{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#IMPORT REQUIRED LIBRARIES:\n\nimport numpy as np\nimport pandas as pd\nimport os\nfrom re import search\nimport shutil\nfrom PIL import Image\nimport matplotlib.pyplot as plt\nfrom tqdm import tqdm\nimport cv2\n\nimport tensorflow as tf\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.callbacks import ModelCheckpoint,EarlyStopping\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.layers import Dense,Activation,Flatten, Conv2D, MaxPooling2D","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#IMAGE PATH & DATAFRAME:\n\nTRAIN_PATH = \"../input/resized-plant2021/img_sz_256\"\ntrain_df = pd.read_csv(\"../input/plant-pathology-2021-fgvc8/train.csv\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"count_dict = train_df.labels.value_counts()\nclasses = list(count_dict.index)\nclasses_count = list(count_dict.values)\nprint(\"Number of unique labels: \",len(classes))\nprint(\"-------------------------------------------\")\ntrain_df.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize=(35,15))\nplt.bar(classes,classes_count)\nplt.title(\"Number of instances per class\",fontweight=\"bold\",fontsize=40)\nplt.xlabel(\"Classes\",fontsize = 30)\nplt.xticks(rotation=20,fontsize = 20,fontweight = \"bold\")\nplt.xticks(fontsize = 20,fontweight = \"bold\")\nplt.ylabel(\"Count\",fontsize=30)\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Use the Image Data Generator to import the images from the dataset\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\ntrain_datagen = ImageDataGenerator(rescale = 1/255.,\n    rotation_range=20,\n    width_shift_range=0.2,\n    height_shift_range=0.2,\n    horizontal_flip=True,\n    validation_split = 0.2,\n    zoom_range = 0.2,\n    shear_range = 0.2,\n    vertical_flip = False)\n\n\nHEIGHT = 124\nWIDTH=124\nSEED = 143\nBATCH_SIZE=32\ntrain_ds = train_datagen.flow_from_dataframe(\n    train_df,\n    directory = TRAIN_PATH,\n    x_col = \"image\",\n    y_col = \"labels\",\n    target_size = (HEIGHT,WIDTH),\n    class_mode='categorical',\n    batch_size = BATCH_SIZE,\n    subset = \"training\",\n    shuffle = True,\n    seed = SEED,\n    validate_filenames = False\n)\n\n\nval_ds = train_datagen.flow_from_dataframe(\n    train_df,\n    directory = TRAIN_PATH,\n    x_col = \"image\",\n    y_col = \"labels\",\n    target_size = (HEIGHT,WIDTH),\n    class_mode='categorical',\n    batch_size = BATCH_SIZE,\n    subset = \"validation\",\n    shuffle = True,\n    seed = SEED,\n    validate_filenames = False\n)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"model=Sequential()\nmodel.add(Conv2D(64,(3,3),activation='relu',padding='same',input_shape=(HEIGHT,WIDTH,3)))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Conv2D(64,(3,3),activation='relu',padding='same'))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Conv2D(64,(3,3),activation='relu',padding='same'))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Conv2D(128,(3,3),activation='relu',padding='same'))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Flatten())\nmodel.add(Dense(12,activation='softmax'))\n\n# Compile the Model\nmodel.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),\n    loss='categorical_crossentropy',\n    metrics=['accuracy'])\nmodel.summary()","metadata":{}},{"cell_type":"code","source":"model=Sequential()\nmodel.add(Conv2D(64,(3,3),activation='relu',padding='same',input_shape=(HEIGHT,WIDTH,3)))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Conv2D(64,(3,3),activation='relu',padding='same'))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Conv2D(64,(3,3),activation='relu',padding='same'))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Conv2D(128,(3,3),activation='relu',padding='same'))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Flatten())\nmodel.add(Dense(12,activation='softmax'))\n\n# Compile the Model\nmodel.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),\n    loss='categorical_crossentropy',\n    metrics=['accuracy'])\nmodel.summary()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"checkpoint=ModelCheckpoint(r'D:\\Python37\\Projects\\Foliar diseases in apple trees\\models\\apple2.h5',\n                          monitor='val_loss',\n                          mode='min',\n                          save_best_only=True,\n                          verbose=1)\nearlystop=EarlyStopping(monitor='val_loss',\n                       min_delta=0,\n                       patience=10,\n                       verbose=1,\n                       restore_best_weights=True)\n\ncallbacks=[checkpoint,earlystop]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model_history=model.fit_generator(train_ds,validation_data=val_ds,\n                                 epochs=30,\n                                 steps_per_epoch=train_ds.samples//128,\n                                 validation_steps=val_ds.samples//128,\n                                 callbacks=callbacks)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.read_csv('/kaggle/input/plant-pathology-2021-fgvc8/sample_submission.csv')\nsubmission.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_datagen = ImageDataGenerator(\n    rescale = 1./255\n)\nINPUT_SIZE = (124,124,3)\ntest_generator =  test_datagen.flow_from_dataframe(\n    submission,\n    directory=\"../input/plant-pathology-2021-fgvc8/test_images\",\n    x_col='image',\n    y_col=None,\n    class_mode=None,\n    target_size=INPUT_SIZE[:2]\n)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_key(val):\n    for key, value in train_ds.class_indices.items():\n        if val == value:\n            return key","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"preds = model.predict(test_generator)\nprint(preds)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_preds_to_labels(preds):\n    pred_lists = []\n    for pred in preds:\n        pred_list = []\n        health = (pred>=0.4)\n        \n        # get healthy\n        if health.sum()==0:\n            label = 'healthy'\n            pred_list.append(label)\n            \n        elif pred[2]>=0.5:\n            label = 'healthy'\n            pred_list.append(label)\n            \n        # get eles label\n        else:\n            for j, sub in enumerate(pred):\n                if sub>=0.28:\n                    label = get_key(j)\n                    pred_list.append(label)\n                               \n        pred_lists.append(' '.join(pred_list))\n    return pred_lists","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"preds_list = get_preds_to_labels(preds)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission['labels'] = preds_list\nsubmission.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.to_csv('submission.csv', index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}