eb42a07f24b31f7"
   },
   "source": [
    "Transform Image Labels uisng [Scikit Learn](http://scikit-learn.org/)'s LabelBinarizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "_uuid": "904ff893fe14f5060dd9e7be2ccf96ec793597e5"
   },
   "outputs": [],
   "source": [
    "label_binarizer = LabelBinarizer()\n",
    "image_labels = label_binarizer.fit_transform(label_list)\n",
    "pickle.dump(label_binarizer,open('label_transform.pkl', 'wb'))\n",
    "n_classes = len(label_binarizer.classes_)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_uuid": "f860c29a1d714f06d25e6a0c5bca94739e5d24cc"
   },
   "source": [
    "Print the classes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "_uuid": "0f876397c40c3c8aa09772a92fd60481fc9ba268"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Pepper__bell___Bacterial_spot' 'Pepper__bell___healthy'\n",
      " 'Potato___Early_blight' 'Potato___Late_blight' 'Potato___healthy'\n",
      " 'Tomato_Bacterial_spot' 'Tomato_Early_blight' 'Tomato_Late_blight'\n",
      " 'Tomato_Leaf_Mold' 'Tomato_Septoria_leaf_spot'\n",
      " 'Tomato_Spider_mites_Two_spotted_spider_mite' 'Tomato__Target_Spot'\n",
      " 'Tomato__Tomato_YellowLeaf__Curl_Virus' 'Tomato__Tomato_mosaic_virus'\n",
      " 'Tomato_healthy']\n"
     ]
    }
   ],
   "source": [
    "print(label_binarizer.classes_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "_uuid": "6cd9c977b3d164a5570a0c24fdd8624adb9d56b8"
   },
   "outputs": [],
   "source": [
    "np_image_list = np.array(image_list, dtype=np.float16) / 225.0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {
    "_uuid": "9f4829560fdfa218cee18c1cfb2eb9452ef180e5"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[INFO] Spliting data to train, test\n"
     ]
    }
   ],
   "source": [
    "print(\"[INFO] Spliting data to train, test\")\n",
    "x_train, x_test, y_train, y_test = train_test_split(np_image_list, image_labels, test_size=0.2, random_state = 42) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {
    "_uuid": "eec8afa64e676d52c814fc8e096955a60f13b6c5"
   },
   "outputs": [],
   "source": [
    "aug = ImageDataGenerator(\n",
    "    rotation_range=25, width_shift_range=0.1,\n",
    "    height_shift_range=0.1, shear_range=0.2, \n",
    "    zoom_range=0.2,horizontal_flip=True, \n",
    "    fill_mode=\"nearest\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "_cell_guid": "79c7e3d0-c299-4dcb-8224-4455121ee9b0",
    "_uuid": "d629ff2d2480ee46fbb7e2d37f6b5fab8052498a"
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'n_classes' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-4-8fc6d8bc5645>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m     31\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mBatchNormalization\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     32\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mDropout\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m0.5\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 33\u001b[0;31m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mDense\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mn_classes\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     34\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mActivation\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"softmax\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mNameError\u001b[0m: name 'n_classes' is not defined"
     ]
    }
   ],
   "source": [
    "model = Sequential()\n",
    "inputShape = (height, width, depth)\n",
    "chanDim = -1\n",
    "if K.image_data_format() == \"channels_first\":\n",
    "    inputShape = (depth, height, width)\n",
    "    chanDim = 1\n",
    "model.add(Conv2D(32, (3, 3), padding=\"same\",input_shape=inputShape))\n",
    "model.add(Activation(\"relu\"))\n",
    "model.add(BatchNormalization(axis=chanDim))\n",
    "model.add(MaxPooling2D(pool_size=(3, 3)))\n",
    "model.add(Dropout(0.25))\n",
    "model.add(Conv2D(64, (3, 3), padding=\"same\"))\n",
    "model.add(Activation(\"relu\"))\n",
    "model.add(BatchNormalization(axis=chanDim))\n",
    "model.add(Conv2D(64, (3, 3), padding=\"same\"))\n",
    "model.add(Activation(\"relu\"))\n",
    "model.add(BatchNormalization(axis=chanDim))\n",
    "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
    "model.add(Dropout(0.25))\n",
    "model.add(Conv2D(128, (3, 3), padding=\"same\"))\n",
    "model.add(Activation(\"relu\"))\n",
    "model.add(BatchNormalization(axis=chanDim))\n",
    "model.add(Conv2D(128, (3, 3), padding=\"same\"))\n",
    "model.add(Activation(\"relu\"))\n",
    "model.add(BatchNormalization(axis=chanDim))\n",
    "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
    "model.add(Dropout(0.25))\n",
    "model.add(Flatten())\n",
    "model.add(Dense(1024))\n",
    "model.add(Activation(\"relu\"))\n",
    "model.add(BatchNormalization())\n",
    "model.add(Dropout(0.5))\n",
