Skip to content

Feedback#1

Open
github-classroom[bot] wants to merge 49 commits intofeedbackfrom
main
Open

Feedback#1
github-classroom[bot] wants to merge 49 commits intofeedbackfrom
main

Conversation

@github-classroom
Copy link

@github-classroom github-classroom bot commented Feb 3, 2024

👋! GitHub Classroom created this pull request as a place for your teacher to leave feedback on your work. It will update automatically. Don’t close or merge this pull request, unless you’re instructed to do so by your teacher.
In this pull request, your teacher can leave comments and feedback on your code. Click the Subscribe button to be notified if that happens.
Click the Files changed or Commits tab to see all of the changes pushed to main since the assignment started. Your teacher can see this too.

Notes for teachers

Use this PR to leave feedback. Here are some tips:

  • Click the Files changed tab to see all of the changes pushed to main since the assignment started. To leave comments on specific lines of code, put your cursor over a line of code and click the blue + (plus sign). To learn more about comments, read “Commenting on a pull request”.
  • Click the Commits tab to see the commits pushed to main. Click a commit to see specific changes.
  • If you turned on autograding, then click the Checks tab to see the results.
  • This page is an overview. It shows commits, line comments, and general comments. You can leave a general comment below.
    For more information about this pull request, read “Leaving assignment feedback in GitHub”.

Subscribed: @jinjero @Jungtaxi @ChoeHyeonWoo @hyunseo-k @rudeuns @rsl82

Jungtaxi added a commit that referenced this pull request Feb 6, 2024
Jungtaxi and others added 27 commits February 7, 2024 00:57
feat: Customize training and validation logic
* feat: Add loss

- bce_with_logits_loss
- dice_bce_loss
- dice_loss
- iou_loss
- focal_loss
- tversky_loss
- focal_tversky_loss
- lovasz_hinge_loss
- combo_loss

#13

* docs: add bce with logits loss in config

#13

* fix: Use foward in class

#13

* refactor: Change var name

- inputs to outputs
- targets to masks

#13
* feat: Add dice metric

#18

* docs: Write dice_coef metric in config

#18

* remove: Remove acc metric

#18
* feat: Add fcn_resnet50 model

#20

* docs: Write model type in config

#20

* remove: Remove mnist model

#20

* fix: fix the layer

#20

* fix: add last layer

#20
* feat: Add wandb logger

#14

* chore: Add wandb to .gitignore

#14

* remove: Remove epoch log in wandb

#14

* feat: Split best checkpoint save

#14

* remove: Remove make_dir function

#14
* feat: Add classes list in utils

#22

* refactor: Refactor name loader to data_loader

#22

* fix: Fix code about metric

#22
* feat: Add dice_coef in MetricTracker

#24

* remove: Remove not used function

#24
* feat: Add FCN_ResNet101 model

#32

* refactor: Refactor the code

- fcn model results dict type and our needs is results.output
- change forward to return results.output

#32
* refactor: Refactor trainer config

#33

* refactor: Refactor trainer with config.init_obj

#33
* feat: Add smp models

- Unet, Linknet, FPN, PSPNet, PAN model

#35

* refactor: Move torchvision model to arch folder

- add init
- move torchvision model

#35

* feat: add config file for smp library

#35

* refactor: Move loss and metric to trainer

- move loss and metric to traniner folder
- remove arch folder and move models to model folder

#35
- used mmap_ninja library
- modifications on train.py, config.json
- created make_mmap.py, dataset.py

#11
* refactor: Refactor dataset code

#42

* refactor: Add base & renamed variables

#42

* fix: fix potential bugs

#42

* fix: fix potential bugs

#42
* feat: Add inference

- add inference
- modify config

#41

* remove: Remove MNIST data loader

#41

* refactor: Refactor transform code

- put transform in init

#41

* refactor: Import CLASS2IND from utils

- refactor code
- remove warnings which doesn't work

#41

* refactor: Remove SEED var and use default opt

#41
* feat: Add kfold config

#40

* fix: Fix dir name error

#40

* fix: Fix name error for kfold training

#40
* fix: Revert label structure

#48

* fix: rename variable

#48

* fix: fix config.json files

#48
* feat: Add transforms in config

#50

* refactor: Split dataset class

#50

* feat: Add transforms config parsing logic

#50

* remove: Remove not used files

#50

* fix: Fix for customizing transforms

#50

* fix: Fix for customizing transforms

#50
* refactor: Refactor inference

#51

* refactor: Refactor inference

#51

* feat: Add transfrom in config

#51

* remove: Remove unused file in init

#51

* fix: remove use transform opt

#51
jinjero and others added 16 commits February 15, 2024 14:48
* feat: Add gradcam with streamlit

#44

* refactor: Refactor code

#44

* refactor: Refactor model

#44

* fix: Fix model

#44

---------

Co-authored-by: jinjero <jinjero@gmail.com>
* feat: Add mixup trainer

#57

* refactor: Refactor mixup

#57
* feat: Add making bin files

#63

* feat: Add mask_load_dataset

#63

* feat: Add fast trainer

#63

* feat: Add fast train config

#63

* feat: Add dict type metric tracker

#63

* refactor: Refactor values

#63

* fix: Fix valid_dataset transforms

#63
* feat: Add fine-tuning mode

#65

* fix: Fix test_path name

#65
* feat: Add Unet++ model

#71

* feat: Add DeepLabV3 model

#71
* feat: Add PseudoTestDataset class

#72

* feat: Add train_pseudo with config_pseudo

#72
* feat: Add save logit file

#73

* feat: Add soft voting with config_ensemble

#73

* refactor: Rename files

#73
* feat: Add ensemble code

#69

* fix: Apply weights when combining masks

#69
* feat: Add Real-ESRGAN

#77

* feat: Add handbone super resolution code

#77

* docs: add readme

#77
* feat: Add csv visulize

* remove: remove validation ensemble
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants