{"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":"markdown","source":"<h1><center> 🍎 Classify foliar diseases in apple trees</center></h1>","metadata":{}},{"cell_type":"markdown","source":"# 1. Problem Statement ？\n\nApples are one of the most important temperate fruit crops in the world. Foliar (leaf) diseases pose a major threat to the overall productivity and quality of apple orchards. The current process for disease diagnosis in apple orchards is based on manual scouting by humans, which is time-consuming and expensive.\n\nThe main objective of the competition is to develop machine learning-based models to accurately classify a given leaf image from the test dataset to a particular disease category, and to identify an individual disease from multiple disease symptoms on a single leaf image.\n","metadata":{}},{"cell_type":"markdown","source":"## libraries ","metadata":{}},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\n%matplotlib inline\nimport seaborn as sns\nimport matplotlib.pyplot as plt\nimport cv2\nimport os\nimport warnings\nwarnings.filterwarnings('ignore')\nimport tensorflow as tf\nimport random\nimport albumentations as A\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.layers import Dense,Activation,Flatten, Conv2D, MaxPooling2D\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.callbacks import ModelCheckpoint,EarlyStopping","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:15:31.999249Z","iopub.execute_input":"2022-02-17T08:15:31.999662Z","iopub.status.idle":"2022-02-17T08:15:32.013881Z","shell.execute_reply.started":"2022-02-17T08:15:31.99963Z","shell.execute_reply":"2022-02-17T08:15:32.013123Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 2. About Dataset","metadata":{}},{"cell_type":"code","source":"train_image_path = '../input/plant-pathology-2021-fgvc8/train_images'\ntest_image_path = '../input/plant-pathology-2021-fgvc8/test_images'\ntrain_df_path = '../input/plant-pathology-2021-fgvc8/train.csv'\ntest_df_path = '../input/plant-pathology-2021-fgvc8/sample_submission.csv'","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:15:32.015206Z","iopub.execute_input":"2022-02-17T08:15:32.015679Z","iopub.status.idle":"2022-02-17T08:15:32.029463Z","shell.execute_reply.started":"2022-02-17T08:15:32.015647Z","shell.execute_reply":"2022-02-17T08:15:32.028367Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"> 📌**Note**:\n* `train.csv` contains information about the image files available in `train_images`. It contains 18632 rows(images) with 2 columns i.e (image , labels )\n* `test.csv` The test set images. This competition has a hidden test set: only three images are provided here as samples while the remaining 5,000 images will be available to your notebook once it is submitted.","metadata":{}},{"cell_type":"code","source":"df_train = pd.read_csv(train_df_path)\ndf_test=pd.read_csv(test_df_path)","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:15:32.03115Z","iopub.execute_input":"2022-02-17T08:15:32.031622Z","iopub.status.idle":"2022-02-17T08:15:32.081403Z","shell.execute_reply.started":"2022-02-17T08:15:32.03159Z","shell.execute_reply":"2022-02-17T08:15:32.080256Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_test","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:15:32.082812Z","iopub.execute_input":"2022-02-17T08:15:32.083267Z","iopub.status.idle":"2022-02-17T08:15:32.096289Z","shell.execute_reply.started":"2022-02-17T08:15:32.083235Z","shell.execute_reply":"2022-02-17T08:15:32.094803Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_train.labels.value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize=(15,12))\nlabels = sns.barplot(df_train.labels.value_counts().index,df_train.labels.value_counts())\nfor item in labels.get_xticklabels():\n    item.set_rotation(45)","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:15:32.121311Z","iopub.execute_input":"2022-02-17T08:15:32.121642Z","iopub.status.idle":"2022-02-17T08:15:32.442927Z","shell.execute_reply.started":"2022-02-17T08:15:32.121611Z","shell.execute_reply":"2022-02-17T08:15:32.442173Z"},"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"> 📌**Note**:\n* We have multiple labels for eg. label can be **scab** or **scab and rust**\n* Main labels are - **scb** , **healthy** , **frog_eye_leaf_spot** , **rust** , **complex** and **powdery_mildew**","metadata":{}},{"cell_type":"markdown","source":"## Batch Visualisation of Images ","metadata":{}},{"cell_type":"code","source":"def batch_visualize(df,batch_size,path):\n    sample_df = df_train.sample(9)\n    image_names = sample_df[\"image\"].values\n    