Add lazy-resampling benchmark tutorial

[KumoLiu]

part of Project-MONAI/MONAI#6156

Description

Show lazy-resampling benchmark results on 3d spleen segmentation. The results include the following two main parts.

• Time spent on each transform and the total amount of data preparation in the lazy and non-lazy mode.
• End-to-end time comparison

Checks

• Avoid including large-size files in the PR.
• Clean up long text outputs from code cells in the notebook.
• For security purposes, please check the contents and remove any sensitive info such as user names and private key.
• Ensure (1) hyperlinks and markdown anchors are working (2) use relative paths for tutorial repo files (3) put figure and graphs in the ./figure folder
• Notebook runs automatically ./runner.sh -t <path to .ipynb file>

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[KumoLiu]

Hi @wyli, @Nic-Ma, since I was using latest MONAI version to do the benchmark, can I just use MONAI 1.2.0 in the tutorial or should I use 1.2.0rc5 and updated it once 1.2.0 release?

[wyli]

Hi @wyli, @Nic-Ma, since I was using latest MONAI version to do the benchmark, can I just use MONAI 1.2.0 in the tutorial or should I use 1.2.0rc5 and updated it once 1.2.0 release?

The main goal is to make the numbers reported reproducible as much as possible, so I think we just report what has been used in the experiments. 1.2.0rc5. (and pytorch 1.14.0? I couldn't find it)

[KumoLiu]

Hi @wyli, @Nic-Ma, since I was using latest MONAI version to do the benchmark, can I just use MONAI 1.2.0 in the tutorial or should I use 1.2.0rc5 and updated it once 1.2.0 release?

The main goal is to make the numbers reported reproducible as much as possible, so I think we just report what has been used in the experiments. 1.2.0rc5. (and pytorch 1.14.0? I couldn't find it)

Hi @wyli, but I'm not test on 1.2.0rc5 because we have some new changes such as Project-MONAI/MONAI#6412, and the pytorch version is "1.14.0a0+410ce96". Maybe I should change both version to the stable one and retrain it?

[wyli]

Hi @wyli, @Nic-Ma, since I was using latest MONAI version to do the benchmark, can I just use MONAI 1.2.0 in the tutorial or should I use 1.2.0rc5 and updated it once 1.2.0 release?

The main goal is to make the numbers reported reproducible as much as possible, so I think we just report what has been used in the experiments. 1.2.0rc5. (and pytorch 1.14.0? I couldn't find it)

Hi @wyli, but I'm not test on 1.2.0rc5 because we have some new changes such as Project-MONAI/MONAI#6412, and the pytorch version is "1.14.0a0+410ce96". Maybe I should change both version to the stable one and retrain it?

sure, you can also just report the monai version from python -c "import monai; monai.config.print_config()" I see in the notebook there is 1.2.0rc4+9.ge18097d0 and 1.13.0a0+d0d6b1f these are good enough for reproducing the results.