{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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\npd.set_option(\"display.max_columns\",None)\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 5GB 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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"#heavily inspired by: https://www.kaggle.com/ibtesama/siim-baseline-keras-vgg16\n\nbase_tile_dir = '/kaggle/input/siim-isic-melanoma-classification/jpeg/train/'\ndf = pd.read_csv(\"../input/siim-isic-melanoma-classification/train.csv\")\ndf['path']=base_tile_dir+df.image_name+\".jpg\"\ndf.head()\n# df['path'].head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# pd.DataFrame.to_string(df)\ndf_0=df[df['target']==0].sample(2000)\ndf_1=df[df['target']==1]\ntrain=pd.concat([df_0,df_1])\ntrain=train.reset_index()\ntrain.head()\n\ndf=train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import cv2\nimg=cv2.imread(\"/kaggle/input/siim-isic-melanoma-classification/jpeg/train/ISIC_0015719.jpg\")\ncv2.imshow(\"Output here\",img)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# y = l_encoded\n# y=df['target']\nfrom sklearn.model_selection import train_test_split\ntrain_x, test_x, train_y, test_y = train_test_split(df['path'],df['target'], test_size=0.2, random_state=1234)\n# train_x, test_x, train_y, test_y = train_test_split(df['path'],y, test_size=0.15, shuffle=True)\ntest_x.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_x=pd.DataFrame(train_x)\ntrain_y=pd.DataFrame(train_y)\ntrain_x.reset_index(drop=True, inplace=True)\ntrain_y.reset_index(drop=True, inplace=True)\n\ntrain=pd.concat([train_x,train_y],axis=1)\ntrain.head()\n\ntest_x=pd.DataFrame(test_x)\ntest_y=pd.DataFrame(test_y)\ntest_x.reset_index(drop=True, inplace=True)\ntest_y.reset_index(drop=True, inplace=True)\n\ntest=pd.concat([test_x,test_y],axis=1)\ntest.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['target']=train['target'].astype('str')\ntest['target']=test['target'].astype('str')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\nbatch_size=64\ncolormode = 'rgb'\nclassmode = 'binary'\nshuffle=True\nseed=666\ntarget_size=(224,224)\n# target_size=(299,299)\n\ndatagen = ImageDataGenerator(rescale = 1./255,\n                             shear_range = 0.2,\n                             zoom_range = 0.2,\n                             horizontal_flip = True)\n# train_set_path =\"/content/train_images/\"\nvalidation=test\ncolumns = [0,1]\n\ntraining_generator = datagen.flow_from_dataframe(train,\n                                           x_col='path',\n                                          #  y_col=0,\n                                           y_col='target',\n                                           target_size = target_size,\n                                           batch_size = batch_size,\n                                           class_mode = classmode,\n                                           color_mode=colormode,\n                                           shuffle = shuffle,\n                                           seed=seed)\n\nvalidation_generator = datagen.flow_from_dataframe(validation,\n                                             x_col='path',\n                                             y_col='target',\n                                             target_size = target_size,\n                                             batch_size = batch_size,\n                                             class_mode = classmode,\n                                             color_mode=colormode,\n                                             shuffle = shuffle,\n                                             seed=seed)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras import layers\nfrom keras.preprocessing import image\nfrom keras.layers import Input, Dense, Activation, BatchNormalization, Flatten, Conv2D\nfrom keras.layers import AveragePooling2D, MaxPooling2D, Dropout\nfrom keras.models import Model\n\nimport keras.backend as K\nfrom keras.models import Sequential\n\nfrom keras.metrics import categorical_accuracy, top_k_categorical_accuracy, categorical_crossentropy\nfrom keras.models import Sequential\nfrom keras.callbacks import EarlyStopping, ReduceLROnPlateau, ModelCheckpoint\nfrom keras.optimizers import Adam\nfrom keras.applications import vgg19\nfrom keras.applications.vgg19 import preprocess_input\nfrom keras.applications.vgg16 import VGG16,preprocess_input\n\nimport warnings\nwarnings.simplefilter(\"ignore\", category=DeprecationWarning)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"vgg = VGG16(input_shape=(224,224,3), weights='imagenet', include_top=False)\n\nfor layer in vgg.layers[0:7]:\n  layer.trainable = False\nfor layer in vgg.layers[8:]:\n  layer.trainable=True  \n\n# useful for getting number of classes\n# folders = glob('/content/train_images/*')\n  \n\n# our layers - you can add more if you want\nx = Flatten()(vgg.output)\nx = Dense(2048, activation='relu')(x)\nx = Dropout(0.5)(x)\nprediction = Dense(1, activation='sigmoid')(x)\n# prediction = Dense(5005, activation='softmax')(x)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# create a model object\nmodel = Model(inputs=vgg.input, outputs=prediction)\n\n# view the structure of the model\nmodel.summary()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer=Adam(lr=0.001), loss='binary_crossentropy',\n              metrics=['accuracy'])\n\n# print(model.summary())\nnb_epochs = 2\nbatch_size=16\n# nb_train_steps = train.shape[0]//batch_size\n# nb_val_steps=validation.shape[0]//batch_size\n\nnb_train_steps=training_generator.n//training_generator.batch_size\nnb_val_steps=validation_generator.n//validation_generator.batch_size\n\nprint(\"Number of training and validation steps: {} and {}\".format(nb_train_steps,nb_val_steps))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit_generator(\n    training_generator,\n    steps_per_epoch=nb_train_steps,\n    epochs=nb_epochs,\n    validation_data=validation_generator,\n    # callbacks=cb,\n    verbose=1,\n    validation_steps=nb_val_steps)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}