Open Haoyanlong opened 2 years ago
I have trained the tacotron2 in V100S(32GB)， batch_size=114 for filling memory, but can't achieve the 17604(https://lambdalabs.com/gpu-benchmarks);
I calculate the throughput roughly by: 114*159 / 3.08 = 5885.065, could you give me some advices? Thank you very much!
I have trained the tacotron2 in V100S(32GB)， batch_size=114 for filling memory, but can't achieve the 17604(https://lambdalabs.com/gpu-benchmarks);
I calculate the throughput roughly by: 114*159 / 3.08 = 5885.065, could you give me some advices? Thank you very much!