-
-
Thanks for your reply about the dataset in the former issue!
After I fine-tune the SIIM-ACR Pneumothorax segmentation task with pre-trained model weights and run ``ft.sh`` with mmsegmentation, the f…
-
Hi, thank you for your excellent work!
In Part 5 in README, how is the SIIM-ACR Pneumothorax data from Kaggle mapped to the code you used? The name (ID) of the downloaded data from Kaggle link are l…
-
👋 Hi! Thank you for your contribution, it is really a great job. And I have two questions regarding data processing:
1. **RSNA Pneumonia:** In the paper, it is mentioned, "The official data split i…
-
i get the error below when i try to use my unet with se_resnext50 models trained weight file for ensembling :
RuntimeError: Error(s) in loading state_dict for Unet:
Missing key(s) in state_dict:…
-
## Description
Default loss 인 CrossEntropyLoss외 Dice Loss, Focal Loss 등 과 2개 이상의 Loss 조합 실험
## Details
- CrossEntropyLoss를 최적화하는 것이 iou를 maximize하는 것과 방향이 다르다고 생각.
- Semantic Segmentation Task 에…
-
https://www.kaggle.com/competitions/siim-acr-pneumothorax-segmentation/data?select=download_images.py
-
When I was working on the segmentation task, I ran into a problem:
`Traceback (most recent call last):
File "run.py", line 167, in
main(cfg, args)
File "run.py", line 106, in main
tr…
-
Greetings,
I am trying to run your baseline on a custom dataset. However, there is no train.py in your directory. Is there any way you can share it? Thank you.
-
I'm sorry to bother you again
I want to know how do I load those saved models
`./gloria/data/ckpt/pneumothorax_segmentation_0.01/2022_08_03_12_23_46/epoch=35-step=143.ckpt`
What is the differen…