使用ImageDataGenerator训练CNN时第二轮Epoch触发AttributeError

训练基于ImageDataGenerator的CNN模型时，第二轮Epoch结束后抛出AttributeError: 'NoneType' object has no attribute 'items'错误。

模型代码 #

import tensorflow as tf
from tensorflow.keras.optimizers import RMSprop

def create_model():
  '''创建包含4个卷积层的CNN模型'''
  model = tf.keras.models.Sequential([
      tf.keras.layers.Conv2D(32, (3,3), activation='relu', input_shape=(150, 150, 3)),
      tf.keras.layers.MaxPooling2D(2, 2),
      tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
      tf.keras.layers.MaxPooling2D(2,2),
      tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
      tf.keras.layers.MaxPooling2D(2,2),
      tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
      tf.keras.layers.MaxPooling2D(2,2),
      tf.keras.layers.Flatten(),
      tf.keras.layers.Dense(512, activation='relu'),
      tf.keras.layers.Dense(1, activation='sigmoid')
  ])

  model.compile(loss='binary_crossentropy',
                optimizer=RMSprop(learning_rate=1e-4),
                metrics=['accuracy'])
  
  return model


from tensorflow.keras.preprocessing.image import ImageDataGenerator

train_datagen = ImageDataGenerator(rescale=1./255)
test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
        train_dir,  # 训练图像源目录
        target_size=(150, 150),  # 所有图像将被调整为150x150
        batch_size=20,
        # 使用binary_crossentropy损失，因此需要二进制标签
        class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
        validation_dir,
        target_size=(150, 150),
        batch_size=20,
        class_mode='binary',
        shuffle= False)


EPOCHS = 20

model = create_model()

history = model.fit(
      train_generator,
      steps_per_epoch=100,  # 2000张图像 = batch_size * steps
      epochs=EPOCHS,
      validation_data=validation_generator,
      validation_steps=50,  # 1000张图像 = batch_size * steps
      verbose=2)

报错信息 #

AttributeError                            Traceback (most recent call last)
Cell In[15], line 8
      5 model = create_model()
      7 # 训练模型
----> 8 history = model.fit(
      9       train_generator,
     10       steps_per_epoch=100,  # 2000 images = batch_size * steps
     11       epochs=EPOCHS,
     12       validation_data=validation_generator,
     13       validation_steps=50,  # 1000 images = batch_size * steps
     14       verbose=2)

File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\keras\src\utils\traceback_utils.py:122, in filter_traceback.<locals>.error_handler(*args, **kwargs)
    119     filtered_tb = _process_traceback_frames(e.__traceback__)
    120     # 如需查看完整堆栈跟踪，请调用：
    121     # `keras.config.disable_traceback_filtering()`
--> 122     raise e.with_traceback(filtered_tb) from None
    123 finally:
    124     del filtered_tb

File ~\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\keras\src\backend\tensorflow\trainer.py:354, in TensorFlowTrainer.fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq)
    333         self._eval_epoch_iterator = TFEpochIterator(
    334             x=val_x,
    335             y=val_y,
...
    355     }
    356     epoch_logs.update(val_logs)
    358 callbacks.on_epoch_end(epoch, epoch_logs)

AttributeError: 'NoneType' object has no attribute 'items'
输出已截断。可查看滚动元素或在文本编辑器中打开。调整单元格输出设置...

已尝试的调试步骤 #

• 升级TensorFlow与Keras版本；
• 搭建更简单的神经网络，可正常运行；
• 手动使用numpy处理验证数据而非直接传入validation_generator，但训练数据的准确率和损失值仅在偶数轮Epoch时为0，问题仍未解决。

已确认验证数据已正常加载。

环境版本信息 #

• Python 3.11.9
• TensorFlow 2.17.0
• Keras 3.4.1

内容的提问来源于Stack Exchange，提问作者Darshil Pungalia