labels = sample_df[\"labels\"].values\n    plt.figure(figsize=(16, 12))\n    \n    for image_ind, (image_name, label) in enumerate(zip(image_names, labels)):\n        plt.subplot(3, 3, image_ind + 1)\n        image = cv2.imread(os.path.join(path, image_name))\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n        plt.imshow(image)\n        plt.title(f\"{label}\", fontsize=12)\n        plt.axis(\"off\")\n    plt.show()\n    \nbatch_visualize(df_train,9,train_image_path)","metadata":{"execution":{"iopub.status.busy":"2022-02-17T09:35:58.936208Z","iopub.execute_input":"2022-02-17T09:35:58.936597Z","iopub.status.idle":"2022-02-17T09:35:58.955148Z","shell.execute_reply.started":"2022-02-17T09:35:58.936566Z","shell.execute_reply":"2022-02-17T09:35:58.953598Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Batch visualisation with labels","metadata":{}},{"cell_type":"code","source":"def batch_visualize_with_label(df,batch_size,path,label): \n    sample_df = df_train[df_train[\"labels\"]==label].sample(9)\n    image_names = sample_df[\"image\"].values\n    labels = sample_df[\"labels\"].values\n    plt.figure(figsize=(16, 12))\n    \n    for image_ind, (image_name, label) in enumerate(zip(image_names, labels)):\n        plt.subplot(3, 3, image_ind + 1)\n        image = cv2.imread(os.path.join(path, image_name))\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n        plt.imshow(image)\n        plt.axis(\"off\")\n    plt.show()","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:15:43.601476Z","iopub.execute_input":"2022-02-17T08:15:43.601887Z","iopub.status.idle":"2022-02-17T08:15:43.613708Z","shell.execute_reply.started":"2022-02-17T08:15:43.601848Z","shell.execute_reply":"2022-02-17T08:15:43.611917Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Visualise healthy leaves","metadata":{}},{"cell_type":"code","source":"batch_visualize_with_label(df_train,9,train_image_path,'healthy')","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:15:43.617296Z","iopub.execute_input":"2022-02-17T08:15:43.617789Z","iopub.status.idle":"2022-02-17T08:15:54.734022Z","shell.execute_reply.started":"2022-02-17T08:15:43.617751Z","shell.execute_reply":"2022-02-17T08:15:54.73314Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Visualise scab leaves ","metadata":{}},{"cell_type":"code","source":"batch_visualize_with_label(df_train,9,train_image_path,'scab')","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:15:54.735505Z","iopub.execute_input":"2022-02-17T08:15:54.735929Z","iopub.status.idle":"2022-02-17T08:16:05.955897Z","shell.execute_reply.started":"2022-02-17T08:15:54.735887Z","shell.execute_reply":"2022-02-17T08:16:05.955095Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Visualise frog_eye_leaf_spot  leaves","metadata":{}},{"cell_type":"code","source":"batch_visualize_with_label(df_train,9,train_image_path,'frog_eye_leaf_spot')","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:16:05.957146Z","iopub.execute_input":"2022-02-17T08:16:05.957572Z","iopub.status.idle":"2022-02-17T08:16:16.571965Z","shell.execute_reply.started":"2022-02-17T08:16:05.957528Z","shell.execute_reply":"2022-02-17T08:16:16.571097Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Visualise rust leaves ","metadata":{}},{"cell_type":"code","source":"batch_visualize_with_label(df_train,9,train_image_path,'rust')","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:16:16.573253Z","iopub.execute_input":"2022-02-17T08:16:16.5737Z","iopub.status.idle":"2022-02-17T08:16:26.743138Z","shell.execute_reply.started":"2022-02-17T08:16:16.573655Z","shell.execute_reply":"2022-02-17T08:16:26.742181Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Visualise complex leaves","metadata":{}},{"cell_type":"code","source":"batch_visualize_with_label(df_train,9,train_image_path,'complex')","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:16:26.744344Z","iopub.execute_input":"2022-02-17T08:16:26.744826Z","iopub.status.idle":"2022-02-17T08:16:36.959903Z","shell.execute_reply.started":"2022-02-17T08:16:26.744783Z","shell.execute_reply":"2022-02-17T08:16:36.958893Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### Visualise powdery_mildew leaves","metadata":{}},{"cell_type":"code","source":"batch_visualize_with_label(df_train,9,train_image_path,'powdery_mildew')","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:16:36.961154Z","iopub.execute_input":"2022-02-17T08:16:36.961583Z","iopub.status.idle":"2022-02-17T08:16:47.949537Z","shell.execute_reply.started":"2022-02-17T08:16:36.961552Z","shell.execute_reply":"2022-02-17T08:16:47.947876Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# 