    "model.add(Dense(n_classes))\n",
    "model.add(Activation(\"softmax\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_uuid": "53b13c03e4cea6dc2453a84e254b806ebeed2d99"
   },
   "source": [
    "Model Summary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "_uuid": "1e1523a834fbf872940171fbdefb3dcce2b5f31b"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "_________________________________________________________________\n",
      "Layer (type)                 Output Shape              Param #   \n",
      "=================================================================\n",
      "conv2d_6 (Conv2D)            (None, 256, 256, 32)      896       \n",
      "_________________________________________________________________\n",
      "activation_7 (Activation)    (None, 256, 256, 32)      0         \n",
      "_________________________________________________________________\n",
      "batch_normalization_7 (Batch (None, 256, 256, 32)      128       \n",
      "_________________________________________________________________\n",
      "max_pooling2d_4 (MaxPooling2 (None, 85, 85, 32)        0         \n",
      "_________________________________________________________________\n",
      "dropout_5 (Dropout)          (None, 85, 85, 32)        0         \n",
      "_________________________________________________________________\n",
      "conv2d_7 (Conv2D)            (None, 85, 85, 64)        18496     \n",
      "_________________________________________________________________\n",
      "activation_8 (Activation)    (None, 85, 85, 64)        0         \n",
      "_________________________________________________________________\n",
      "batch_normalization_8 (Batch (None, 85, 85, 64)        256       \n",
      "_________________________________________________________________\n",
      "conv2d_8 (Conv2D)            (None, 85, 85, 64)        36928     \n",
      "_________________________________________________________________\n",
      "activation_9 (Activation)    (None, 85, 85, 64)        0         \n",
      "_________________________________________________________________\n",
      "batch_normalization_9 (Batch (None, 85, 85, 64)        256       \n",
      "_________________________________________________________________\n",
      "max_pooling2d_5 (MaxPooling2 (None, 42, 42, 64)        0         \n",
      "_________________________________________________________________\n",
      "dropout_6 (Dropout)          (None, 42, 42, 64)        0         \n",
      "_________________________________________________________________\n",
      "conv2d_9 (Conv2D)            (None, 42, 42, 128)       73856     \n",
      "_________________________________________________________________\n",
      "activation_10 (Activation)   (None, 42, 42, 128)       0         \n",
      "_________________________________________________________________\n",
      "batch_normalization_10 (Batc (None, 42, 42, 128)       512       \n",
      "_________________________________________________________________\n",
      "conv2d_10 (Conv2D)           (None, 42, 42, 128)       147584    \n",
      "_________________________________________________________________\n",
      "activation_11 (Activation)   (None, 42, 42, 128)       0         \n",
      "_________________________________________________________________\n",
      "batch_normalization_11 (Batc (None, 42, 42, 128)       512       \n",
      "_________________________________________________________________\n",
      "max_pooling2d_6 (MaxPooling2 (None, 21, 21, 128)       0         \n",
      "_________________________________________________________________\n",
      "dropout_7 (Dropout)          (None, 21, 21, 128)       0         \n",
      "_________________________________________________________________\n",
      "flatten_2 (Flatten)          (None, 56448)             0         \n",
      "_________________________________________________________________\n",
      "dense_2 (Dense)              (None, 1024)              57803776  \n",
      "_________________________________________________________________\n",
      "activation_12 (Activation)   (None, 1024)              0         \n",
      "_________________________________________________________________\n",
      "batch_normalization_12 (Batc (None, 1024)              4096      \n",
      "_________________________________________________________________\n",
      "dropout_8 (Dropout)          (None, 1024)              0         \n",
      "_________________________________________________________________\n",
      "dense_3 (Dense)              (None, 15)                15375     \n",
      "_________________________________________________________________\n",
      "activation_13 (Activation)   (None, 15)                0         \n",
      "=================================================================\n",
