Spark in me - Internet, data science, math, deep learning, philo

snakers4 @ telegram, 1356 members, 1614 posts since 2016

All this - lost like tears in rain.

Data science, deep learning, sometimes a bit of philosophy and math. No bs.

Our website
Our chat
DS courses review

August 13, 05:24

Float16 / half training in PyTorch

Tried to do it in the most obvious way + some hacks from here

Did anybody do it successfully on real models?


Resnet18 throws exception on conversion to half floats

Hey, I have tried to launch the following code: from torchvision import models resnet = models.resnet18(pretrained=True).cpu() resnet.half() and have got an exception: libc++abi.dylib: terminating with uncaught exception of type std::invalid_argument: Unsupported tensor type Sounds like the halftensor type is not registered properly. But not sure why it’s the case. Using pytorch 0.2.0 py36_1cu75 soumith Any advice how to fix it?