Closed shaform closed 6 years ago
In theory I agree with you; in practice I haven't found compelling evidence that it's a problem. If you find any I'd love to know :)
You might want to experiment with replacing the penalty of (norm(grad) - 1)^2 by (norm(grad) - k)^2 for a larger k > 1.
Let us know if you find anything interesting :)
Hi, Here the sum of squares is computed
slopes = tf.sqrt(tf.reduce_sum(tf.square(gradients), reduction_indices=[1]))
However, when the input image is extremely large, the dimension of gradients would be huge. It seems possible that the resulting slopes would be extremely large compared to 1. Is this the case?