tangy5

Hi @davidkvcs , thanks for the question and interest of the work. The problem should be related to the patch size. The original configuration used 96x96x96 as the sub-volume for...

Hi @hw-ju , the SwinUNETR is tested of multi-GPU training with both DDP and MP Spawn. Both works well, no performance preference regarding different multi-GPU frameworks. You can safely use...

Hi @lweitkamp thanks for reporting this issue, let me confirm the original implementation. For the contrastive and rotation head, yes. Use one of the channels is the a simple choice...

Hi @davidkvcs , Thanks for reporting this issue. The pre-trained model checkpoints should contain three keys {'epochs': , 'best_acc', 'state_dict': } Key "state_dict" should be the model weights, could you...

HI @ZEKAICHEN , thanks for raising the issue. We've double checked and re-run the test.py using the code. If the used code is from https://github.com/Project-MONAI/research-contributions/tree/main/SwinUNETR/BTCV and use the Swin UNETR/Base...

hi @hanoonaR , thanks for the comment. In the save_checkpoint function, the models are saved as a dictionary. ` save_dict = {"epoch": epoch, "best_acc": best_acc, "state_dict": state_dict}` The "state_dict" should...

Hi @dschoerk , thank for this really cool integration. This is very inspiring! Can I ask how you write the code for annotating video (MP4) in CVAT? I'm trying to...

> > Hi @dschoerk , thank for this really cool integration. This is very inspiring! Can I ask how you write the code for annotating video (MP4) in CVAT? I'm...

> > > Hi @dschoerk , thank for this really cool integration. This is very inspiring! Can I ask how you write the code for annotating video (MP4) in CVAT?...

> > > > Hi @dschoerk , thank for this really cool integration. This is very inspiring! Can I ask how you write the code for annotating video (MP4) in...