diff --git a/README.md b/README.md index 83bd867e5ea832c800ca59ce0a00bba98ae65d70..c5d4bb1dd5432845657c528bc9005ceb2e0b9612 100644 --- a/README.md +++ b/README.md @@ -80,17 +80,17 @@ In practice, throughtput stays below the ideal curve when the number of gpus inc **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. -<img src="https://gitlab.liu.se/xuagu37/Benchmark_nnU-Net_for_PyTorch/-/blob/main/figures/benchmark_throughput_batch_size.png" width="400"> +<img src="https://gitlab.liu.se/xuagu37/Benchmark_nnU-Net_for_PyTorch/-/raw/edb1b56ff5a9bb74bbd220c4fb717b6af6119232/figures/benchmark_throughput_batch_size.png" width="400"> **Observation 3**: Benchmark results are more stable when larger batch_size. -<img src="https://gitlab.liu.se/xuagu37/Benchmark_nnU-Net_for_PyTorch/-/blob/main/figures/benchmark_throughput_cv.png" width="400"> +<img src="https://gitlab.liu.se/xuagu37/Benchmark_nnU-Net_for_PyTorch/-/raw/edb1b56ff5a9bb74bbd220c4fb717b6af6119232/figures/benchmark_throughput_cv.png" width="400"> Coefficient of variation is calculated as the ratio of the standard deviation to the mean. It shows the extent of variability in relation to the mean of the population. **Observation 4**: Ideally, the improvement of throughput would be linear when batch_size increases. In practice, throughtput stays below the ideal curve when batch_size > 16. -<img src="https://gitlab.liu.se/xuagu37/Benchmark_nnU-Net_for_PyTorch/-/blob/main/figures/benchmark_throughput_batch_size_ideal.png" width="400"> +<img src="https://gitlab.liu.se/xuagu37/Benchmark_nnU-Net_for_PyTorch/-/raw/edb1b56ff5a9bb74bbd220c4fb717b6af6119232/figures/benchmark_throughput_batch_size_ideal.png" width="400">