Python Tensorflow 2.3/2.2-导入/导出问题

嗨，当尝试导入使用Tensorflow 2.3（x86）创建的Tensorflow 2.2（在arm上，nvidia jetson）模型时，我遇到以下错误：

File "Anomaly.py", line 50, in anomaly_detection
model = tf.keras.models.load_model('./model.h5')
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/saving/save.py", line 184, in load_model
return hdf5format.loadmodelfromhdf5(filepath, custom_objects, compile)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/saving/hdf5format.py", line 178, in loadmodelfromhdf5
customobjects=customobjects)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/saving/modelconfig.py", line 55, in modelfrom_config
return deserialize(config, customobjects=customobjects)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/layers/serialization.py", line 109, in deserialize
printablemodulename='layer')
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/utils/genericutils.py", line 373, in deserializekeras_object
list(custom_objects.items())))
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/sequential.py", line 398, in from_config
customobjects=customobjects)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/layers/serialization.py", line 109, in deserialize
printablemodulename='layer')
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/utils/genericutils.py", line 375, in deserializekeras_object
return cls.fromconfig(clsconfig)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/baselayer.py", line 655, in fromconfig
return cls(**config)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/layers/convolutional.py", line 453, in init **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/layers/convolutional.py", line 127, in init **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/tracking/base.py", line 456, in methodwrapper
result = method(self, args, *kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 294, in init
genericutils.validatekwargs(kwargs, allowed_kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/utils/genericutils.py", line 792, in validatekwargs
raise TypeError(error_message, kwarg)
TypeError: ('Keyword argument not understood:', 'groups')

模型与此类似：

model = tf.keras.models.Sequential()
model.add(layers.Conv1D(64, 3, activation='relu', padding="same",input_shape=(window,1)))
model.add(layers.MaxPooling1D(2))
model.add(layers.BatchNormalization())
model.add(layers.Dropout(0.1))
...

我尝试了.tf和.h5来保存模型。 我认为错误与不同的keras版本有关，但是我不想（可以）在任何机器上更改keras版本。 有没有办法解决这个兼容性问题

任何帮助都将不胜感激

致以最良好的祝愿，

---

Dominik

是否尝试在创建模型的计算机中导入模型？此外，建议您在TF2中使用Tensorflow保存的模型格式。你能试着用保存的模型格式代替.h5吗？我试过了.tf和.h5。对于这两种情况，我都会遇到相同的错误在我创建模型的机器上导入模型没有问题。不是.tf格式。保存的模型。选中此复选框是否尝试在创建模型的计算机中导入模型？此外，建议您在TF2中使用Tensorflow保存的模型格式。你能试着用保存的模型格式代替.h5吗？我试过了.tf和.h5。对于这两种情况，我都会遇到相同的错误在我创建模型的机器上导入模型没有问题。不是.tf格式。保存的模型。检查这个