hq-jiang / instance-segmentation-with-discriminative-loss-tensorflow

Tensorflow implementation of "Semantic Instance Segmentation with a Discriminative Loss Function"
MIT License
170 stars 47 forks source link

tf.unsorted_segment_sum too slow? #7

Open tejaskhot opened 5 years ago

tejaskhot commented 5 years ago

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?

parthdave1210 commented 3 years ago

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?