diff --git a/README.md b/README.md index 60b1986c60eb8d3d2bca02708019500dec763cdf..c57ace21b49cf25e5a044122e26dbfe42ebe95c6 100644 --- a/README.md +++ b/README.md @@ -83,7 +83,7 @@ We run 100 iterations for each set of parameters. Please see the results in benc **Observation 1**: Ideally, the improvement of throughput would be linear when the number of GPUs increases. In practice, throughtput stays below the ideal curve when the number of gpus increases. -<img src="https://gitlab.liu.se/xuagu37/Benchmark_nnU-Net_for_PyTorch/-/raw/edb1b56ff5a9bb74bbd220c4fb717b6af6119232/figures/benchmark_throughput_gpus_ideal.png" width="1200"> +<img src="https://gitlab.liu.se/xuagu37/Benchmark_nnU-Net_for_PyTorch/-/blob/main/figures/benchmark_throughput_gpus_ideal.png" width="1200"> **Observation 2**: when batch_size is small (1, 2, 4, 8), throughput_amp ≈ throughput_tf32; when batch_size is large (16, 32, 64, 128), throughput_amp > throughput_tf32.