CNN 程序计算时间过长，没有给出任何输出

Question

我在Jupyter notebook中实现了以下代码，已经90多分钟了，程序还是运行，我还没有得到任何输出。

我正在使用 2012 年中期的 MacBook Pro。 4 GB 内存。我检查了 activity 监视器，内存压力在黄色区域，这意味着 mac 不是运行内存不足，我不知道现在怎么办。

该程序在 CIFAR-10 数据集上实现了 CNN 模型。

import sys
from matplotlib import pyplot
from keras.datasets import cifar10
from tensorflow.keras.utils import to_categorical
from keras.models import Sequential
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Dense
from keras.layers import Flatten
from tensorflow.keras.optimizers import SGD
from keras.preprocessing.image import ImageDataGenerator
from keras.layers import Dropout
from keras.layers import BatchNormalization
import ssl
ssl._create_default_https_context = ssl._create_unverified_context

# load train and test dataset
def load_dataset():
    # load dataset
    (trainX, trainY), (testX, testY) = cifar10.load_data()
    # one hot encode target values
    trainY = to_categorical(trainY)
    testY = to_categorical(testY)
    return trainX, trainY, testX, testY

# scale pixels
def prep_pixels(train, test):
    # convert from integers to floats
    train_norm = train.astype('float32')
    test_norm = test.astype('float32')
    # normalize to range 0-1
    train_norm = train_norm / 255.0
    test_norm = test_norm / 255.0
    # return normalized images
    return train_norm, test_norm

# define cnn model
def define_model():
    model = Sequential()
    model.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(32, 32, 3)))
    model.add(BatchNormalization())
    model.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))
    model.add(BatchNormalization())
    model.add(MaxPooling2D((2, 2)))
    model.add(Dropout(0.2))
    model.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))
    model.add(BatchNormalization())
    model.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))
    model.add(BatchNormalization())
    model.add(MaxPooling2D((2, 2)))
    model.add(Dropout(0.3))
    model.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))
    model.add(BatchNormalization())
    model.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))
    model.add(BatchNormalization())
    model.add(MaxPooling2D((2, 2)))
    model.add(Dropout(0.4))
    model.add(Flatten())
    model.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))
    model.add(BatchNormalization())
    model.add(Dropout(0.5))
    model.add(Dense(10, activation='softmax'))
    # compile model
    opt = SGD(lr=0.001, momentum=0.9)
    model.compile(optimizer=opt, loss='categorical_crossentropy', metrics=['accuracy'])
    return model

# plot diagnostic learning curves
def summarize_diagnostics(history):
    # plot loss
    pyplot.subplot(211)
    pyplot.title('Cross Entropy Loss')
    pyplot.plot(history.history['loss'], color='blue', label='train')
    pyplot.plot(history.history['val_loss'], color='orange', label='test')
    # plot accuracy
    pyplot.subplot(212)
    pyplot.title('Classification Accuracy')
    pyplot.plot(history.history['accuracy'], color='blue', label='train')
    pyplot.plot(history.history['val_accuracy'], color='orange', label='test')
    # save plot to file
    filename = sys.argv[0].split('/')[-1]
    pyplot.savefig(filename + '_plot.png')
    pyplot.close()

# run the test harness for evaluating a model
def run_test_harness():
    # load dataset
    trainX, trainY, testX, testY = load_dataset()
    # prepare pixel data
    trainX, testX = prep_pixels(trainX, testX)
    # define model
    model = define_model()
    # create data generator
    datagen = ImageDataGenerator(width_shift_range=0.1, height_shift_range=0.1, horizontal_flip=True)
    # prepare iterator
    it_train = datagen.flow(trainX, trainY, batch_size=64)
    # fit model
    steps = int(trainX.shape[0] / 64)
    history = model.fit_generator(it_train, steps_per_epoch=steps, epochs=100, validation_data=(testX, testY), verbose=0)
    # evaluate model
    _, acc = model.evaluate(testX, testY, verbose=0)
    print('> %.3f' % (acc * 100.0))
    # learning curves
    summarize_diagnostics(history)

# entry point, run the test harness
run_test_harness()```

Answer 1

您的模型训练时间过长的原因是：

您正在训练一个包含多层的大型模型 100 个时期
您使用的是一台性能相对较低的计算机（根据我通过谷歌搜索发现它只有 2.5 GHZ 处理器。）

您可以使用具有 GPU 和 TPU 的免费云环境（例如 Google Colab（https://colab.research.google.com/）或更好的 Kaggle notebook 来加快训练速度更长的时间。如果你想运行它在你的 mac 上，你可以尝试缩小模型或减少你正在训练的时期数。

将笔记本移植到 Google Colab 或 Kaggle 笔记本应该很容易。您需要为 Google Colab 创建一个 google 帐户或为 Kaggle 创建一个单独的帐户。

希望对您有所帮助！

Answer 2

您需要高 GPU 操作系统才能在 Jypyter Notebook 上运行。否则使用 Google Colab (https://colab.research.google.com/)，由于 epoch 值高，在 jupyter notebook

中会花费大量时间

CNN 程序计算时间过长，没有给出任何输出

CNN program has been computing for too long and not giving any output

python

machine-learning

deep-learning

keras

tensorflow