从 Keras 切换到 tf.keras 会向我的屏幕发送垃圾邮件 #010

Question

我构建了一个简单的 Keras 模型，用于在 Amazon SageMaker 中进行实验。我正在使用 Python 3.5 TensorFlow 1.12.0。最近，我将模型切换为使用 TensorFlow.keras，但这样做会导致在下载图像净重并在拟合调用期间显示批次精度时重复打印#010后面的。#015

例如，在 verbose=1 中model.fit：

纪元 1/1

015 1/1563 [................................] - 预计到达时间：5:50:36 - 损失：2.2798 - acc ： 0.1875#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010 #010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010 #010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010 #010#010#010#010#010#010#010#010#010#010#010#010#015

3/1563 [......................................] - 预计到达时间：1:57:18 - 损失：2.3002 - acc: 0.1146#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010# 010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010# 010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010# 010#010#010#010#010#010#010#010#010#010#010#010#015 5/1563 [........................ .........] - 预计到达时间：1:10:36 - 损失：2.3088 - 累计：0.1062#010#010#010#010#010#010#010#010#010#010#010#010 #010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010 #010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010 #010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010#010

有谁知道为什么会发生这种情况或者我该如何防止这种情况？使用最小示例进行复制可能需要通过 SageMaker 运行，但我从 Keras 切换到 tf.keras 的代码来自此示例，特别是trainer/start.py文件：

# Copyright 2018 Amazon.com, Inc. or its affiliates. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License"). You
# may not use this file except in compliance with the License. A copy of
# the License is located at
#
#     http://aws.amazon.com/apache2.0/
#
# or in the "license" file accompanying this file. This file is
# distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF
# ANY KIND, either express or implied. See the License for the specific
# language governing permissions and limitations under the License.
from __future__ import absolute_import
from __future__ import print_function

import keras
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
import os
import numpy as np

from trainer.environment import create_trainer_environment

NUM_CLASSES = 10
EPOCHS = 10
NUM_PREDICTIONS = 20
MODEL_NAME = 'keras_cifar10_trained_model.h5'

# the trainer environment contains useful information about
env = create_trainer_environment()
print('creating SageMaker trainer environment:\n%s' % str(env))

# getting the hyperparameters
batch_size = env.hyperparameters.get('batch_size', object_type=int)
data_augmentation = env.hyperparameters.get('data_augmentation', default=True, object_type=bool)
learning_rate = env.hyperparameters.get('learning_rate', default=.0001, object_type=float)
width_shift_range = env.hyperparameters.get('width_shift_range', object_type=float)
height_shift_range = env.hyperparameters.get('height_shift_range', object_type=float)
EPOCHS = env.hyperparameters.get('epochs', default=10, object_type=int)

# reading data from train and test channels
train_data = np.load(os.path.join(env.channel_dirs['train'], 'cifar-10-npz-compressed.npz'))
(x_train, y_train) = train_data['x'], train_data['y']

test_data = np.load(os.path.join(env.channel_dirs['test'], 'cifar-10-npz-compressed.npz'))
(x_test, y_test) = test_data['x'], test_data['y']


model = Sequential()
model.add(Conv2D(32, (3, 3), padding='same', input_shape=x_train.shape[1:]))
model.add(Activation('relu'))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Conv2D(64, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(NUM_CLASSES))
model.add(Activation('softmax'))

# initiate RMSprop optimizer
opt = keras.optimizers.rmsprop(lr=learning_rate, decay=1e-6)

# Let's train the model using RMSprop
model.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy'])

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255

if not data_augmentation:
    print('Not using data augmentation.')
    model.fit(x_train, y_train, batch_size=batch_size, epochs=EPOCHS, validation_data=(x_test, y_test), shuffle=True)
else:
    print('Using real-time data augmentation.')
    # This will do preprocessing and real time data augmentation:
    data_generator = ImageDataGenerator(
        featurewise_center=False,  # set input mean to 0 over the dataset
        samplewise_center=False,  # set each sample mean to 0
        featurewise_std_normalization=False,  # divide inputs by std of the dataset
        samplewise_std_normalization=False,  # divide each input by its std
        zca_whitening=False,  # apply ZCA whitening
        rotation_range=0,  # randomly rotate images in the range (degrees, 0 to 180)
        width_shift_range=width_shift_range,  # randomly shift images horizontally (fraction of total width)
        height_shift_range=height_shift_range,  # randomly shift images vertically (fraction of total height)
        horizontal_flip=True,  # randomly flip images
        vertical_flip=False)  # randomly flip images

    # Compute quantities required for feature-wise normalization
    # (std, mean, and principal components if ZCA whitening is applied).
    data_generator.fit(x_train)

    # Fit the model on the batches generated by data_generator.flow().
    data_generator_flow = data_generator.flow(x_train, y_train, batch_size=batch_size)
    model.fit_generator(data_generator_flow, epochs=EPOCHS, validation_data=(x_test, y_test), workers=4)

# Save model and weights
model_path = os.path.join(env.model_dir, MODEL_NAME)
model.save(model_path)
print('Saved trained model at %s ' % model_path)

# Score trained model.
scores = model.evaluate(x_test, y_test, verbose=1)
print('Test loss:', scores[0])
print('Test accuracy:', scores[1])

Answer 1

我今天遇到了这个有同样问题的老问题，并想为未来的读者留下答案，因为它仍然是一个悬而未决的问题。在 Sagemaker 上从 切换tensorflow 1.12到1.15.4，我不得不从 切换到keras，tf.keras遇到您描述的问题。关键似乎在这里，因为 keras 使用退格字符（\b 或 octo #010）来创建进度条，而且我认为由于笔记本不是交互式环境，该进度条以某种方式转换为静态字符。目前建议的唯一解决方法是减少冗长，将verbose=2 in model.fit.