{"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":"#Importing required libraries\nimport os\nimport gc\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport numpy as np\nimport pandas as pd \n\nfrom sklearn.model_selection import train_test_split\nfrom tqdm.autonotebook import tqdm\n\nimport tensorflow as tf\nfrom keras import Sequential\nfrom keras.callbacks import EarlyStopping\nfrom keras.optimizers import Adam, SGD\nfrom keras.callbacks import ReduceLROnPlateau\nfrom keras.layers import Flatten,Dense,BatchNormalization,Activation,Dropout\nfrom keras.layers import Lambda, Input, GlobalAveragePooling2D,BatchNormalization\nfrom keras.utils import to_categorical\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.preprocessing.image import load_img","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:29:36.496191Z","iopub.execute_input":"2023-06-19T22:29:36.496521Z","iopub.status.idle":"2023-06-19T22:29:46.961243Z","shell.execute_reply.started":"2023-06-19T22:29:36.496494Z","shell.execute_reply":"2023-06-19T22:29:46.960274Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"labels = pd.read_csv('/kaggle/input/dog-breed-identification/labels.csv')\nlabels.head()","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:29:46.963315Z","iopub.execute_input":"2023-06-19T22:29:46.964091Z","iopub.status.idle":"2023-06-19T22:29:47.009893Z","shell.execute_reply.started":"2023-06-19T22:29:46.964056Z","shell.execute_reply":"2023-06-19T22:29:47.009001Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Create list of alphabetically sorted labels.\nclasses = sorted(list(set(labels['breed'])))\nn_classes = len(classes)\nprint('Total unique breed {}'.format(n_classes))\n\n\n#Map each label string to an integer label.\nclass_to_num = dict(zip(classes, range(n_classes)))","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:29:47.011597Z","iopub.execute_input":"2023-06-19T22:29:47.012311Z","iopub.status.idle":"2023-06-19T22:29:47.020252Z","shell.execute_reply.started":"2023-06-19T22:29:47.012273Z","shell.execute_reply":"2023-06-19T22:29:47.019146Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"input_shape = (331,331,3)\n\ndef images_to_array(directory, label_dataframe, target_size = input_shape):\n    \n    image_labels = label_dataframe['breed']\n    images = np.zeros([len(label_dataframe), target_size[0], target_size[1], target_size[2]],dtype=np.uint8) #as we have huge data and limited ram memory. uint8 takes less memory\n    y = np.zeros([len(label_dataframe),1],dtype = np.uint8)\n    \n    for ix, image_name in enumerate(tqdm(label_dataframe['id'].values)):\n        img_dir = os.path.join(directory, image_name + '.jpg')\n        img = load_img(img_dir, target_size = target_size)\n        images[ix] = img\n        del img\n        \n        dog_breed = image_labels[ix]\n        y[ix] = class_to_num[dog_breed]\n    \n    y = to_categorical(y)\n    \n    return images, y","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:29:47.022959Z","iopub.execute_input":"2023-06-19T22:29:47.023714Z","iopub.status.idle":"2023-06-19T22:29:47.032030Z","shell.execute_reply.started":"2023-06-19T22:29:47.023682Z","shell.execute_reply":"2023-06-19T22:29:47.030953Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import time \nt = time.time()\n\nX, y = images_to_array('/kaggle/input/dog-breed-identification/train', labels[:])\n\nprint('runtime in seconds: {}'.format(time.time() - t))","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:29:47.033477Z","iopub.execute_input":"2023-06-19T22:29:47.034084Z","iopub.status.idle":"2023-06-19T22:31:08.384165Z","shell.execute_reply.started":"2023-06-19T22:29:47.034054Z","shell.execute_reply":"2023-06-19T22:31:08.383271Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(\n    X, y, test_size=0.3, random_state=42)\n\nprint(X_train.shape, y_train.shape)\nprint(X_test.shape, y_test.shape)","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:31:08.385476Z","iopub.execute_input":"2023-06-19T22:31:08.386521Z","iopub.status.idle":"2023-06-19T22:31:09.400043Z","shell.execute_reply.started":"2023-06-19T22:31:08.386486Z","shell.execute_reply":"2023-06-19T22:31:09.399088Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Learning Rate Annealer\nlrr= ReduceLROnPlateau(monitor='val_acc', factor=.01, patience=3, min_lr=1e-5,verbose = 1)\n\n#Prepare call backs\nEarlyStop = EarlyStopping(monitor='val_loss', patience=10, restore_best_weights=True)","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:31:09.401564Z","iopub.execute_input":"2023-06-19T22:31:09.402132Z","iopub.status.idle":"2023-06-19T22:31:09.407669Z","shell.execute_reply.started":"2023-06-19T22:31:09.402099Z","shell.execute_reply":"2023-06-19T22:31:09.406274Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Hyperparameters\nbatch_size= 128\nepochs=25\nlearn_rate=.001\nsgd=SGD(learning_rate=learn_rate, momentum=0.9, nesterov=False)\nadam=Adam(learning_rate=learn_rate, beta_1=0.9, beta_2=0.999, epsilon=None,  