      "Total params: 58,102,671\n",
      "Trainable params: 58,099,791\n",
      "Non-trainable params: 2,880\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "_uuid": "b21dffee32c325136b4ea23ac511049723f34a24"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[INFO] training network...\n"
     ]
    }
   ],
   "source": [
    "opt = Adam(lr=INIT_LR, decay=INIT_LR / EPOCHS)\n",
    "# distribution\n",
    "model.compile(loss=\"binary_crossentropy\", optimizer=opt,metrics=[\"accuracy\"])\n",
    "# train the network\n",
    "print(\"[INFO] training network...\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "_uuid": "1a13efc5ded339fc3c0d9e61041e8ca555362db0"
   },
   "outputs": [],
   "source": [
    "history = model.fit_generator(\n",
    "    aug.flow(x_train, y_train, batch_size=BS),\n",
    "    validation_data=(x_test, y_test),\n",
    "    steps_per_epoch=len(x_train) // BS,\n",
    "    epochs=EPOCHS, \n",
    "    verbose=1\n",
    "    )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_uuid": "1495fea08b37e4d4293f975ba30e6c1fc7a85ed9"
   },
   "source": [
    "Plot the train and val curve"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "_uuid": "0af5e0f23657a4effc2d21cf8e840e81f42ec8e7"
   },
   "outputs": [],
   "source": [
    "acc = history.history['acc']\n",
    "val_acc = history.history['val_acc']\n",
    "loss = history.history['loss']\n",
    "val_loss = history.history['val_loss']\n",
    "epochs = range(1, len(acc) + 1)\n",
    "#Train and validation accuracy\n",
    "plt.plot(epochs, acc, 'b', label='Training accurarcy')\n",
    "plt.plot(epochs, val_acc, 'r', label='Validation accurarcy')\n",
    "plt.title('Training and Validation accurarcy')\n",
    "plt.legend()\n",
    "\n",
    "plt.figure()\n",
    "#Train and validation loss\n",
    "plt.plot(epochs, loss, 'b', label='Training loss')\n",
    "plt.plot(epochs, val_loss, 'r', label='Validation loss')\n",
    "plt.title('Training and Validation loss')\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_uuid": "9ca1a4489bd624c69a13cd37c0c2306ac8de55c2"
   },
   "source": [
    "Model Accuracy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "_uuid": "bb44f3d0b7e2862bc7d1a032612ebfd48212c1fe"
   },
   "outputs": [],
   "source": [
    "print(\"[INFO] Calculating model accuracy\")\n",
    "scores = model.evaluate(x_test, y_test)\n",
    "print(f\"Test Accuracy: {scores[1]*100}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "_uuid": "2a1f759db8afe933e62fe4cf8332cb303bb11be8"
   },
   "source": [
    "Save model using Pickle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "_uuid": "5cdf06adf492d79ed28fbdc36e02ad7489c7b33e"
   },
   "outputs": [],
   "source": [
    "# save the model to disk\n",
    "print(\"[INFO] Saving model...\")\n",
    "pickle.dump(model,open('cnn_model.pkl', 'wb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "from keras.models import load_model\n",
    "model_disease=load_model(\"cnn_model.h5\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 172,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['Pepper__bell___Bacterial_spot' 'Pepper__bell___healthy'\n",
      " 'Potato___Early_blight' 'Potato___Late_blight' 'Potato___healthy'\n",
      " 'Tomato_Bacterial_spot' 'Tomato_Early_blight' 'Tomato_Late_blight'\n",
      " 'Tomato_Leaf_Mold' 'Tomato_Septoria_leaf_spot'\n",
      " 'Tomato_Spider_mites_Two_spotted_spider_mite' 'Tomato__Target_Spot'\n",
      " 'Tomato__Tomato_YellowLeaf__Curl_Virus' 'Tomato__Tomato_mosaic_virus'\n",
      " 'Tomato_healthy']\n"
     ]
    }
   ],
   "source": [
    "print(label_binarizer.classes_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "loaded_model = pickle.load(open('Folders/cnn_model.pkl', 'rb'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "model_disease=loaded_model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "image_dir=\"plantdisease/Validation_Set/Potato___Early_blight/1d301622-e359-49d5-b4ca-6837f254fd1b___RS_Early.B 6719.JPG\"\n",
    "\n",
    "im=convert_image_to_array(image_dir)\n",
    "np_image_li = np.array(im, dtype=np.float16) / 225.0\n",
    "npp_image = np.expand_dims(np_image_li, axis=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[2.6678255e-01 1.1153113e-06 4.5579544e-01 1.1362200e-05 1.1805475e-10\n",
      "  7.7005342e-07 1.6653335e-04 2.6217926e-01 2.0812025e-04 1.4749763e-02\n",
      "  3.0556703e-11 1.0746547e-10 1.6307396e-06 1.5610477e-06 1.0193537e-04]]\n"
     ]
    }
   ],
   "source": [
    "result=model_disease.predict(npp_image)\n",
    "print(result)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "probability:0.45579544\n",
      "Potato___Early_blight\n"
     ]
    }
   ],
   "source": [
    "itemindex = np.where(result==np.max(result))\n",
    "print(\"probability:\"+str(np.max(result))+\"\\n\"+label_binarizer.classes_[itemindex[1][0]])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}