Closed rockywind closed 3 years ago
It's possible that there are small floating point differences due to different environment versions/hardware. I've experienced different results when running the exact same code with different environments/hardware, and have achieved slightly different results. This difference is quite negligible, I wouldn't worry about it.
The result is that I tested the pre-train model downloaded from GitHub. The setting is: per_GPU_size=12 GPU_num=3
Okay that looks good.
My Environment is: ubuntu 16.04 cuda11.1 pytorch1.7.1 Per_GPU_batch_size=4 GPU_num=4