CODEWITHSUNDEEP
pythontensorflow
phoenixwing
phoenixwing

Reputation: 337

How to iterate over the elements of a tensor in TensorFlow?

I have coded a neural network that returns a list of 3 numbers for every input sample. These values are then subtracted from the actual values to get the difference.

For example, 

actual    = [1,2,3]  
predicted = [0,0,1]  
diff      = [1,2,2]

So my tensor now has the shape [batch_size, 3] What I want to do is to iterate over the tensor elements to construct my loss function.
For instance, if my batch_size is 2 and finally 

diff = [[a,b,c],[d,e,f]]

I want the loss to be 

Loss = mean(sqrt(a^2+b^2+c^2), sqrt(d^2+e^2+f^2))

I know that TensorFlow has a tf.nn.l2_loss() function that computes the L2 loss of the entire tensor. But what I want is the mean of l2 losses of elements of a tensor along some axis.
How do I go about doing this?

Upvotes: 3

Views: 4240

Answers (1)

Franck Dernoncourt
Franck Dernoncourt

Reputation: 83157

You can use tf.sqrt followed by tf.reduce_sum and tf.reduce_mean. Both tf.reduce_sum and tf.reduce_mean have an axis argument that indicates which dimensions to reduce.

For more reduction operations, see https://www.tensorflow.org/api_guides/python/math_ops#Reduction

Upvotes: 1

Related Questions