Python tflearn 模块，ImageAugmentation() 实例源码

def run(self):
        # Real-time pre-processing of the image data
        img_prep = ImagePreprocessing()
        img_prep.add_featurewise_zero_center()
        img_prep.add_featurewise_stdnorm()

        # Real-time data augmentation
        img_aug = tflearn.ImageAugmentation()
        img_aug.add_random_flip_leftright()
        # img_aug.add_random_crop([48, 48], padding=8)

        # Building Residual Network
        net = tflearn.input_data(shape=[None, 48, 48, 1], data_preprocessing=img_prep, data_augmentation=img_aug)
        net = tflearn.conv_2d(net, nb_filter=16, filter_size=3, regularizer='L2', weight_decay=0.0001)
        net = tflearn.residual_block(net, self.n, 16)
        net = tflearn.residual_block(net, 1, 32, downsample=True)
        net = tflearn.residual_block(net, self.n - 1, 32)
        net = tflearn.residual_block(net, 1, 64, downsample=True)
        net = tflearn.residual_block(net, self.n - 1, 64)
        net = tflearn.batch_normalization(net)
        net = tflearn.activation(net, 'relu')
        net = tflearn.global_avg_pool(net)

        # Regression
        net = tflearn.fully_connected(net, 7, activation='softmax')
        mom = tflearn.Momentum(learning_rate=0.1, lr_decay=0.0001, decay_step=32000, staircase=True, momentum=0.9)
        net = tflearn.regression(net, optimizer=mom,
                                 loss='categorical_crossentropy')

        self.model = tflearn.DNN(net, checkpoint_path='models/model_resnet_emotion',
                            max_checkpoints=10, tensorboard_verbose=0,
                            clip_gradients=0.)

        self.model.load('current_model/model_resnet_emotion-42000')

        face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
        cap = cv2.VideoCapture(0)

        while True:
            ret, img = cap.read()
            gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
            faces = face_cascade.detectMultiScale(gray, 1.3, 5)
            for (x, y, w, h) in faces:
                cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2)
                roi_gray = gray[y:y + h, x:x + w]
                roi_color = img[y:y + h, x:x + w]
                self.process_image(roi_gray, img)
            if cv2.waitKey(1) & 0xFF == ord('q'):
                break

        cap.release()
        cv2.destroyAllWindows()

def get_model(model_name):
    # First we load the network
    print("Setting up neural networks...")
    n = 18

    # Real-time data preprocessing
    print("Doing preprocessing...")
    img_prep = tflearn.ImagePreprocessing()
    img_prep.add_featurewise_zero_center(per_channel=True, mean=[0.573364,0.44924123,0.39455055])

    # Real-time data augmentation
    print("Building augmentation...")
    img_aug = tflearn.ImageAugmentation()
    img_aug.add_random_flip_leftright()
    img_aug.add_random_crop([32, 32], padding=4)

    #Build the model (for 32 x 32)
    print("Shaping input data...")
    net = tflearn.input_data(shape=[None, 32, 32, 3],
                             data_preprocessing=img_prep,
                             data_augmentation=img_aug)
    net = tflearn.conv_2d(net, 16, 3, regularizer='L2', weight_decay=0.0001)

    print("Carving Resnext blocks...")
    net = tflearn.resnext_block(net, n, 16, 32)
    net = tflearn.resnext_block(net, 1, 32, 32, downsample=True)
    net = tflearn.resnext_block(net, n-1, 32, 32)
    net = tflearn.resnext_block(net, 1, 64, 32, downsample=True)
    net = tflearn.resnext_block(net, n-1, 64, 32)

    print("Erroding Gradient...")
    net = tflearn.batch_normalization(net)
    net = tflearn.activation(net, 'relu')
    net = tflearn.global_avg_pool(net)
    net = tflearn.fully_connected(net, 8, activation='softmax')
    opt = tflearn.Momentum(0.1, lr_decay=0.1, decay_step=32000, staircase=True)
    net = tflearn.regression(net, optimizer=opt,
                             loss='categorical_crossentropy')

    print("Structuring model...")
    model = tflearn.DNN(net, tensorboard_verbose=0,
                        clip_gradients=0.)

    # Load the model from checkpoint
    print("Loading the model...")
    model.load(model_name)

    return model