diff --git a/README.md b/README.md index d57095a6c263efdd78396cb5eeebdd67edcfb115..9b341d32ffd3244bf6e9d9a5b52457a2638d4c23 100644 --- a/README.md +++ b/README.md @@ -84,7 +84,7 @@ when batch_size is large (16, 32, 64, 128), throughput_amp > throughput_tf32. - Observation 2: The coefficient of variation of throughput for the 100 iterations is smallest when batch_size = 128. -Benchmarking with batch_size = 128 can be used for node health check. +Benchmarking with dim=2, nodes=1,2, gpus=8, batch_size = 128 can be used for node health check. For example, the expected throughput for dim = 2, nodes = 1, gpus = 4, batch_size = 128 would be 2500 ± 200 (TF32) and 4100 ± 400 (AMP). <img src="https://github.com/xuagu37/Benchmark_nnU-Net_for_PyTorch/blob/main/figures/benchmark_cv_example.png" width="400">