Wenqi Li

warning msgs `auto3dseg/notebooks/hpo_optuna.ipynb`

3

``` [2022-12-19T17:36:30.048Z] Running ./auto3dseg/notebooks/hpo_optuna.ipynb [2022-12-19T17:36:30.048Z] Checking PEP8 compliance... [2022-12-19T17:36:30.609Z] Running notebook... [2022-12-19T17:36:30.609Z] Before: [2022-12-19T17:36:30.609Z] "max_epochs = 2\n", [2022-12-19T17:36:30.609Z] After: [2022-12-19T17:36:30.609Z] "max_epochs = 1\n", [2022-12-19T17:36:34.777Z] MONAI version: 1.1.0rc1+49.gb159ce78 [2022-12-19T17:36:34.777Z] Numpy version:...

**Is your feature request related to a problem? Please describe.** according to this list: https://github.com/Project-MONAI/tutorials/tree/main/auto3dseg#demystifying-auto3dseg-components would be great to rename the notebooks, for example: `data_analyzer.ipynb` -> `step_1_data_analyzer.ipynb` cc @mingxin-zheng @Nic-Ma...

host/load pretrained weights for 3D resnet

11

**Is your feature request related to a problem? Please describe.** PR https://github.com/Project-MONAI/MONAI/pull/2253 implements a generic version of resnet for spatial 1/2/3D inputs. It'd be very useful for MONAI to provide...

multi-gpu tensorboard handlers initialization

2

https://github.com/Project-MONAI/model-zoo/blob/cf5e0322ee25b178b6cf841f3bd81e0a8adf2b16/models/spleen_ct_segmentation/configs/multi_gpu_train.json#L18 the multi-gpu override essentially set the trainer handlers to `$@train#handlers[:-2]` for the worker nodes. but because of the `@train#handlers` reference, the config parser will still trigger handler constructor calls...

**Is your feature request related to a problem? Please describe.** The current metadata format supports specific versions of dependencies: https://github.com/Project-MONAI/model-zoo/blob/ff6175a18bda80c2093cd6fb2a493055cccacf70/models/brats_mri_segmentation/configs/metadata.json#L28-L30 would be great to extend the syntax to have more...

logging configuration

3

> Currently, bundles usually leverage this line config to run with correct logging: > https://github.com/Project-MONAI/model-zoo/blob/dev/models/spleen_ct_segmentation/configs/logging.conf#L11 > Please show the recommendation change or how to update the existing bundles? > CC...

using the original labels, instead of inverted transformed labels for evaluation

11

Currently quite a few bundles use the inverted version of preprocessed original labels as the reference during evaluation: https://github.com/Project-MONAI/model-zoo/blob/987f49fe9e0f20f047a2252c1ace38bd760cfb33/models/spleen_ct_segmentation/configs/evaluate.json#L12-L21 which is different from the approach taken in the tutorial using...

**Is your feature request related to a problem? Please describe.** currently we don't have enough quota for LFS data: 

Create a pypi release of this project

4

would be great if we can create an initial pypi release of this repository, so that `pip install MetricsReloaded` and the downstream applications can rely on it. please see also...