问题描述
class MyLayer(Layer):
def __init__(self,config,**kwargs):
super(MyLayer,self).__init__(**kwargs)
....
def call(self,x):
B,T,C = x.shape.as_list()
...
ones = tf.ones((B,C))
...
# output projection
y = ...
return y
现在问题是评估图层时B
(批次大小)为None,这导致tf.ones
失败并出现以下错误:
ValueError: in user code:
<ipython-input-69-f3322a54c05c>:29 call *
ones = tf.ones((B,C))
/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper **
return target(*args,**kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/array_ops.py:3080 ones
shape = ops.convert_to_tensor(shape,dtype=dtypes.int32)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/profiler/trace.py:163 wrapped
return func(*args,**kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py:1535 convert_to_tensor
ret = conversion_func(value,dtype=dtype,name=name,as_ref=as_ref)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/constant_op.py:356 _tensor_shape_tensor_conversion_function
"Cannot convert a partially kNown TensorShape to a Tensor: %s" % s)
ValueError: Cannot convert a partially kNown TensorShape to a Tensor: (None,8,128)
我该如何工作?
解决方法
如果只想获得与x
相同形状的张量,则可以使用tf.ones_like。像这样:
class MyLayer(Layer):
....
def call(self,x):
ones = tf.ones_like(x)
...
# output projection
y = ...
return y
直到运行时才需要知道x
的形状。
但是,通常,我们可能需要在运行时之前知道输入的形状,在这种情况下,我们可以在我们的层中实现build()
方法,该方法将input_shape
作为参数,并在我们编译我们的模型。
从文档here复制的示例:
class Linear(keras.layers.Layer):
def __init__(self,units=32):
super(Linear,self).__init__()
self.units = units
def build(self,input_shape):
self.w = self.add_weight(
shape=(input_shape[-1],self.units),initializer="random_normal",trainable=True,)
self.b = self.add_weight(
shape=(self.units,),trainable=True
)
def call(self,inputs):
return tf.matmul(inputs,self.w) + self.b