Yes - here's a doc about doing quantized inference in TensorFlow, for example: h... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

dgacmu on June 8, 2017 | parent | context | favorite | on: DeepLearning10: The 8x Nvidia GTX 1080 Ti GPU Mon...

Yes - here's a doc about doing quantized inference in TensorFlow, for example: https://www.tensorflow.org/performance/quantization

AFAIK, there's still a bit of a performance gap between just using TF and using the specialized gemmlowp library on Android, but that part's getting cleaned up.

Haven't seen much in generalized results on training using lower precision.

dharma1 on June 8, 2017 [–]

Does that work with Pascal CUDA8 INT8 out of the box?

dgacmu on June 8, 2017 | [–]

I'm not sure - I believe it depends on getting cuDNN6 working, and from this bug, I can't quite tell if it works or not (but it's probably not officially supported yet): https://github.com/tensorflow/tensorflow/issues/8828

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact