You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am using FP16 to infer with libspconv.so and noticed some precision drop.
Is there any chances of making libspconv.so support FP32 inference? With that I can deploy my model with FP32 inference, and treat that as a benchmark.
The text was updated successfully, but these errors were encountered:
I am using FP16 to infer with libspconv.so and noticed some precision drop.
Is there any chances of making libspconv.so support FP32 inference? With that I can deploy my model with FP32 inference, and treat that as a benchmark.
The text was updated successfully, but these errors were encountered: