search

keroro824 / HashingDeepLearning

Codebase for "SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems"
MIT License
1.07k stars 169 forks source link

batch size for Amazon-670K dataset #3

Closed hyoo closed 4 years ago

hyoo commented 5 years ago

in paper, it says, "We chose a batch size of 128 for Delicious-200K dataset and 256 for Amazon-670K dataset".

but in the code, https://github.com/keroro824/HashingDeepLearning/blob/master/SLIDE/Config_amz.csv#L6

it is still 128. Which one is correct?

keroro824 commented 5 years ago

The paper is correct. But we did have experiments for different batch sizes.