instance-segmentation-with-discriminative-loss-tensorflow icon indicating copy to clipboard operation
instance-segmentation-with-discriminative-loss-tensorflow copied to clipboard

Published 20 hours ago • verified publisher icon hq-jiang

tf.unsorted_segment_sum too slow?

Open tejaskhot opened this issue 6 years ago • 1 comments

In my experiments (a different setup but using discriminative loss), I am finding the loss computation to be very time-consuming. I suspect the lag is coming from the tf.unsorted_segment_sum. Have you noticed such latency issues in your experiments? Is there perhaps a way to speed up/optimize the loss computation?

tejaskhot avatar Oct 21 '18 18:10 tejaskhot

Hi, This is Parth Dave. I am trying to run this repository on my machine. Can you please give me the requirements in order to run this repo successfully?

parthdave1210 avatar May 19 '21 04:05 parthdave1210