维数未知时如何创建一维范围张量？

Question

我有一个 n 维数组。我需要根据尺寸创建一维范围张量。

举个例子：

x = tf.placeholder(tf.float32, shape=[None,4]) 
  
r = tf.range(start=0, limit=, delta=x.shape[0],dtype=tf.int32, name='range')

sess = tf.Session()

result = sess.run(r, feed_dict={x: raw_lidar})
print(r)

问题是，x.shape[0]在构建计算图时是none。所以我无法使用范围构建张量。它给出了一个错误。

ValueError: Cannot convert an unknown Dimension to a Tensor: ?

对问题的任何建议或帮助。

提前致谢

Answer 1

x.shape[0] 当运行此代码是图形模式时，可能还不存在。如果你想要一个值，你需要使用tf.shape(x)[0].

documentation for tf.Tensor.get_shape 中有关该行为的更多信息。摘录（重点是我的）：

tf.Tensor.get_shape() is equivalent to tf.Tensor.shape.

When executing in a tf.function or building a model using tf.keras.Input, Tensor.shape may return a partial shape (including None for unknown dimensions). See tf.TensorShape for more details.
>>> inputs = tf.keras.Input(shape = [10])
>>> # Unknown batch size
>>> print(inputs.shape)
(None, 10)
The shape is computed using shape inference functions that are registered for each tf.Operation. The returned tf.TensorShape is determined at build time, without executing the underlying kernel. It is not a tf.Tensor. If you need a shape tensor, either convert the tf.TensorShape to a tf.constant, or use the tf.shape(tensor) function, which returns the tensor's shape at execution time.

维数未知时如何创建一维范围张量？

How to create a 1-D range tensor when dimension is Unknown?

python

tensorflow

computation-graph