Tensorboard AttributeError: 'ModelCheckpoint' object has no attribute 'on_train_batch_begin'

Question

我目前正在使用 Tensorboard 使用下面的回调，如下所示。

from keras.callbacks import ModelCheckpoint

CHECKPOINT_FILE_PATH = '/{}_checkpoint.h5'.format(MODEL_NAME)
checkpoint = ModelCheckpoint(CHECKPOINT_FILE_PATH, monitor='val_acc', verbose=1, save_best_only=True, mode='max', period=1)

当我运行 Keras 的密集网络模型时，出现以下错误。我的任何其他模型都没有以这种方式运行ning Tensorboard 出现任何问题，这使得这个错误非常奇怪。按照这个Github post，官方的解决方案是使用官方的Tensorboard实现；但是，这需要升级到 Tensorflow 2.0，这对我来说并不理想。任何人都知道为什么我会收到此特定 densenet 的以下错误，是否有人知道 workaround/fix？

AttributeError Traceback (most recent call last) in () 26 batch_size=32, 27 class_weight=class_weights_dict, ---> 28 callbacks=callbacks_list 29 ) 30

2 frames /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/callbacks.py in _call_batch_hook(self, mode, hook, batch, logs) 245 t_before_callbacks = time.time() 246 for callback in self.callbacks: --> 247 batch_hook = getattr(callback, hook_name) 248 batch_hook(batch, logs) 249 self._delta_ts[hook_name].append(time.time() - t_before_callbacks)

AttributeError: 'ModelCheckpoint' object has no attribute 'on_train_batch_begin'

密网我运行宁

from tensorflow.keras import layers, Sequential
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.applications.densenet import preprocess_input, DenseNet121
from keras.optimizers import SGD, Adagrad
from keras.utils.np_utils import to_categorical

IMG_SIZE = 256
NUM_CLASSES = 5
NUM_EPOCHS = 100

x_train = np.asarray(x_train)
x_test = np.asarray(x_test)

y_train = to_categorical(y_train, NUM_CLASSES)
y_test = to_categorical(y_test, NUM_CLASSES)


x_train = x_train.reshape(x_train.shape[0], IMG_SIZE, IMG_SIZE, 3)
x_test = x_test.reshape(x_test.shape[0], IMG_SIZE, IMG_SIZE, 3)

densenet = DenseNet121(
    include_top=False,
    input_shape=(IMG_SIZE, IMG_SIZE, 3)
)

model = Sequential()
model.add(densenet)
model.add(layers.GlobalAveragePooling2D())
model.add(layers.Dense(NUM_CLASSES, activation='softmax'))
model.summary()

model.compile(loss='categorical_crossentropy',
              optimizer='adam',
              metrics=['accuracy'])

history = model.fit(x_train,
                    y_train,
                    epochs=NUM_EPOCHS,
                    validation_data=(x_test, y_test),
                    batch_size=32,
                    class_weight=class_weights_dict,
                    callbacks=callbacks_list
                   )

Answer 1

在您的导入中，您混合了 keras 和 tf.keras，它们彼此 不兼容 ，因为您会遇到像这样的奇怪错误。

所以一个简单的解决方案是选择 keras 或 tf.keras，并从该包中导入所有内容，并且永远不要将其与其他包混合。

Answer 2

从 keras 或 tensorflow.keras

进行所有导入

我希望这能解决问题！[=12=]

Answer 3

是的，从 keras 和 tensorflow 混合导入

尝试坚持 tensorflow.keras 例如：

from tensorflow.keras.callbacks import EarlyStopping

Answer 4

我替换了这一行

from keras.callbacks import EarlyStopping, ModelCheckpoint

到这一行

from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint

Tensorboard AttributeError: 'ModelCheckpoint' object has no attribute 'on_train_batch_begin'

Tensorboard AttributeError: 'ModelCheckpoint' object has no attribute 'on_train_batch_begin'

python

keras

tensorflow

tensorboard