我想在tensorflow中定义一个新的CustomLayer，以便记下自定义的前进和后退操作。 实际上，我已经根据Dense tensorflow层定义了一个CustomLayer。但是它不起作用，我坚持下去。 谁能帮我这个？ 这是我代码的当前版本：
class CustomLayer(Layer):
def __init__(self,
units,
activation=None,
use_bias=True,
kernel_initializer='glorot_uniform',
bias_initializer='zeros',
kernel_regularizer=None,
bias_regularizer=None,
activity_regularizer=None,
kernel_constraint=None,
bias_constraint=None,
dynamic=True,
**kwargs):
if 'input_shape' not in kwargs and 'input_dim' in kwargs:
kwargs['input_shape'] = (kwargs.pop('input_dim'),)
super(CustomLayer, self).__init__(activity_regularizer=regularizers.get(activity_regularizer), **kwargs)
self.units = int(units)
self.activation = activations.get(activation)
self.use_bias = use_bias
self.kernel_initializer = initializers.get(kernel_initializer)
self.bias_initializer = initializers.get(bias_initializer)
self.kernel_regularizer = regularizers.get(kernel_regularizer)
self.bias_regularizer = regularizers.get(bias_regularizer)
self.kernel_constraint = constraints.get(kernel_constraint)
self.bias_constraint = constraints.get(bias_constraint)
self.supports_masking = True
self.input_spec = InputSpec(min_ndim=2)
def build(self, input_shape):
dtype = dtypes.as_dtype(self.dtype or K.floatx())
if not (dtype.is_floating or dtype.is_complex):
raise TypeError('Unable to build Dense layer with non-floating point '
'dtype %s' % (dtype,))
input_shape = tensor_shape.TensorShape(input_shape)
if tensor_shape.dimension_value(input_shape[-1]) is None:
raise ValueError('The last dimension of the inputs to Dense '
'should be defined. Found None.')
last_dim = tensor_shape.dimension_value(input_shape[-1])
self.input_spec = InputSpec(min_ndim=2,
axes={-1: last_dim})
self.kernel = self.add_weight(
'kernel',
shape=[last_dim, self.units],
initializer=self.kernel_initializer,
regularizer=self.kernel_regularizer,
constraint=self.kernel_constraint,
dtype=self.dtype,
trainable=True)
if self.use_bias:
self.bias = self.add_weight(
'bias',
shape=[self.units, ],
initializer=self.bias_initializer,
regularizer=self.bias_regularizer,
constraint=self.bias_constraint,
dtype=self.dtype,
trainable=True)
else:
self.bias = None
self.built = True
def call(self, inputs):
global global_self
global_self = self
return custom_op(inputs)
global_self = None
@tf.custom_gradient
def custom_op(inputs):
self = global_self
rank = len(inputs.shape)
if rank > 2:
# Broadcasting is required for the inputs.
outputs = standard_ops.tensordot(inputs, self.kernel, [[rank - 1], [0]])
# Reshape the output back to the original ndim of the input.
if not context.executing_eagerly():
shape = inputs.shape.as_list()
output_shape = shape[:-1] + [self.units]
outputs.set_shape(output_shape)
else:
inputs = math_ops.cast(inputs, self._compute_dtype)
if K.is_sparse(inputs):
outputs = sparse_ops.sparse_tensor_dense_matmul(inputs, self.kernel)
else:
outputs = gen_math_ops.mat_mul(inputs, self.kernel)
if self.use_bias:
outputs = nn.bias_add(outputs, self.bias)
if self.activation is not None:
return self.activation(outputs) # pylint: disable=not-callable
def custom_grad(dy):
print(dy, [dy])
grad = dy # compute gradient
return grad
return outputs, custom_grad
当我尝试执行时，获取此回溯
Traceback (most recent call last):
File "/home/labt41/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 802, in call
outputs = call_fn(cast_inputs, *args, **kwargs)
File "/home/labt41/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/autograph/impl/api.py", line 237, in wrapper
raise e.ag_error_metadata.to_exception(e)
tensorflow.python.framework.errors_impl.OperatorNotAllowedInGraphError: in converted code:
relative to /home/labt41:
PycharmProjects/TF_Custom/CustomLayer_stackoverflow.py:125 call *
return custom_op(inputs)
PycharmProjects/TF_Custom/CustomLayer_stackoverflow.py:136 decorated *
return _graph_mode_decorator(f, *args, **kwargs)
anaconda3/lib/python3.7/site-packages/tensorflow_core/python/ops/custom_gradient.py:229 _graph_mode_decorator
result, grad_fn = f(*args)
anaconda3/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:547 iter
self._disallow_iteration()
anaconda3/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:543 _disallow_iteration
self._disallow_in_graph_mode("iterating over `tf.Tensor`")
anaconda3/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:523 _disallow_in_graph_mode
" this function with @tf.function.".format(task))
OperatorNotAllowedInGraphError: iterating over tf.Tensor is not allowed in Graph execution. Use Eager execution or decorate this function with @tf.function.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/labt41/PycharmProjects/TF_Custom/CustomLayer_stackoverflow.py", line 179, in <module>
model = create_model()
File "/home/labt41/PycharmProjects/TF_Custom/CustomLayer_stackoverflow.py", line 50, in create_model
layer = CustomLayer(units=128)(visible)
File "/home/labt41/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/base_layer.py", line 814, in call
str(e) + '\n"""')
TypeError: You are attempting to use Python control flow in a layer that was not declared to be dynamic. Pass dynamic=True to the class constructor.
Encountered error:
in converted code:
relative to /home/labt41:
PycharmProjects/TF_Custom/CustomLayer_stackoverflow.py:125 call *
return custom_op(inputs)
PycharmProjects/TF_Custom/CustomLayer_stackoverflow.py:136 decorated *
return _graph_mode_decorator(f, *args, **kwargs)
anaconda3/lib/python3.7/site-packages/tensorflow_core/python/ops/custom_gradient.py:229 _graph_mode_decorator
result, grad_fn = f(*args)
anaconda3/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:547 iter
self._disallow_iteration()
anaconda3/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:543 _disallow_iteration
self._disallow_in_graph_mode("iterating over `tf.Tensor`")
anaconda3/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py:523 _disallow_in_graph_mode
" this function with @tf.function.".format(task))
OperatorNotAllowedInGraphError: iterating over tf.Tensor is not allowed in Graph execution. Use Eager execution or decorate this function with @tf.function.