Tensorflow gradients

Question

I am trying to adapt the tf DeepDream tutorial code to work with another model. Right now when I call tf.gradients():

t_grad = tf.gradients(t_score, t_input)[0]
g      = sess.run(t_grad, {t_input:img0})

I am getting a type error:

TypeError: Fetch argument None of None has invalid type <type 'NoneType'>,     
must be a string or Tensor. (Can not convert a NoneType into a Tensor or 
Operation.)

Where should I even start to look for fixing this error?

Is it possible to use tf.gradients() with a model that has an Optimizer in it?

Answer 1

I'm guessing your t_grad has some Nones. None is mathematically equivalent to 0 gradient, but is returned for the special case when the cost doesn't depend on the argument it is differentiated against. There are various reasons why we don't just return 0 instead of None which you can see in discussion here

Because None can be annoying in cases like above, or when computing second derivatives, I use helper function below

def replace_none_with_zero(l):
  return [0 if i==None else i for i in l] 

Answer 2

The following is a helpful tip for debugging tf.gradients()

for an invalid pair of tensors:

grads = tf.gradients(<a tensor>, <another tensor that doesn't depend on the first>)

even before you try to run tf.gradients in a session you can see it is invalid using print

print grads

It will return [None] a list with a single None in it.

If you try to run it in a session anyways:

results = sess.run(grads) 

You will not get None again, instead you get the error message described in the question.

For a valid pair of tensors:

grads = tf.gradients(<a tensor>, <a related tensor>)
print grads 

You will get something like:

Tensor("gradients_1/sub_grad/Reshape:0", dtype=float32)

In a valid situation:

results = sess.run(grads, {<appropriate feeds>})
print results

you get something like

[array([[ 4.97156498e-06, 7.87349381e-06, 9.25197037e-06, ..., 8.72526925e-06, 6.78442757e-06, 3.85240173e-06], [ 7.72772819e-06, 9.26370740e-06, 1.19129227e-05, ..., 1.27088233e-05, 8.76379818e-06, 6.00637532e-06], [ 9.46506498e-06, 1.10620931e-05, 1.43903117e-05, ..., 1.40718612e-05, 1.08670165e-05, 7.12365863e-06], ..., [ 1.03536004e-05, 1.03090524e-05, 1.32107480e-05, ..., 1.40605653e-05, 1.25974075e-05, 8.90011415e-06], [ 9.69486427e-06, 8.18045282e-06, 1.12702282e-05, ..., 1.32554378e-05, 1.13317501e-05, 7.74569162e-06], [ 5.61043908e-06, 4.93397192e-06, 6.33513537e-06, ..., 6.26539259e-06, 4.52598442e-06, 4.10689108e-06]], dtype=float32)]