How can I change the values of a numpy array stored in a TensorFlow Variable Without Changing ANY other properties of the Tensor?

Question

I want to change the weights of one layer of a neural net to a new set of known values. The current set of values is:

>>> import tensorflow as tf
...
>>> curr_layer.weights
<tf.Variable 'conv2d/kernel:0' shape=(4, 4, 1, 64) dtype=float32, numpy=
array([[[[ 0.02059445, -0.01320859, -0.00185177, ...,  0.02550568,
          -0.02180868,  0.00089696]], 
         ...

        [[-0.03411875, -0.00027762, -0.00894349, ...,  0.04085622,
           0.02792494, -0.02052956]]]], dtype=float32)>

For the sake of this example, I created a zero array with the same shape:

>>> silly = np.zeros([4,4,1,64])

However, when I use assign to transfer the values, the name of the graph node associated with the Tensor also changes:

>>> curr_layer.weights[0].assign(silly)
curr_layer.weights[0].assign(silly)
<tf.Variable 'UnreadVariable' shape=(4, 4, 1, 64) dtype=float32, numpy=
array([[[[0., 0., 0., ..., 0., 0., 0.]],
       ....
       [[0., 0., 0., ..., 0., 0., 0.]]]], dtype=float32)>

Where now 'conv2d/kernel:0' has become'Unread Variable'. How do I prevent this from happening? How do I change only the values associated with the tensor?

Answer 1

The name doesn't actually change:

a = tf.Variable(np.zeros((3, 4)), name='test')
a.name

prints test:0. And then

a.assign(np.zeros((3, 4)))
a.name

still prints test:0.

Answer 2

For a tf.Variable instance, the .assign method has a read_value argument that's True by default. If x is an arbitrary tf.Variable, then for a numpy array silly (of the same dimensions as x), you can do:

x.assign(silly, read_value=False)

This won't return anything, but it will change the tf.Variable instance, x in place.

For a toy example I adapted from the original post, doing the following:

silly = np.zeros([2,2])

x = tf.Variable([[1,0],[0,1]], dtype=tf.float32, name='test')

x.assign(silly, read_value=False)

x

resulted in:

<tf.Variable 'test:0' shape=(2, 2) dtype=float32, numpy=
array([[0., 0.],
       [0., 0.]], dtype=float32)>

Obviously not the same exact tensors involved in the original post, but the expected behavior is as desired.