amsgrad=False)","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:31:09.409179Z","iopub.execute_input":"2023-06-19T22:31:09.409576Z","iopub.status.idle":"2023-06-19T22:31:09.431394Z","shell.execute_reply.started":"2023-06-19T22:31:09.409546Z","shell.execute_reply":"2023-06-19T22:31:09.430272Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#function to extract features from the dataset by a given pretrained model\nimg_size = (331,331,3)\n\ndef get_features(model_name, model_preprocessor, input_size, data):\n\n    input_layer = Input(input_size)\n    preprocessor = Lambda(model_preprocessor)(input_layer)\n    base_model = model_name(weights='imagenet', include_top=False,\n                            input_shape=input_size)(preprocessor)\n    avg = GlobalAveragePooling2D()(base_model)\n    feature_extractor = Model(inputs = input_layer, outputs = avg)\n    \n    #Extract feature.\n    feature_maps = feature_extractor.predict(data, verbose=1)\n    print('Feature maps shape: ', feature_maps.shape)\n    return feature_maps","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:31:09.432774Z","iopub.execute_input":"2023-06-19T22:31:09.433075Z","iopub.status.idle":"2023-06-19T22:31:09.441268Z","shell.execute_reply.started":"2023-06-19T22:31:09.433046Z","shell.execute_reply":"2023-06-19T22:31:09.438256Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Extract features using InceptionV3 \nfrom keras.applications.inception_v3 import InceptionV3, preprocess_input\ninception_preprocessor = preprocess_input\ninception_features = get_features(InceptionV3,\n                                  inception_preprocessor,\n                                  img_size, X_train)\n\nprint('Inception feature maps shape', inception_features.shape)","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:31:09.445412Z","iopub.execute_input":"2023-06-19T22:31:09.445791Z","iopub.status.idle":"2023-06-19T22:31:47.312407Z","shell.execute_reply.started":"2023-06-19T22:31:09.445765Z","shell.execute_reply":"2023-06-19T22:31:47.311404Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"del X, X_train #to free up some ram memory\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:31:47.313712Z","iopub.execute_input":"2023-06-19T22:31:47.314089Z","iopub.status.idle":"2023-06-19T22:31:47.936069Z","shell.execute_reply.started":"2023-06-19T22:31:47.314055Z","shell.execute_reply":"2023-06-19T22:31:47.935149Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Prepare Deep net\n\nmodel = Sequential()\n# model.add(Dense(1028,input_shape=(final_features.shape[1],)))\nmodel.add(Dropout(0.7,input_shape=(inception_features.shape[1],)))\nmodel.add(Dense(n_classes,activation= 'softmax'))\n\nmodel.compile(optimizer=adam,\n              loss='categorical_crossentropy',\n              metrics=['accuracy'])\n\n#Training the model. \nhistory = model.fit(inception_features, y_train,\n            batch_size=batch_size,\n            epochs=epochs,\n            validation_split=0.2,\n            callbacks=[lrr, EarlyStop])","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:31:47.938480Z","iopub.execute_input":"2023-06-19T22:31:47.938828Z","iopub.status.idle":"2023-06-19T22:31:58.716568Z","shell.execute_reply.started":"2023-06-19T22:31:47.938797Z","shell.execute_reply":"2023-06-19T22:31:58.715538Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.summary()","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:31:58.718556Z","iopub.execute_input":"2023-06-19T22:31:58.719009Z","iopub.status.idle":"2023-06-19T22:31:58.737946Z","shell.execute_reply.started":"2023-06-19T22:31:58.718973Z","shell.execute_reply":"2023-06-19T22:31:58.737171Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Plot result\nacc = history.history['accuracy']\nval_acc = history.history['val_accuracy']\nloss = history.history['loss']\nval_loss = history.history['val_loss']\nepochs = range(1, len(acc) + 1)\n\n# Accuracy\nplt.plot(epochs, acc, label='Train accuracy')\nplt.plot(epochs, val_acc, label='Val accuracy')\nplt.title('Training & validation accuracy')\nplt.legend()\n\n# Loss\nplt.figure()\nplt.plot(epochs, loss, label='Train loss')\nplt.plot(epochs, val_loss, label='Val loss')\nplt.title('Training & validation loss')\nplt.legend()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:31:58.739227Z","iopub.execute_input":"2023-06-19T22:31:58.739553Z","iopub.status.idle":"2023-06-19T22:31:59.347073Z","shell.execute_reply.started":"2023-06-19T22:31:58.739521Z","shell.execute_reply":"2023-06-19T22:31:59.346162Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"del inception_features\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:31:59.348553Z","iopub.execute_input":"2023-06-19T22:31:59.348889Z","iopub.status.idle":"2023-06-19T22:31:59.599136Z","shell.execute_reply.started":"2023-06-19T22:31:59.348857Z","shell.execute_reply":"2023-06-19T22:31:59.598197Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Extract test data features.