import numpy as np np.random.seed(2017) import os import glob import cv2 import datetime import pandas as pd import time import warnings warnings.filterwarnings("ignore") from sklearn.cross_validation import KFold from keras.models import Sequential from keras.layers.core import Dense, Dropout, Flatten from keras.layers.convolutional import Convolution2D, MaxPooling2D, ZeroPadding2D from keras.optimizers import SGD from keras.callbacks import EarlyStopping from keras.utils import np_utils from sklearn.metrics import log_loss from keras import __version__ as keras_version def get_img(path): img = cv2.imread(path) img = cv2.resize(img, (32, 32), cv2.INTER_LINEAR) return img def load_train(): X_train = [] X_train_id = [] y_train = [] start_time = time.time() print('Read train images') folders = ['Type_1', 'Type_2', 'Type_3'] for fld in folders: index = folders.index(fld) print("loading folder ",fld) path = os.path.join('..', 'input', 'train', fld, '*.jpg') files = glob.glob(path) for f in files: name = os.path.basename(f) img = get_img(f) X_train.append(img) X_train_id.append(name) y_train.append(index) print('Read train data time: {} seconds'.format(round(time.time() - start_time, 2))) return X_train, y_train, X_train_id def load_test(): path = os.path.join('..', 'input', 'test', '*.jpg') files = glob.glob(path) X_test = [] X_test_id = [] for f in files: name = os.path.basename(f) img = get_img(f) X_test.append(img) X_test_id.append(name) return X_test, X_test_id def create_submission(predictions, test_id, info): result1 = pd.DataFrame(predictions, columns=['Type_1', 'Type_2', 'Type_3']) result1.loc[:, 'image_name'] = pd.Series(test_id, index=result1.index) now = datetime.datetime.now() sub_file = 'submission_' + info + '_' + str(now.strftime("%Y-%m-%d-%H-%M")) + '.csv' result1.to_csv(sub_file, index=False) def read_and_normalize_train_data(): train_data, train_target, train_id = load_train() print('Convert to numpy...') train_data = np.array(train_data, dtype=np.uint8) train_target = np.array(train_target, dtype=np.uint8) print('Reshape...') train_data = train_data.transpose((0, 3, 1, 2)) print('Convert to float...') train_data = train_data.astype('float32') train_data = train_data / 255 train_target = np_utils.to_categorical(train_target, 3) print('Train shape:', train_data.shape) print(train_data.shape[0], 'train samples') return train_data, train_target, train_id def read_and_normalize_test_data(): start_time = time.time() test_data, test_id = load_test() test_data = np.array(test_data, dtype=np.uint8) test_data = test_data.transpose((0, 3, 1, 2)) test_data = test_data.astype('float32') test_data = test_data / 255 print('Test data shape', test_data.shape) return test_data, test_id def dict_to_list(d): ret = [] for i in d.items(): ret.append(i[1]) return ret def merge_several_folds_mean(data, nfolds): a = np.array(data[0]) for i in range(1, nfolds): a += np.array(data[i]) a /= nfolds return a.tolist() def create_model(): model = Sequential() model.add(ZeroPadding2D((1, 1), input_shape=(3, 32, 32), dim_ordering='th')) model.add(Convolution2D(4, 3, 3, activation='relu', dim_ordering='th')) model.add(ZeroPadding2D((1, 1), dim_ordering='th')) model.add(Convolution2D(4, 3, 3, activation='relu', dim_ordering='th')) model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), dim_ordering='th')) model.add(ZeroPadding2D((1, 1), dim_ordering='th')) model.add(Convolution2D(8, 3, 3, activation='relu', dim_ordering='th')) model.add(ZeroPadding2D((1, 1), dim_ordering='th')) model.add(Convolution2D(8, 3, 3, activation='relu', dim_ordering='th')) model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), dim_ordering='th')) model.add(Flatten()) model.add(Dense(32, activation='relu')) model.add(Dropout(0.5)) model.add(Dense(32, activation='relu')) model.add(Dropout(0.5)) model.add(Dense(3, activation='softmax')) sgd = SGD(lr=1e-2, decay=1e-6, momentum=0.9, nesterov=True) model.compile(optimizer=sgd, loss='categorical_crossentropy', metrics=['accuracy']) return model def create_model2(opt_='adamax'): model = Sequential() model.add(Convolution2D(4, 3, 3, activation='relu', dim_ordering='th', input_shape=(3, 32, 32))) #use input_shape=(3, 64, 64) model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), dim_ordering='th')) model.add(Convolution2D(8, 3, 3, activation='relu', dim_ordering='th')) model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), dim_ordering='th')) model.add(Dropout(0.2)) model.add(Flatten()) model.add(Dense(12, activation='tanh')) model.add(Dropout(0.1)) model.add(Dense(3, activation='softmax')) model.compile(optimizer=opt_, loss='sparse_categorical_crossentropy', metrics=['accuracy']) return model def get_validation_predictions(train_data, predictions_valid): pv = [] for i in range(len(train_data)): pv.append(predictions_valid[i]) return pv def run_cross_validation_create_models(nfolds=10): # input image dimensions batch_size = 16 nb_epoch = 30 random_state = 51 train_data, train_target, train_id = read_and_normalize_train_data() yfull_train = dict() kf = KFold(len(train_id), n_folds=nfolds, shuffle=True, random_state=random_state) num_fold = 0 sum_score = 0 models = [] for train_index, test_index in kf: model = create_model() X_train = train_data[train_index] Y_train = train_target[train_index] X_valid = train_data[test_index] Y_valid = train_target[test_index] num_fold += 1 print('Start KFold number {} from {}'.format(num_fold, nfolds)) print('Split train: ', len(X_train), len(Y_train)) print('Split valid: ', len(X_valid), len(Y_valid)) callbacks = [ EarlyStopping(monitor='val_loss', patience=3, verbose=0), ] model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch, shuffle=True, verbose=2, validation_data=(X_valid, Y_valid), callbacks=callbacks) predictions_valid = model.predict(X_valid.astype('float32'), batch_size=batch_size, verbose=2) score = log_loss(Y_valid, predictions_valid) print('Score log_loss: ', score) sum_score += score*len(test_index) # Store valid predictions for i in range(len(test_index)): yfull_train[test_index[i]] = predictions_valid[i] models.append(model) score = sum_score/len(train_data) print("Log_loss train independent avg: ", score) info_string = 'loss_' + str(score) + '_folds_' + str(nfolds) + '_ep_' + str(nb_epoch) return info_string, models def run_cross_validation_process_test(info_string, models): batch_size = 16 num_fold = 0 yfull_test = [] test_id = [] nfolds = len(models) for i in range(nfolds): model = models[i] num_fold += 1 print('Start KFold number {} from {}'.format(num_fold, nfolds)) test_data, test_id = read_and_normalize_test_data() test_prediction = model.predict(test_data, batch_size=batch_size, verbose=2) yfull_test.append(test_prediction) test_res = merge_several_folds_mean(yfull_test, nfolds) info_string = 'loss_' + info_string \ + '_folds_' + str(nfolds) create_submission(test_res, test_id, info_string) """train_data, train_target, train_id = read_and_normalize_train_data() model=create_model() model.fit(train_data, train_target, batch_size=16, nb_epoch=30, shuffle=True, verbose=2) test_data, test_id = read_and_normalize_test_data() test_prediction = model.predict(test_data, batch_size=16, verbose=2) print (test_prediction)""" if __name__ == '__main__': print('Keras version: {}'.format(keras_version)) num_folds = 3 info_string, models = run_cross_validation_create_models(num_folds) run_cross_validation_process_test(info_string, models)