3
$\begingroup$

I want to train a function that given metadata about an image produces hyper-parameters for an algorithm which operates on the image.

My understanding is (please forgive me I'm a novice here) a neural network would suit this purpose.

I want to train a function:

def myHyperParameterFunction(a,b,c,...):
  return (one,two,three,...)

(This being a neural network starting with keras.layers.InputLayer(input_shape=(n,)) and ending with keras.layers.Dense(m))

Which produces hyper-parameters for another algorithm:

def myAlgorithm(image, (one,two,three,...)):
  return newImage

By using myAlgorithm a cost function can be formed:

def lossFunction(true_image, image, (one,two,three,...)):
  return true_image-myAlgorithm(image, (one,two,three,...)) 

Looking at the tensorflow documentation it seems I can only defined a loss function in terms of 2 variables y_true and y_pred, this seems to make this impossible. Possibly I could get around this by y_true being an index to arrays which contain images and true_images, but this feels a rather awkward solution (notably the object type of y_true cannot be numpy.ndarray so I cannot package both images in).

In summary, it seems the problem is that to compute the loss requires an additional external value (that being image, where y_pred is (one,two,three,...) and y_true is true_image). I am not bound to tensorflow, any tool or framework which helps with this I would be interested in.

How could I solve this?

$\endgroup$
3
  • $\begingroup$ I won't vote to close, but this seems to be the kind of question for which the Data Science Stack was created to address. $\endgroup$
    – Dave
    Commented Jul 20, 2021 at 21:49
  • $\begingroup$ @Dave It's always tricky with these, both data science and cross validated mention Machine Learning and it is still programming so overflow still in mind. But I'll trust you know this best. $\endgroup$ Commented Jul 20, 2021 at 21:52
  • $\begingroup$ I didn't fully understand from where your external variables come. However you can use a wrapper for your loss function to pass external variable. Something like the code here which passes the weights to a loss function. $\endgroup$
    – Kaveh
    Commented Jul 21, 2021 at 20:56

0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.