无法使用 keras 中的回调保存模型答案

【问题标题】：Unable to save model using call backs in keras无法使用 keras 中的回调保存模型
【发布时间】：2021-01-22 05:27:46
【问题描述】：

我正在研究图像识别问题。我正在训练我的模型 200 个 epoch。如果它具有迄今为止最好的验证准确度，我想在每个 epoch 之后保存模型。这是我的代码，

from keras.models import Sequential
from keras.models import Model
from keras.callbacks import ModelCheckpoint, LearningRateScheduler, EarlyStopping, ReduceLROnPlateau, TensorBoard
from keras import optimizers, losses, activations, models
from keras.layers import Convolution2D, Dense, Input, Flatten, Dropout, MaxPooling2D, BatchNormalization, GlobalAveragePooling2D, Concatenate
from keras import applications
from keras import backend as K
from keras import callbacks
from keras.preprocessing.image import ImageDataGenerator

ROWS,COLS = 669,1026


input_shape = (ROWS, COLS, 3)

base_model = applications.VGG19(weights='imagenet', 
                                include_top=False, 
                                input_shape=(ROWS, COLS,3))

l = 0
for layer in base_model.layers:
    layer.trainable = False
    l += 1

c = 0
for layer in base_model.layers:
    c += 1
    if c > l-5:
        layer.trainable = True 

for layer in base_model.layers:
    print(layer,layer.trainable)

base_model.summary()

add_model = Sequential()
add_model.add(base_model)
add_model.add(GlobalAveragePooling2D())
add_model.add(Dense(514, activation='relu'))
add_model.add(Dense(128, activation='relu'))
add_model.add(Dense(64, activation='relu'))
add_model.add(Dropout(0.5))
add_model.add(Dense(8, activation='relu'))
add_model.add(Dropout(0.5))
add_model.add(Dense(1, activation='sigmoid'))

model = add_model
# model.compile(loss='binary_crossentropy', 
#               optimizer=optimizers.SGD(lr=1e-, 
#                                        momentum=0.9),
#               metrics=['accuracy'])
model.compile(loss='binary_crossentropy', 
              optimizer='adam',
              metrics=['accuracy'])
model.summary()

train_data_dir = '/home/spectrograms/train'
validation_data_dir = '/home/spectrograms/test'
nb_train_samples = 791
nb_validation_samples = 198
epochs = 200
batch_size = 3

if K.image_data_format() == 'channels_first':
    input_shape = (3, ROWS, COLS)
else:
    input_shape = (ROWS, COLS,3)


# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0,
    zoom_range=0,
    horizontal_flip=False)

test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(ROWS, COLS),
    batch_size=batch_size,
    class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(ROWS, COLS),
    batch_size=batch_size,
    class_mode='binary')

checkpoint_filepath = '/home/CNN/saved_model/checkpoints/checkpoint-{epoch:02d}-{val_loss:.2f}.h5'

model_checkpoint_callback = callbacks.ModelCheckpoint(
    filepath=checkpoint_filepath,
    save_weights_only=False,
    monitor='val_accuracy',
    mode='max',
    save_best_only=True)

model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    callbacks = [model_checkpoint_callback],
    validation_data=validation_generator,
    validation_steps=nb_validation_samples // batch_size)

但我收到了错误OSError: Unable to create file (unable to open file: name = '/home/CNN/saved_model/checkpoints/checkpoint-01-0.69.h5', errno = 2, error message = 'No such file or directory', flags = 13, o_flags = 242)

但是文件目录实际上退出了。我不明白这是什么问题。

【问题讨论】：

您是否尝试添加 save_weights=True ？
我想保存整个模型。不只是权重。所以 save_weights 应该保持 False 对吧？
在那种情况下，是的

标签： machine-learning keras deep-learning conv-neural-network

【解决方案1】：

在您的代码中添加以下内容

save_dir = '/home/CNN/saved_model/checkpoints/'
if not os.path.exists(save_dir):
   os.makedirs(save_dir)

checkpoint_filepath = os.path.join(save_dir, "checkpoint-{epoch:02d}-{val_loss:.2f}.h5")

model_checkpoint_callback = callbacks.ModelCheckpoint(
filepath=checkpoint_filepath,
save_weights_only=False,
monitor='val_accuracy',
mode='max',
save_best_only=True)

【讨论】：