def read(self, img_rows=IMAGE_SIZE, img_cols=IMAGE_SIZE, img_channels=3, nb_classes=2): images, labels = extract_data('C:\\video\\') # labels : boss 이면 0 , 아니면 1 # print(images.shape) # print(labels.shape) labels = np.reshape(labels, [-1]) # print(labels.shape) # numpy.reshape X_train, X_test, y_train, y_test = train_test_split(images, labels, test_size=0.2, random_state=random.randint(0, 100)) # random.randint(0, 100) 0과 100사이의 랜덤한 정수를 생성 X_valid, X_test, y_valid, y_test = train_test_split(X_train, y_train, test_size=0.33, random_state=random.randint(0, 100)) if K.image_dim_ordering() == 'th': X_train = X_train.reshape(X_train.shape[0], 3, img_rows, img_cols) X_valid = X_valid.reshape(X_valid.shape[0], 3, img_rows, img_cols) X_test = X_test.reshape(X_test.shape[0], 3, img_rows, img_cols) input_shape = (3, img_rows, img_cols) else: X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 3) X_valid = X_valid.reshape(X_valid.shape[0], img_rows, img_cols, 3) X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 3) input_shape = (img_rows, img_cols, 3) # the data, shuffled and split between train and test sets print('X_train shape:', X_train.shape) print(X_train.shape[0], 'train samples') print(X_valid.shape[0], 'valid samples') print(X_test.shape[0], 'test samples') # convert class vectors to binary class matrices Y_train = np_utils.to_categorical(y_train, nb_classes) # 원핫인코딩 Y_valid = np_utils.to_categorical(y_valid, nb_classes) Y_test = np_utils.to_categorical(y_test, nb_classes) print(X_train.dtype) X_train = X_train.astype('float32') X_valid = X_valid.astype('float32') X_test = X_test.astype('float32') # X_train /= 255 #데이터 정규화를 위해 , 255: 0부터 255사이의 이미지 픽셀 값 # X_valid /= 255 # X_test /= 255 # print('###',X_train) #정규화 된 data 확인 self.X_train = X_train # 정규화 된 data self.X_valid = X_valid self.X_test = X_test self.Y_train = Y_train # 원핫 인코딩된 label self.Y_valid = Y_valid self.Y_test = Y_test
def read(self, img_rows=IMAGE_SIZE, img_cols=IMAGE_SIZE, img_channels=3, nb_classes=2): images, labels = extract_data('./data/') labels = np.reshape(labels, [-1]) # numpy.reshape X_train, X_test, y_train, y_test = train_test_split( images, labels, test_size=0.3, random_state=random.randint(0, 100)) X_valid, X_test, y_valid, y_test = train_test_split( images, labels, test_size=0.5, random_state=random.randint(0, 100)) if K.image_dim_ordering() == 'th': X_train = X_train.reshape(X_train.shape[0], 3, img_rows, img_cols) X_valid = X_valid.reshape(X_valid.shape[0], 3, img_rows, img_cols) X_test = X_test.reshape(X_test.shape[0], 3, img_rows, img_cols) input_shape = (3, img_rows, img_cols) else: X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 3) X_valid = X_valid.reshape(X_valid.shape[0], img_rows, img_cols, 3) X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 3) input_shape = (img_rows, img_cols, 3) # the data, shuffled and split between train and test sets print('X_train shape:', X_train.shape) print(X_train.shape[0], 'train samples') print(X_valid.shape[0], 'valid samples') print(X_test.shape[0], 'test samples') # convert class vectors to binary class matrices Y_train = np_utils.to_categorical(y_train, nb_classes) Y_valid = np_utils.to_categorical(y_valid, nb_classes) Y_test = np_utils.to_categorical(y_test, nb_classes) X_train = X_train.astype('float32') X_valid = X_valid.astype('float32') X_test = X_test.astype('float32') X_train /= 255 X_valid /= 255 X_test /= 255 self.X_train = X_train self.X_valid = X_valid self.X_test = X_test self.Y_train = Y_train self.Y_valid = Y_valid self.Y_test = Y_test
def read(self, img_rows=IMAGE_SIZE, img_cols=IMAGE_SIZE, img_channels=3, nb_classes=2): images, labels = extract_data('d:/code/python/bossWin/data') # numpy.reshape labels = np.reshape(labels, [-1]) X_train, X_test, y_train, y_test = train_test_split(images, labels, test_size=0.3, random_state=random.randint(0, 100)) X_valid, X_test, y_valid, y_test = train_test_split(images, labels, test_size=0.5, random_state=random.randint(0, 100)) if K.image_dim_ordering() == 'th': X_train = X_train.reshape(X_train.shape[0], 3, img_rows, img_cols) X_valid = X_valid.reshape(X_valid.shape[0], 3, img_rows, img_cols) X_test = X_test.reshape(X_test.shape[0], 3, img_rows, img_cols) input_shape = (3, img_rows, img_cols) else: X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 3) X_valid = X_valid.reshape(X_valid.shape[0], img_rows, img_cols, 3) X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 3) input_shape = (img_rows, img_cols, 3) # the data, shuffled and split between train and test sets print('X_train shape:', X_train.shape) print(X_train.shape[0], 'train samples') print(X_valid.shape[0], 'valid samples') print(X_test.shape[0], 'test samples') # convert class vectors to binary class matrices Y_train = np_utils.to_categorical(y_train, nb_classes) Y_valid = np_utils.to_categorical(y_valid, nb_classes) Y_test = np_utils.to_categorical(y_test, nb_classes) X_train = X_train.astype('float32') X_valid = X_valid.astype('float32') X_test = X_test.astype('float32') X_train /= 255 X_valid /= 255 X_test /= 255 self.X_train = X_train self.X_valid = X_valid self.X_test = X_test self.Y_train = Y_train self.Y_valid = Y_valid self.Y_test = Y_test
import matplotlib.pyplot as plt from keras.utils import np_utils from keras.models import Sequential from keras.layers import Dense, Dropout, Activation sys.path.insert(0, '/Users/shaomingliang/Downloads/BossSensor-master') from boss_input import extract_data,resize_with_pad #DatasetPath = [] #for i in os.listdir("yalefaces"): # DatasetPath.append(os.path.join("yalefaces", i)) imageData = [] imageLabels = [] imageData1, imageLabels= extract_data('/Users/shaomingliang/Downloads/BossSensor-master/data') imageData = [] labels = [] for index,img in enumerate(imageData1): if img is None: continue frame = cv2.resize(img, (64, 64)) imageData.append(cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)) labels.append(imageLabels[index]) imageDataFin = imageData imageLabels = labels #for i in DatasetPath: # imgRead = io.imread(i,as_grey=True) # imageData.append(imgRead) #