benchmarks icon indicating copy to clipboard operation
benchmarks copied to clipboard

Different kinds of preprocessing

Open chrisrn opened this issue 7 years ago • 1 comments

Inside preprocessing.py you are using inception preprocessing to train images and vgg preprocessing for evaluation, according to slim. It's a little bit confusing. If you want to train a different network from inception, then this is not the optimized preprocessing in terms of accuracy. Are you planning to integrate different kinds of preprocessing?

chrisrn avatar Jan 11 '18 08:01 chrisrn

We do plan on looking into the preprocessing eventually, as part of an effort to converge to good accuracies. See #104 for more information.

Assigning to @bignamehyp for now.

reedwm avatar Jan 11 '18 18:01 reedwm