CODEWITHSUNDEEP
pythontensorflow
Shadow
Shadow

Reputation: 2478

Why tensorflow may want to specify dynamic dimension

I have an existing complex model. Inside there is tensor x with shape (None, 128, 128, 3). First axis has dynamic shape, that should be materialized when batch is passed to feed_dict in session.run. However when I attempt to define broadcast operation to shape of x:

y = tf.broadcast_to(z, (x.shape[0], x.shape[1], x.shape[2], 1))

Exception is raised:

Failed to convert object of type <class 'tuple'> to 
Tensor. Contents: (Dimension(None), Dimension(128), 
Dimension(128), 1). Consider casting elements to a supported type.

Exception occurs when creating model, not when running it. Converting first element to number helps, but this is not the solution.

Upvotes: 1

Views: 215

Answers (1)

javidcf
javidcf

Reputation: 59731

The .shape attribute gives you the shape known at graph construction time, which is a tf.TensorShape structure. If the shape of x were fully known, you could get your code to work as follows:

y = tf.broadcast_to(z, (x.shape[0].value, x.shape[1].value, x.shape[2].value, 1))

However, in your case x has an unknown first dimension. In order to use the actual tensor shape as a regular tf.Tensor (with value only known at runtime), you can use tf.shape:

x_shape = tf.shape(x)
y = tf.broadcast_to(z, (x_shape[0], x_shape[1], x_shape[2], 1))

Upvotes: 2

Related Questions