如何使用 model.fit 生成器

Question

我有这个变量

#Data Preprocessing
train_datagen = ImageDataGenerator(rescale=1.0/255)
train_generator = train_datagen.flow_from_directory(directory=images_train,target_size=(1024,1024),class_mode='categorical',batch_size=32)

val_datagen = ImageDataGenerator(rescale=1.0/255)
val_generator = train_datagen.flow_from_directory(directory=images_valid,target_size=(1024,1024),class_mode='categorical',batch_size=32)

test_datagen = ImageDataGenerator(rescale=1.0/255)
test_generator = train_datagen.flow_from_directory(directory=images_test,target_size=(1024,1024),class_mode='categorical',batch_size=32)

我想输入 model.fit 但我不知道如何输入。它保持错误

这是错误

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-38-032c8242ff66> in <module>
      2                     steps_per_epoch=len(train_generator)//32,
      3                     epochs=20,validation_data=val_generator,
----> 4                     validation_steps=len(val_generator)//32)

1 frames
/usr/local/lib/python3.7/dist-packages/keras/engine/training.py in 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, max_queue_size, workers, use_multiprocessing)
   1418         logs = tf_utils.sync_to_numpy_or_python_type(logs)
   1419         if logs is None:
-> 1420           raise ValueError('Unexpected result of `train_function` '
   1421                            '(Empty logs). Please use '
   1422                            '`Model.compile(..., run_eagerly=True)`, or '

ValueError: Unexpected result of `train_function` (Empty logs). Please use `Model.compile(..., run_eagerly=True)`, or `tf.config.run_functions_eagerly(True)` for more information of where went wrong, or file a issue/bug to `tf.keras`.

如何使用 model.fit 函数？

Answer 1

在调用 model.fit(x, y) 之前，请先通过以下方式编译它：

model.compile()

参考：

https://keras.io/api/models/model_training_apis/