julianyulu / tf_pb_model_convert Goto Github PK

Hi,

因想轉換以下這個tensorflow mode為1.15使用，
https://tfhub.dev/google/movenet/singlepose/lightning/4
但用你的tf22_saved_model_to_tf115_pb.py出現以下錯誤。

Traceback (most recent call last):
File "convert.py", line 17, in
model = tf.keras.models.load_model(model_path)
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/save.py", line 190, in load_model
return saved_model_load.load(filepath, compile)
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/saved_model/load.py", line 116, in load
model = tf_load.load_internal(path, loader_cls=KerasObjectLoader)
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/saved_model/load.py", line 602, in load_internal
loader = loader_cls(object_graph_proto,
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/saved_model/load.py", line 188, in init
super(KerasObjectLoader, self).init(*args, **kwargs)
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/saved_model/load.py", line 123, in init
self._load_all()
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/saved_model/load.py", line 209, in _load_all
self._layer_nodes = self._load_layers()
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/saved_model/load.py", line 309, in _load_layers
layers[node_id] = self._load_layer(proto.user_object, node_id)
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/saved_model/load.py", line 335, in _load_layer
obj, setter = self._revive_from_config(proto.identifier, metadata, node_id)
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/saved_model/load.py", line 353, in _revive_from_config
self._revive_layer_from_config(metadata, node_id))
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/keras/saving/saved_model/load.py", line 407, in _revive_layer_from_config
obj = layers_module.deserialize(
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/keras/layers/serialization.py", line 105, in deserialize
return deserialize_keras_object(
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/keras/utils/generic_utils.py", line 375, in deserialize_keras_object
return cls.from_config(cls_config)
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/base_layer.py", line 655, in from_config
return cls(**config)
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/keras/layers/convolutional.py", line 1985, in init
super(DepthwiseConv2D, self).init(
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/keras/layers/convolutional.py", line 582, in init
super(Conv2D, self).init(
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/keras/layers/convolutional.py", line 121, in init
super(Conv, self).init(
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/training/tracking/base.py", line 456, in _method_wrapper
result = method(self, *args, **kwargs)
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/keras/engine/base_layer.py", line 294, in init
generic_utils.validate_kwargs(kwargs, allowed_kwargs)
File "/home/lion/.local/lib/python3.8/site-packages/tensorflow/python/keras/utils/generic_utils.py", line 792, in validate_kwargs
raise TypeError(error_message, kwarg)
TypeError: ('Keyword argument not understood:', 'groups')

請教該如何解決？
或是可以提供你使用的環境？或是不能直接這樣用？
我使用的指令是python3.8 tf22_saved_model_to_tf115_pb.py

PS. tensorflow 2.2 keras 2.4.3