I found piece of code like this:
y = tf.strided_slice(data, [0, i * num_steps + 1],
[batch_size, (i + 1) * num_steps + 1])
y.set_shape([batch_size, num_steps])
as Clarification on tf.Tensor.set_shape() said, set_shape can make the shape information more specific. But why data's shape information here is not specific? When does the tensor's information unspecific?
