{"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":"
PLANT PATHOLOGY USING TRANSFER LEARNING (ResNet50)","metadata":{}},{"cell_type":"markdown","source":"TABLE OF CONTENTS:\n \n------------------------------------------------------------------------------------------------------ \n \n* Import Required Libraries\n* Load the Images (Train_images), DataFrame (train.csv)\n* Data Augumentation using ImageDataGenerator\n* Create Model (ResNet50)\n* Create Callbacks\n* Fit the model\n* Test the Model\n* Make the Submission\n ","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19"}},{"cell_type":"markdown","source":"-------------","metadata":{}},{"cell_type":"markdown","source":"## 1. IMPORT LIBRARIES","metadata":{}},{"cell_type":"code","source":"#IMPORT REQUIRED LIBRARIES:\n\nfrom tensorflow.keras.layers import Input, Lambda, Dense, Flatten\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.applications.resnet50 import ResNet50\nfrom tensorflow.keras.applications.resnet50 import preprocess_input\nfrom tensorflow.keras.preprocessing import image\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator,load_img\nfrom tensorflow.keras.models import Sequential\nimport numpy as np\nfrom glob import glob\nimport matplotlib.pyplot as plt\nimport pandas as pd","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## 2. DATASET LOCATION","metadata":{}},{"cell_type":"code","source":"TRAIN_PATH = \"../input/plant-pathology-2021-fgvc8/train_images\"\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":"markdown","source":"-----","metadata":{}},{"cell_type":"markdown","source":"## 3. VISUALIZATION","metadata":{}},{"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":"markdown","source":"-----","metadata":{}},{"cell_type":"markdown","source":"## 4. DATA AUGMENTATION","metadata":{}},{"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","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"HEIGHT = 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)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"val_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":"-----","metadata":{}},{"cell_type":"markdown","source":"## 5. CREATE THE RESNET MODEL","metadata":{}},{"cell_type":"code","source":"import tensorflow\ndef create_model():\n \n pretrained = ResNet50(include_top=False, weights='imagenet',input_shape=[HEIGHT,WIDTH, 3])\n \n x = pretrained.output\n x = tensorflow.keras.layers.GlobalAveragePooling2D() (x)\n outputs = tensorflow.keras.layers.Dense(len(classes),activation=\"softmax\", dtype='float32')(x)\n \n model = tensorflow.keras.Model(pretrained.input, outputs)\n return model\n\nmodel = create_model()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.summary()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"-----","metadata":{}},{"cell_type":"markdown","source":"## 6. COMPILE THE MODEL","metadata":{}},{"cell_type":"code","source":"import tensorflow_addons as tfa\n\ndef compile_model(model, lr=0.0001):\n \n optimizer = tensorflow.keras.optimizers.Adam(lr=lr)\n \n loss = tensorflow.keras.losses.CategoricalCrossentropy()\n \n #tf.keras.metrics.CategoricalAccuracy(name='categorical_accuracy')\n metrics = [\n tfa.metrics.F1Score(num_classes = len(classes),average = \"macro\",name = \"f1_score\")\n ]\n\n model.compile(optimizer=optimizer, loss=loss, metrics=metrics)\n\n return model","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"------","metadata":{}},{"cell_type":"markdown","source":"## 7. CREATE CALLBACKS","metadata":{}},{"cell_type":"code","source":"METRIC = \"val_f1_score\"\n\ndef create_callbacks(metric = METRIC):\n \n cpk_path = './best_model.h5'\n \n checkpoint = tensorflow.keras.callbacks.ModelCheckpoint(\n filepath=cpk_path,\n monitor= metric,\n mode='max',\n save_best_only=True,\n verbose=1,\n )\n\n reducelr = tensorflow.keras.callbacks.ReduceLROnPlateau(\n monitor= metric,\n mode='max',\n factor=0.1,\n patience=3,\n verbose=0\n )\n\n earlystop = tensorflow.keras.callbacks.EarlyStopping(\n monitor= metric,\n mode='max',\n patience=10, \n verbose=1\n )\n \n callbacks = [checkpoint, reducelr, earlystop] \n \n return callbacks","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"-------","metadata":{}},{"cell_type":"markdown","source":"## 8. FIT THE MODEL","metadata":{}},{"cell_type":"code","source":"EPOCHS= 3\nVERBOSE =1\n\ntensorflow.keras.backend.clear_session()\n\nwith tensorflow.device('/device:GPU:0'):\n \n model = create_model()\n model = compile_model(model, lr=0.0001)\n \n callbacks = create_callbacks()\n \n history = model.fit(\n train_ds,\n epochs=EPOCHS,\n callbacks=callbacks,\n validation_data = val_ds,\n verbose=VERBOSE\n )","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"------","metadata":{}},{"cell_type":"markdown","source":"## 9. SUBMISSION OF FILE","metadata":{}},{"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":"train_ds.class_indices.items()","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":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}