这是Keras和Python的代码。当以下代码在Linux Mint上运行时，所有的批次都没有完成。训练总是停留在第32批次，如下所示：

1/100  .............. ETA 30:00 Loss ..  2/100 =........... ETA 29:59 Loss ..  3/100 ==......... ETA 29:58 Loss ..  .  .  .  32/100 ==....... ETA 25:00 Loss .. 

(训练因不明原因停止)

但是当在Windows上运行这段代码时，训练可以正常进行直到第100批次。是什么导致了这种行为？

from __future__ import print_functionimport numpy as npimport kerasfrom keras.models import Sequentialfrom keras.layers import Conv2D, MaxPooling2Dfrom keras.layers import Activation, Dropout, Flatten, Densefrom keras.layers.noise import AlphaDropoutfrom keras.preprocessing.image import ImageDataGeneratorfrom keras.models import model_from_jsonfrom keras.layers import Dense, Dropout, Activationfrom keras.preprocessing.text import Tokenizerimport keras.backend.tensorflow_backend as KTFimport tensorflow as tfimport os.pathf_log = './log'f_model = './model/dogvscat'model_yaml = 'dogvscat_model.yaml'model_filename = 'dogvscat_model.json'weights_filename = 'dogvscat_model_weights.hdf5'batch_size = 64epochs = 15nb_validation_samples = 100print('Building model...')if os.path.isfile(os.path.join(f_model,model_filename)):    print('Saved parameters found. I will use this file...')    json_string = open(os.path.join(f_model, model_filename)).read()    model = model_from_json(json_string)    model.summary()    model.compile(loss='categorical_crossentropy',                optimizer='adam',                metrics=['accuracy'])    model.load_weights(os.path.join(f_model,weights_filename))else:    print('Saved parameters Not found. Creating new model...')    model = Sequential()    model.add(Conv2D(32, (3, 3), input_shape=(128, 128, 3)))    model.add(Activation('selu'))    model.add(MaxPooling2D(pool_size=(2, 2)))    model.add(Conv2D(64, (3, 3)))    model.add(Activation('selu'))    model.add(MaxPooling2D(pool_size=(2, 2)))    model.add(Flatten())    model.add(Dense(64, kernel_initializer='lecun_normal'))    model.add(Activation('selu'))    model.add(AlphaDropout(0.1))    model.add(Dense(2))    model.add(Activation('softmax'))    model.summary()    model.compile(loss='categorical_crossentropy',                optimizer='adam',                metrics=['accuracy'])train_datagen = ImageDataGenerator(    rescale=1.0 / 255,    shear_range=0.2,    zoom_range=0.2,    horizontal_flip=True)test_datagen = ImageDataGenerator(rescale=1.0 / 255)train_generator = train_datagen.flow_from_directory(    'data/train',    target_size=(128, 128),    batch_size=batch_size,    class_mode='categorical',    shuffle=True)validation_generator = test_datagen.flow_from_directory(    'data/validation',    target_size=(128, 128),    batch_size=batch_size,    class_mode='categorical',    shuffle=True)tb_cb = keras.callbacks.TensorBoard(log_dir=f_log, histogram_freq=0)cp_cb = keras.callbacks.ModelCheckpoint(filepath = os.path.join(f_model,weights_filename), monitor='val_loss', verbose=1, save_best_only=True, mode='auto')cbks = [tb_cb, cp_cb]history = model.fit_generator(    train_generator,    steps_per_epoch=nb_validation_samples,    epochs=epochs,    validation_data=validation_generator,    validation_steps=nb_validation_samples,    callbacks=cbks    )score = model.evaluate_generator(validation_generator, nb_validation_samples)print('')print('Test score:', score[0])print('Test accuracy:', score[1])json_string = model.to_json()       open(os.path.join(f_model,model_filename), 'w').write(json_string)      yaml_string = model.to_yaml()       open(os.path.join(f_model,model_yaml), 'w').write(yaml_string)      print('save weights')       model.save_weights(os.path.join(f_model,weights_filename))      

回答：

你的代码中有一个错误，你应该修改steps_per_epoch和validation_steps，如下所示。

history = model.fit_generator(train_generator,steps_per_epoch=np.ceil(nb_training_samples/batch_size),epochs=epochs,validation_data=validation_generator,validation_steps=np.ceil(nb_validation_samples/batch_size),callbacks=cbks)

在每个步骤中都会使用你的batch_size数量的样本，因此你需要np.ceil(nb_training_samples/batch_size)步来完成一个epoch