# This Python 3 environment comes with many helpful analytics libraries installed # It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python # For example, here's several helpful packages to load in import numpy as np # linear algebra import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv) # Input data files are available in the "../input/" directory. # For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory import os print(os.listdir("../input")) # Any results you write to the current directory are saved as output. from glob import glob from skimage.io import imread import gc from sklearn.utils import shuffle from sklearn.model_selection import train_test_split from sklearn.metrics import roc_curve from sklearn.metrics import auc from keras.utils import to_categorical import shutil import os import pandas as pd import numpy as np import PIL import matplotlib import matplotlib.pyplot as plt from keras.models import load_model,save_model from keras.callbacks import ModelCheckpoint from matplotlib.patches import Rectangle import os from scipy.misc import imsave from tqdm import tqdm import keras from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img from keras.preprocessing import image from keras.applications import xception from keras.models import Sequential from keras.layers import Conv2D, MaxPooling2D from keras.layers import Activation, Dropout, Flatten, Dense from keras.layers import BatchNormalization from keras.optimizers import SGD, Adam,Adagrad from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau from keras.layers.advanced_activations import LeakyReLU from math import sqrt from keras.callbacks import History from keras.optimizers import Adam, SGD from keras.layers import Activation from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau from keras.layers.advanced_activations import LeakyReLU from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img from keras.preprocessing import image from keras.applications import xception from keras.models import Sequential from keras.layers import Conv2D, MaxPooling2D, UpSampling2D, merge, GlobalAveragePooling2D, MaxPool2D, GlobalMaxPooling2D from keras.layers import Activation, Dropout, Flatten, Dense,Input, Concatenate from keras.layers import BatchNormalization from keras.models import Model from keras.activations import relu from keras.layers.advanced_activations import LeakyReLU from keras.layers.advanced_activations import ELU import keras.backend as K from math import sqrt from keras.callbacks import History from keras.applications import ResNet50, VGG19, NASNetMobile,DenseNet169 import gc import numpy as np # linear algebra import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv) # Input data files are available in the "../input/" directory. # For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory import os from glob import glob from random import shuffle import cv2 import matplotlib.pyplot as plt from sklearn.model_selection import train_test_split from keras.preprocessing.image import ImageDataGenerator from keras.layers import Convolution1D, concatenate, SpatialDropout1D, GlobalMaxPool1D, GlobalAvgPool1D, Embedding, \ Conv2D, SeparableConv1D, Add, BatchNormalization, Activation, GlobalAveragePooling2D, LeakyReLU, Flatten from keras.layers import Dense, Input, Dropout, MaxPooling2D, Concatenate, GlobalMaxPooling2D, GlobalAveragePooling2D, \ Lambda, Multiply, LSTM, Bidirectional, PReLU, MaxPooling1D from keras.layers.pooling import _GlobalPooling1D from keras.losses import mae, sparse_categorical_crossentropy, binary_crossentropy from keras.models import Model # from keras.applications.inception_v3 import InceptionV3, preprocess_input from keras.applications.densenet import DenseNet169, preprocess_input from keras.optimizers import Adam, RMSprop from keras.callbacks import ModelCheckpoint, EarlyStopping, ReduceLROnPlateau from imgaug import augmenters as iaa import imgaug as ia from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img from keras.preprocessing import image from keras.applications import xception from keras.models import Sequential from keras.layers import Conv2D, MaxPooling2D from keras.layers import Activation, Dropout, Flatten, Dense from keras.layers import BatchNormalization from keras.optimizers import SGD, Adam,Adagrad from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau from keras.layers.advanced_activations import LeakyReLU from