\ndef extact_features(data):\n    inception_features = get_features(InceptionV3, inception_preprocessor, img_size, data)\n    print('Inception feature maps shape', inception_features.shape)\n    return inception_features\n\ntest_features = extact_features(X_test)","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:31:59.600625Z","iopub.execute_input":"2023-06-19T22:31:59.600993Z","iopub.status.idle":"2023-06-19T22:32:15.886365Z","shell.execute_reply.started":"2023-06-19T22:31:59.600960Z","shell.execute_reply":"2023-06-19T22:32:15.885235Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_pred = model.predict(test_features)","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:32:15.888032Z","iopub.execute_input":"2023-06-19T22:32:15.888403Z","iopub.status.idle":"2023-06-19T22:32:16.318192Z","shell.execute_reply.started":"2023-06-19T22:32:15.888370Z","shell.execute_reply":"2023-06-19T22:32:16.317091Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.metrics import accuracy_score\n\ny_test_indices = np.argmax(y_test, axis=1)\ny_pred_indices = np.argmax(y_pred, axis=1)\n\naccuracy_score(y_test_indices, y_pred_indices)","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:32:16.319804Z","iopub.execute_input":"2023-06-19T22:32:16.320148Z","iopub.status.idle":"2023-06-19T22:32:16.330516Z","shell.execute_reply.started":"2023-06-19T22:32:16.320115Z","shell.execute_reply":"2023-06-19T22:32:16.329387Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Function to read images from test directory\n\ndef images_to_array_test(test_path, img_size = (331,331,3)):\n    test_filenames = [test_path + fname for fname in os.listdir(test_path)]\n    data_size = len(test_filenames)\n    images = np.zeros([data_size, img_size[0], img_size[1], 3], dtype=np.uint8)\n        \n    for ix,img_dir in enumerate(tqdm(test_filenames)):\n        img = load_img(img_dir, target_size = img_size)\n        images[ix]=img\n        del img\n    print('Ouptut Data Size: ', images.shape)\n    return images\n\ntest_data = images_to_array_test('/kaggle/input/dog-breed-identification/test/', img_size)","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:34:59.044155Z","iopub.execute_input":"2023-06-19T22:34:59.045126Z","iopub.status.idle":"2023-06-19T22:36:07.017116Z","shell.execute_reply.started":"2023-06-19T22:34:59.045092Z","shell.execute_reply":"2023-06-19T22:36:07.016230Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Extract test data features.\ndef extact_features(data):\n    inception_features = get_features(InceptionV3, inception_preprocessor, img_size, data)\n    print('Inception feature maps shape', inception_features.shape)\n    return inception_features\n\ntest_features = extact_features(test_data)","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:36:07.018852Z","iopub.execute_input":"2023-06-19T22:36:07.019791Z","iopub.status.idle":"2023-06-19T22:36:42.934544Z","shell.execute_reply.started":"2023-06-19T22:36:07.019756Z","shell.execute_reply":"2023-06-19T22:36:42.933550Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Free up some space.\ndel test_data\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:36:49.599340Z","iopub.execute_input":"2023-06-19T22:36:49.599702Z","iopub.status.idle":"2023-06-19T22:36:50.432876Z","shell.execute_reply.started":"2023-06-19T22:36:49.599662Z","shell.execute_reply":"2023-06-19T22:36:50.431806Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pred = model.predict(test_features)","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:36:59.302314Z","iopub.execute_input":"2023-06-19T22:36:59.302666Z","iopub.status.idle":"2023-06-19T22:37:00.159163Z","shell.execute_reply.started":"2023-06-19T22:36:59.302638Z","shell.execute_reply":"2023-06-19T22:37:00.158062Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Create pandas DataFrame with empty columns\npreds_df = pd.DataFrame(columns=[\"id\"] + list(classes))\n\ntest_path = \"/kaggle/input/dog-breed-identification/test/\"\npreds_df[\"id\"] = [os.path.splitext(path)[0] for path in os.listdir(test_path)]","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:37:15.904065Z","iopub.execute_input":"2023-06-19T22:37:15.904420Z","iopub.status.idle":"2023-06-19T22:37:15.961067Z","shell.execute_reply.started":"2023-06-19T22:37:15.904392Z","shell.execute_reply":"2023-06-19T22:37:15.960114Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"preds_df.loc[:,list(classes)] = pred\n\npreds_df.to_csv('submission.csv',index=None)","metadata":{"execution":{"iopub.status.busy":"2023-06-19T22:38:07.442913Z","iopub.execute_input":"2023-06-19T22:38:07.443281Z","iopub.status.idle":"2023-06-19T22:38:11.059280Z","shell.execute_reply.started":"2023-06-19T22:38:07.443250Z","shell.execute_reply":"2023-06-19T22:38:11.057728Z"},"trusted":true},"execution_count":null,"outputs":[]}]}