每当我尝试使用TensorFlow训练我的模型时，我都会遇到一个TypeError。目前为止：
history = model.fit(train_batches, steps_per_epoch=train_steps, class_weight=class_weights, validation_data=validation_batches, validation_steps=val_steps, epochs=30, verbose=1, callbacks=callbacks_list )会给我以下错误：
Traceback (most recent call last): File "/home/brian/Desktop/381-deep-learning/main.py", line 359, in <module> callbacks=callbacks_list File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 66, in _method_wrapper return method(self, *args, **kwargs) File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 815, in fit model=self) File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/data_adapter.py", line 1112, in __init__ model=model) File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/data_adapter.py", line 772, in __init__ peek, x = self._peek_and_restore(x) File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/data_adapter.py", line 830, in _peek_and_restore peek = next(x) File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/keras_preprocessing/image/iterator.py", line 104, in __next__ return self.next(*args, **kwargs) File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/keras_preprocessing/image/iterator.py", line 116, in next return self._get_batches_of_transformed_samples(index_array) File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/keras_preprocessing/image/iterator.py", line 239, in _get_batches_of_transformed_samples x = self.image_data_generator.standardize(x) File "/home/brian/Desktop/381-deep-learning/venv/lib/python3.6/site-packages/keras_preprocessing/image/image_data_generator.py", line 704, in standardize x = self.preprocessing_function(x)TypeError: 'module' object is not callable这是我的模型定义：
resnet = tf.keras.applications.inception_resnet_v2.InceptionResNetV2()predictions_layer = tf.keras.layers.Dense(7, activation='softmax')(x)# Create an Image Data Generator to input later into our model.data_generation = ImageDataGenerator( # Use Inception ResNet v2 preprocessing_function=tf.keras.applications.inception_resnet_v2)model = tf.keras.Model(inputs=resnet.input, outputs=predictions_layer)到目前为止，一切都正常运行，我还仔细检查了所有的导入语句（通常会导致此类错误），一切看起来都正常：
import osos.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'import pandas as pdimport numpy as npimport shutilimport tensorflow as tffrom tensorflow.keras.layers import Dense, Dropoutfrom tensorflow.keras.optimizers import SGDfrom tensorflow.keras.metrics import categorical_crossentropyfrom tensorflow.keras.preprocessing.image import ImageDataGeneratorfrom tensorflow.keras.models import Modelfrom tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau, ModelCheckpointfrom sklearn.metrics import confusion_matrixfrom tensorflow.keras.preprocessing.image import ImageDataGeneratorfrom sklearn.model_selection import train_test_splitfrom PIL import ImageFileImageFile.LOAD_TRUNCATED_IMAGES = True到目前为止，我尝试过的一些方法包括降级TensorFlow版本（2.2.0 -> 1.15.2）和Keras版本（2.3.1 -> 1.2.2）；这样做的唯一区别是我的模型可以进入第一个epoch，但随后以同样的错误失败。
另外，如果这有帮助的话，这里是我用来编译模型的方法：
model.compile(optimizer=tf.keras.optimizers.SGD(learning_rate=0.0007), loss='categorical_crossentropy', metrics=[tf.keras.metrics.categorical_accuracy])以及有问题的callbacks_list（然而，在使用Pycharm调试器后，这个列表的值如预期）：
checkpoint = tf.keras.callbacks.ModelCheckpoint(filepath, monitor='categorical_accuracy', verbose=1, save_best_only=True, mode='max')reduce_lr = tf.keras.callbacks.ReduceLROnPlateau(monitor='categorical_accuracy', factor=0.5, patience=2, verbose=1, mode='max', min_lr=0.00001)callbacks_list = [checkpoint, reduce_lr]我还提供了一个整个文件的pastebin，以防我遗漏了任何可能导致问题的重要信息： https://pastebin.com/raw/XCWj0b78
回答：
我调用了一个模块而不是模块中包含的类。
# Create an Image Data Generator to input later into our model.data_generation = ImageDataGenerator( # Use Inception ResNet v2 preprocessing_function=tf.keras.applications.inception_resnet_v2.preprocess_input)阅读文档后，我在生成器中使用了.preprocess_input()函数。
