我有一个使用视网膜网络构建的对象检测模型，该模型是使用Tensorflow后端的Keras构建的。但是现在我希望使用Theano后端进行测试，因为theano线程安全性更高，并且允许在同一模型上运行多个预测。但是，当我尝试使用theano作为后端运行代码时，出现以下错误：
TypeError: Failed to convert object of type <class 'theano.tensor.var.TensorVariable'> to Tensor. Contents: Elemwise{add,no_inplace}.0. Consider casting elements to a supported type
该错误的整个堆栈跟踪为：
Traceback (most recent call last):
File "/data/home/ubuntu/myproject/myprojectenv/lib/python3.5/site-packages/tensorflow/python/framework/tensor_util.py", line 517, in make_tensor_proto
str_values = [compat.as_bytes(x) for x in proto_values]
File "/data/home/ubuntu/myproject/myprojectenv/lib/python3.5/site-packages/tensorflow/python/framework/tensor_util.py", line 517, in <listcomp>
str_values = [compat.as_bytes(x) for x in proto_values]
File "/data/home/ubuntu/myproject/myprojectenv/lib/python3.5/site-packages/tensorflow/python/util/compat.py", line 67, in as_bytes
(bytes_or_text,))
TypeError: Expected binary or unicode string, got Elemwise{add,no_inplace}.0
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "convert_to_theano.py", line 8, in <module>
model = load_model('retinanet_models/models/tlc_all_new30.h5', backbone_name='resnet50')
File "/data/home/ubuntu/myproject/keras_retinanet/models/__init__.py", line 76, in load_model
model = keras.models.load_model(filepath, custom_objects=backbone(backbone_name).custom_objects)
File "/data/home/ubuntu/myproject/myprojectenv/lib/python3.5/site-packages/keras/engine/saving.py", line 261, in load_model
model = model_from_config(model_config, custom_objects=custom_objects)
File "/data/home/ubuntu/myproject/myprojectenv/lib/python3.5/site-packages/keras/engine/saving.py", line 335, in model_from_config
return deserialize(config, custom_objects=custom_objects)
File "/data/home/ubuntu/myproject/myprojectenv/lib/python3.5/site-packages/keras/layers/__init__.py", line 55, in deserialize
printable_module_name='layer')
File "/data/home/ubuntu/myproject/myprojectenv/lib/python3.5/site-packages/keras/utils/generic_utils.py", line 145, in deserialize_keras_object
list(custom_objects.items())))
File "/data/home/ubuntu/myproject/myprojectenv/lib/python3.5/site-packages/keras/engine/network.py", line 1046, in from_config
process_node(layer, node_data)
File "/data/home/ubuntu/myproject/myprojectenv/lib/python3.5/site-packages/keras/engine/network.py", line 1005, in process_node
layer(input_tensors, **kwargs)
File "/data/home/ubuntu/myproject/myprojectenv/lib/python3.5/site-packages/keras/engine/base_layer.py", line 460, in __call__
output = self.call(inputs, **kwargs)
File "/data/home/ubuntu/myproject/keras_retinanet/layers/_misc.py", line 82, in call
return backend.resize_images(source, (target_shape[1], target_shape[2]))
File "/data/home/ubuntu/myproject/keras_retinanet/backend/tensorflow_backend.py", line 38, in resize_images
return tensorflow.image.resize_images(*args, **kwargs)
File "/data/home/ubuntu/myproject/myprojectenv/lib/python3.5/site-packages/tensorflow/python/ops/image_ops_impl.py", line 893, in resize_images
images = ops.convert_to_tensor(images, name='images')
File "/data/home/ubuntu/myproject/myprojectenv/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1014, in convert_to_tensor
as_ref=False)
File "/data/home/ubuntu/myproject/myprojectenv/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1104, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/data/home/ubuntu/myproject/myprojectenv/lib/python3.5/site-packages/tensorflow/python/framework/constant_op.py", line 235, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "/data/home/ubuntu/myproject/myprojectenv/lib/python3.5/site-packages/tensorflow/python/framework/constant_op.py", line 214, in constant
value, dtype=dtype, shape=shape, verify_shape=verify_shape))
File "/data/home/ubuntu/myproject/myprojectenv/lib/python3.5/site-packages/tensorflow/python/framework/tensor_util.py", line 521, in make_tensor_proto
"supported type." % (type(values), values))
TypeError: Failed to convert object of type <class 'theano.tensor.var.TensorVariable'> to Tensor. Contents: Elemwise{add,no_inplace}.0. Consider casting elements to a supported type.
我已经知道如何更改.keras / keras.json文件以选择哪个后端，并且可以正常工作。启动代码时，它会提供Using Theano，所以我知道它使用的是正确的后端