Does K-FAC support only float32 operations?

tensorflow / kfac

An implementation of KFAC for TensorFlow

Apache License 2.0

197 stars 40 forks source link

Does K-FAC support only float32 operations? #40

Open KapllaniLorenc opened 4 years ago

KapllaniLorenc commented 4 years ago

I was working with the RNN example, and tried to implement for some other problem using float64. I got an error for this, and it required float32 representation. Then it worked.

james-martens commented 4 years ago

Float64 should work. Although maybe a casting to float32 crept in somewhere. What was the error?