W.P. McNeill - 1 year ago 678

Python Question

My TensorFlow model uses

`tf.random_uniform`

`init = tf.placeholder(tf.float32, name="init")`

v = tf.Variable(tf.random_uniform((100, 300), -init, init), dtype=tf.float32)

initialize = tf.initialize_all_variables()

I initialize variables at the start of training like so.

`session.run(initialize, feed_dict={init: 0.5})`

This gives me the following error:

`ValueError: initial_value must have a shape specified: Tensor("Embedding/random_uniform:0", dtype=float32)`

I cannot figure out the correct

`shape`

`tf.placeholder`

`init = tf.placeholder(tf.float32, shape=0, name="init")`

`ValueError: Incompatible shapes for broadcasting: (100, 300) and (0,)`

If I replace

`init`

`0.5`

`tf.random_uniform`

How do I pass this scalar initial value via the feed dictionary?

Answer Source

**TL;DR:** Define `init`

with a scalar shape as follows:

```
init = tf.placeholder(tf.float32, shape=(), name="init")
```

This looks like an unfortunate implementation detail of `tf.random_uniform()`

: it currently uses `tf.add()`

and `tf.mul()`

to rescale the random value from [-1, +1] to [`minval`

, `maxval`

], but if the shape of `minval`

or `maxval`

is unknown, `tf.add()`

and `tf.mul()`

can't infer the proper shapes, because there might be broadcasting involved.

By defining `init`

with a known shape (where a scalar is `()`

or `[]`

, not `0`

), TensorFlow can draw the proper inferences about the shape of the result of `tf.random_uniform()`

, and your program should work as intended.