3. Tensorflow Dataset Generation","metadata":{}},{"cell_type":"code","source":"HEIGHT = 128\nWIDTH=128\nSEED = 45\nBATCH_SIZE= 64\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\ntrain_dataset = train_datagen.flow_from_dataframe(\n    df_train,\n    directory = train_image_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\nvalidation_dataset = train_datagen.flow_from_dataframe(\n    df_train,\n    directory = train_image_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)\n\ntest_datagen = ImageDataGenerator(\n    rescale = 1./255\n)\nINPUT_SIZE = (HEIGHT,WIDTH,3)\ntest_dataset=test_datagen.flow_from_dataframe(\n    df_test,\n    directory=test_image_path,\n    x_col='image',\n    y_col=None,\n    class_mode=None,\n    target_size=INPUT_SIZE[:2]\n)\n","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:16:47.951401Z","iopub.execute_input":"2022-02-17T08:16:47.951876Z","iopub.status.idle":"2022-02-17T08:16:48.088586Z","shell.execute_reply.started":"2022-02-17T08:16:47.951834Z","shell.execute_reply":"2022-02-17T08:16:48.087441Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"> Refer Tensorflow docs for more information [here](https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/image/ImageDataGenerator)","metadata":{}},{"cell_type":"markdown","source":"# 4. Convolutional Neural Networks ","metadata":{}},{"cell_type":"code","source":"model=Sequential()\nmodel.add(Conv2D(32,(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'))","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:16:48.090159Z","iopub.execute_input":"2022-02-17T08:16:48.090803Z","iopub.status.idle":"2022-02-17T08:16:48.185102Z","shell.execute_reply.started":"2022-02-17T08:16:48.090754Z","shell.execute_reply":"2022-02-17T08:16:48.183898Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),\n    loss='categorical_crossentropy',\n    metrics=['accuracy'])\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:16:48.186891Z","iopub.execute_input":"2022-02-17T08:16:48.18761Z","iopub.status.idle":"2022-02-17T08:16:48.215926Z","shell.execute_reply.started":"2022-02-17T08:16:48.187558Z","shell.execute_reply":"2022-02-17T08:16:48.214038Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"checkpoint_path = \"training_1/cp.ckpt\"\ncheckpoint_dir = os.path.dirname(checkpoint_path)\n\n# Create a callback that saves the model's weights\ncp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_path,\n                                                 save_weights_only=True,\n                                                 verbose=1)","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:16:48.217679Z","iopub.execute_input":"2022-02-17T08:16:48.218112Z","iopub.status.idle":"2022-02-17T08:16:48.226133Z","shell.execute_reply.started":"2022-02-17T08:16:48.218076Z","shell.execute_reply":"2022-02-17T08:16:48.224433Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model_history=model.fit_generator(train_dataset,\n                                  validation_data=validation_dataset,\n                                  epochs=5,\n                                  steps_per_epoch=train_dataset.samples//128,\n                                 validation_steps=validation_dataset.samples//128,\n                                 callbacks=[cp_callback]\n                                 )","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:16:48.228158Z","iopub.execute_input":"2022-02-17T08:16:48.229031Z","iopub.status.idle":"2022-02-17T08:35:57.025066Z","shell.execute_reply.started":"2022-02-17T08:16:48.228909Z","shell.execute_reply":"2022-02-17T08:35:57.021726Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Prediction","metadata":{}},{"cell_type":"code","source":"train_dataset.class_indices.items()","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:35:57.027567Z","iopub.status.idle":"2022-02-17T08:35:57.028499Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"preds = model.predict(test_dataset)\nprint(preds)","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:35:57.029784Z","iopub.status.idle":"2022-02-17T08:35:57.03089Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"preds_disease_ind=np.argmax(preds, axis=-1)","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:35:57.032454Z","iopub.status.idle":"2022-02-17T08:35:57.033385Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"preds_disease_ind","metadata":{"execution":{"iopub.status.busy":"2022-02-17T08:35:57.034867Z","iopub.status.idle":"2022-02-17T08:35:57.035827Z"},"trusted":true},"execution_count":null,"outputs":[]}]}