research-contributions

research-contributions copied to clipboard

Why use torch.multiprocessing.spawn for distributed training

9

Hi there, In the Swin UNETR scripts, e.g., https://github.com/Project-MONAI/research-contributions/blob/main/SwinUNETR/BRATS21/main.py, `torch.multiprocessing.spawn` is used for launching distributed training. Any reason why you didn't use `torch.distributed.launch`? Did `torch.multiprocessing.spawn` give better performance than `torch.distributed.launch`...

hw-ju

  Dice score is 0.918 in the paper and 0.8225/0.8186 in the repository. Why there is a huge gap in between? Are they evaluated on validation set or test...

steve-seagal

Effect of flattening and reshaping

2

My question is regarding the following code snippet: https://github.com/Project-MONAI/research-contributions/blob/1b93b892f31390e98c4faa68e5660c7fcfb22083/SwinUNETR/Pretrain/models/ssl_head.py#L96-L97 What is the use of this? When running the code, the following shapes are present: ``` x_out: torch.Size([1, 768, 3, 3,...

lweitkamp

DATASET Problem

4

Hello! Each CT in the btcv data set used in the code contains all 14 organs. I want to apply unetr to the ribtrac data set. Each CT contains at...

BelieferQAQ

Ask for the code for running Swin UNETR on MSD dataset

5

Hi thank you for your great work. Could you release code for running Swin UNETR on MSD dataset?

jiaomei222

Hello, how can I calculate the classification index of the segmented multiple organs, such as F1 score, after I have segmented multiple organs in the btcv dataset. For example, set...

BelieferQAQ

Add steps for integrating SwinUNETR with the huggingface api.

darraghdog

Hello, The number of FLOPs for input size of 96x96x96 is written in Table. 5. in UNETR paper as **_41.19 GFLOPS_**. However, I measured it using [ptflops ](https://github.com/sovrasov/flops-counter.pytorch) and it...

Amshaker

Pretrained model on BTCV doesn't reproduce the mean dice score

3

Hi there, The provided model weights for BTCV (swinunetr-base) can't reproduce the same mean dice score on validation set. I only get a mean dice score around 0.16~0.2 which is...

zackchen-lb

Evaluation of trained UNETR models with test.py

1

Hi, I am facing an issue in evaluating the UNETR models trained with the repository. I saw there was a previous issue that raised the same problem: https://github.com/Project-MONAI/research-contributions/issues/46. The models...

hanoonaR