训练神经网络时列出超出范围的索引

Question

我正在尝试使用ResNet实现卫星图像的超分辨率。我已经加载了所有的图像。我有2240个图像用于输入和输出，560个用于验证。我总是出现“列表索引超出范围”错误。是因为图像的大小吗？如果是这样，是否有任何方法可以更改代码中图像的大小

代码如下：

from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Convolution2D
from keras.preprocessing.image import ImageDataGenerator
from keras.layers import UpSampling2D
import tensorflow as tf
from keras.models import Sequential
from keras.models import Model

train_datagen = ImageDataGenerator(rescale=1./255)
validation_datagen = ImageDataGenerator(rescale=1./255)
train_indir = r"D:\\For_Training1\\train"
validation_indir = r"D:\\For_Training2\\val"
train_generator = train_datagen.flow_from_directory(
        train_indir,
        target_size = (3402,3401),
        class_mode='input')
valid_generator = validation_datagen.flow_from_directory(
            validation_indir,
            target_size = (3402,3401),
            class_mode = 'input')

train_outdir = r"D:\\For_Training3\\Train"
train_generator = train_datagen.flow_from_directory(
        train_outdir,
        target_size = (3402,3401),
        class_mode='input')

base_model = tf.keras.applications.ResNet50(
    include_top=False,
    weights="imagenet",
    input_shape=(3402,3401,3),
    pooling=None,  
)
for layer in base_model.layers[:46]:
    layer.trainable = False
model = Sequential()
model.add(base_model)
model.add(Convolution2D(3,9,activation='relu',padding='same'))
model.add(UpSampling2D())
model.add(UpSampling2D())
model.add(Convolution2D(3,9,activation='relu',padding='same'))




model.compile(optimizer="adam", loss='mean_squared_error', metrics=['mean_squared_error'])
model.fit(train_indir,train_outdir,validation_data = validation_indir,batch_size=32, epochs=100, verbose=0)

错误：

Found 2240 images belonging to 1 classes.
Found 560 images belonging to 1 classes.
Found 2240 images belonging to 1 classes.
---------------------------------------------------------------------------
IndexError                                Traceback (most recent call last)
<ipython-input-5-7c9709ce4116> in <module>
     45 
     46 model.compile(optimizer="adam", loss='mean_squared_error', metrics=['mean_squared_error'])
---> 47 model.fit(train_indir,train_outdir,validation_data = validation_indir,batch_size=32, epochs=100, verbose=0)
     48 
     49 

~\anaconda3\lib\site-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)
   1106          training_utils.RespectCompiledTrainableState(self):
   1107       # Creates a `tf.data.Dataset` and handles batch and epoch iteration.
-> 1108       data_handler = data_adapter.get_data_handler(
   1109           x=x,
   1110           y=y,

~\anaconda3\lib\site-packages\keras\engine\data_adapter.py in get_data_handler(*args, **kwargs)
   1346   if getattr(kwargs["model"], "_cluster_coordinator", None):
   1347     return _ClusterCoordinatorDataHandler(*args, **kwargs)
-> 1348   return DataHandler(*args, **kwargs)
   1349 
   1350 

~\anaconda3\lib\site-packages\keras\engine\data_adapter.py in __init__(self, x, y, sample_weight, batch_size, steps_per_epoch, initial_epoch, epochs, shuffle, class_weight, max_queue_size, workers, use_multiprocessing, model, steps_per_execution, distribute)
   1136     adapter_cls = select_data_adapter(x, y)
   1137     self._verify_data_adapter_compatibility(adapter_cls)
-> 1138     self._adapter = adapter_cls(
   1139         x,
   1140         y,

~\anaconda3\lib\site-packages\keras\engine\data_adapter.py in __init__(self, x, y, sample_weights, sample_weight_modes, batch_size, shuffle, **kwargs)
    655         sample_weights, sample_weight_modes)
    656 
--> 657     self._internal_adapter = TensorLikeDataAdapter(
    658         x,
    659         y=y,

~\anaconda3\lib\site-packages\keras\engine\data_adapter.py in __init__(self, x, y, sample_weights, sample_weight_modes, batch_size, epochs, steps, shuffle, **kwargs)
    239     inputs = pack_x_y_sample_weight(x, y, sample_weights)
    240 
--> 241     num_samples = set(int(i.shape[0]) for i in tf.nest.flatten(inputs)).pop()
    242     _check_data_cardinality(inputs)
    243 

~\anaconda3\lib\site-packages\keras\engine\data_adapter.py in <genexpr>(.0)
    239     inputs = pack_x_y_sample_weight(x, y, sample_weights)
    240 
--> 241     num_samples = set(int(i.shape[0]) for i in tf.nest.flatten(inputs)).pop()
    242     _check_data_cardinality(inputs)
    243 

~\anaconda3\lib\site-packages\tensorflow\python\framework\tensor_shape.py in __getitem__(self, key)
    894       else:
    895         if self._v2_behavior:
--> 896           return self._dims[key].value
    897         else:
    898           return self._dims[key]

IndexError: list index out of range