math import sqrt from keras.callbacks import History from keras.optimizers import Adam, SGD from keras.layers import Activation from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau from keras.layers.advanced_activations import LeakyReLU from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img from keras.preprocessing import image from keras.applications import xception from keras.models import Sequential from keras.layers import Conv2D, MaxPooling2D, UpSampling2D, merge, GlobalAveragePooling2D, MaxPool2D from keras.layers import Activation, Dropout, Flatten, Dense,Input from keras.layers import BatchNormalization from keras.models import Model from keras.activations import relu from keras.layers.advanced_activations import LeakyReLU from keras.layers.advanced_activations import ELU import keras.backend as K from math import sqrt from keras.callbacks import History df_train = pd.read_csv("../input/train_labels.csv") id_label_map = {k:v for k,v in zip(df_train.id.values, df_train.label.values)} df_train.head() def get_id_from_file_path(file_path): return file_path.split(os.path.sep)[-1].replace('.tif', '') labeled_files = glob('../input/train/*.tif') test_files = glob('../input/test/*.tif') train, val = train_test_split(labeled_files, test_size=0.1, random_state=101010) def chunker(seq, size): return (seq[pos:pos + size] for pos in range(0, len(seq), size)) def get_seq(): sometimes = lambda aug: iaa.Sometimes(0.5, aug) seq = iaa.Sequential( [ # apply the following augmenters to most images iaa.Fliplr(0.5), # horizontally flip 50% of all images iaa.Flipud(0.2), # vertically flip 20% of all images sometimes(iaa.Affine( scale={"x": (0.9, 1.1), "y": (0.9, 1.1)}, # scale images to 80-120% of their size, individually per axis translate_percent={"x": (-0.1, 0.1), "y": (-0.1, 0.1)}, # translate by -20 to +20 percent (per axis) rotate=(-10, 10), # rotate by -45 to +45 degrees shear=(-5, 5), # shear by -16 to +16 degrees order=[0, 1], # use nearest neighbour or bilinear interpolation (fast) cval=(0, 255), # if mode is constant, use a cval between 0 and 255 mode=ia.ALL # use any of scikit-image's warping modes (see 2nd image from the top for examples) )), # execute 0 to 5 of the following (less important) augmenters per image # don't execute all of them, as that would often be way too strong iaa.SomeOf((0, 5), [ sometimes(iaa.Superpixels(p_replace=(0, 1.0), n_segments=(20, 200))), # convert images into their superpixel representation iaa.OneOf([ iaa.GaussianBlur((0, 1.0)), # blur images with a sigma between 0 and 3.0 iaa.AverageBlur(k=(3, 5)), # blur image using local means with kernel sizes between 2 and 7 iaa.MedianBlur(k=(3, 5)), # blur image using local medians with kernel sizes between 2 and 7 ]), iaa.Sharpen(alpha=(0, 1.0), lightness=(0.9, 1.1)), # sharpen images iaa.Emboss(alpha=(0, 1.0), strength=(0, 2.0)), # emboss images # search either for all edges or for directed edges, # blend the result with the original image using a blobby mask iaa.SimplexNoiseAlpha(iaa.OneOf([ iaa.EdgeDetect(alpha=(0.5, 1.0)), iaa.DirectedEdgeDetect(alpha=(0.5, 1.0), direction=(0.0, 1.0)), ])), iaa.AdditiveGaussianNoise(loc=0, scale=(0.0, 0.01*255), per_channel=0.5), # add gaussian noise to images iaa.OneOf([ iaa.Dropout((0.01, 0.05), per_channel=0.5), # randomly remove up to 10% of the pixels iaa.CoarseDropout((0.01, 0.03), size_percent=(0.01, 0.02), per_channel=0.2), ]), iaa.Invert(0.01, per_channel=True), # invert color channels iaa.Add((-2, 2), per_channel=0.5), # change brightness of images (by -10 to 10 of original value) iaa.AddToHueAndSaturation((-1, 1)), # change hue and saturation # either change the brightness of the whole image (sometimes # per channel) or change the brightness of subareas iaa.OneOf([ iaa.Multiply((0.9, 1.1), per_channel=0.5), iaa.FrequencyNoiseAlpha( exponent=(-1, 0), first=iaa.Multiply((0.9, 1.1), per_channel=True), second=iaa.ContrastNormalization((0.9, 1.1)) ) ]), sometimes(iaa.ElasticTransformation(alpha=(0.5, 3.5), sigma=0.25)), # move pixels locally around (with random strengths) sometimes(iaa.PiecewiseAffine(scale=(0.01, 0.05))), # sometimes move parts of the image around sometimes(iaa.PerspectiveTransform(scale=(0.01, 0.1))) ], random_order=True ) ], random_order=True ) return seq def data_gen(list_files, id_label_map, batch_size, augment=False): seq = get_seq() while True: shuffle(list_files) for batch in chunker(list_files, batch_size): X = [cv2.imread(x) for x in batch] Y = [id_label_map[get_id_from_file_path(x)] for x in batch] if augment: X = seq.augment_images(X) X = [preprocess_input(x) for x in X] yield np.array(X), np.array(Y) lr_reduce = ReduceLROnPlateau(monitor='val_loss', factor=0.1, epsilon=1e-5, patience=3, verbose=1) modelID=0 checkPoint = ModelCheckpoint(filepath='./model_resnet_{epoch:02d}_{val_loss:.4f}_{val_acc:4f}.hdf5',verbose=1,save_best_only=True,mode=min) bestCheckPoint = ModelCheckpoint(filepath='./bestModel.hdf5',verbose=0,save_best_only=True,mode=min) datagen = ImageDataGenerator(preprocessing_function=lambda x:(x - x.mean()) / x.std() if x.std() > 0 else x, horizontal_flip=True, vertical_flip=True, validation_split=0.1) def conv_layer(feature_batch, feature_map, kernel_size=(3, 3),strides=(1,1), zp_flag=False): if zp_flag: zp = ZeroPadding2D((1,1))(feature_batch) else: zp = feature_batch conv = Conv2D(filters=feature_map, kernel_size=kernel_size, strides=strides)(zp) bn = BatchNormalization(axis=3)(conv) act = LeakyReLU(1/10)(bn) return act model = DenseNet169(include_top = False, input_shape=(96,96,3)) # for layer in model.layers: # layer.trainable = False x = model.output out1 = GlobalMaxPooling2D()(x) out2 = GlobalAveragePooling2D()(x) out3 = Flatten()(x) out = Concatenate(axis=-1)([out1, out2, out3]) out = Dropout(0.4)(out) out = Dense(256, activation="relu")(out) predictions = Dense(1, activation="sigmoid")(out) fullModel = Model(inputs=model.input, outputs=predictions) adam = Adam(lr=0.00001) fullModel.compile(loss="binary_crossentropy", optimizer=adam, metrics=["accuracy"]) ### TRAINING batch_size=32 h5_path = "model.h5" checkpoint = ModelCheckpoint(h5_path, monitor='val_acc', verbose=1, save_best_only=True, mode='max') history = fullModel.fit_generator( data_gen(train, id_label_map, batch_size, augment=True), validation_data=data_gen(val, id_label_map, batch_size), epochs=5, verbose=1, callbacks=[checkpoint, lr_reduce, bestCheckPoint,checkPoint], steps_per_epoch=2000, validation_steps=200) ##******************************** Plotting curves for the above model **********************************## # Plot training & validation accuracy values ##************************ ROC can be foudn here by putting in the test data set ****************### # y_pred_keras = fullmodel.predict(X_test).ravel() # fpr_keras, tpr_keras, thresholds_keras = roc_curve(y_test, y_pred_keras) # auc_keras = auc(fpr_keras, tpr_keras) # plt.figure(1) # plt.plot([0, 1], [0, 1], 'k--') # plt.plot(fpr_keras, tpr_keras, label='Keras (area = {:.3f})'.format(auc_keras)) # plt.plot(fpr_rf, tpr_rf, label='RF (area = {:.3f})'.format(auc_rf)) # plt.xlabel('False positive rate') # plt.ylabel('True positive rate') # plt.title('ROC curve') # plt.legend(loc='best') # plt.show() ##********************************** New model **********************************************### batch_size=64 history1 = fullModel.fit_generator( data_gen(train, id_label_map, batch_size, augment=True), validation_data=data_gen(val, id_label_map, batch_size), epochs=9, verbose=1, callbacks=[checkpoint, lr_reduce, bestCheckPoint,checkPoint], steps_per_epoch=2000, validation_steps=200) ##******************************** Plotting models for the above curve **********************************## # Plot training & validation accuracy values plt.plot(history.history['acc'] + history1.history['acc']) plt.plot(history.history['val_acc'] + history1.history['val_acc']) plt.title('Model accuracy') plt.ylabel('Accuracy') plt.xlabel('Epoch') plt.legend(['Train', 'Test'], loc='upper left') plt.savefig("acc.jpg") plt.clf() plt.close() plt.plot(history.history['loss']+ history1.history['loss']) plt.plot(history.history['val_loss']+ history1.history['val_loss']) plt.title('Model loss') plt.ylabel('Loss') plt.xlabel('Epoch') plt.legend(['Train', 'Test'], loc='upper left') plt.savefig("loss.jpg") fullModel.load_weights('./bestModel.hdf5') #### TESTING preds = [] ids = [] for batch in chunker(test_files, batch_size): X = [preprocess_input(cv2.imread(x)) for x in batch] ids_batch = [get_id_from_file_path(x) for x in batch] X = np.array(X) preds_batch = ((fullModel.predict(X).ravel()*fullModel.predict(X[:, ::-1, :, :]).ravel()*fullModel.predict(X[:, ::-1, ::-1, :]).ravel()*fullModel.predict(X[:, :, ::-1, :]).ravel())**0.25).tolist() preds += preds_batch ids += ids_batch df = pd.DataFrame({'id':ids, 'label':preds}) df.to_csv("submission.csv", index=False) df.head()