Skip to content
This repository has been archived by the owner on Mar 22, 2021. It is now read-only.

Problem with submission.csv #31

Closed
ymittal23 opened this issue Aug 24, 2018 · 5 comments
Closed

Problem with submission.csv #31

ymittal23 opened this issue Aug 24, 2018 · 5 comments

Comments

@ymittal23
Copy link

There is problem with submission.csv file as kaggle is not accepting the file and showing error

Evaluation Exception: Index was outside the bounds of the array.

There might be some problem with rle encoding
@jakubczakon
Copy link
Contributor

@ymittal23 hmm that is interesting.

I haven't had any problems so far. Did you manage to solve it yet?

@ymittal23
Copy link
Author

No I tried multiple times but got same error.
Evaluation Exception: Index was outside the bounds of the array.
I checked csv it looks fine to me. There are 18000 id for which prediction is done but when i am submitting result on kaggle it gives error

@jakubczakon
Copy link
Contributor

I've just got that error (lucky me).

Working on a fix but my guess is that it predicts the very last bottom right pixel and there is some evaluation bugs (as pointed out by Heng CherKeng).

@jakubczakon
Copy link
Contributor

Ok, it seems that the problem was with the run_lenght_encoding function in the utils.py.
I dropped something that was there because of the DSB-2018 challenge it worked for me.

It is already on the newest master

@ymittal23
Copy link
Author

Yeah I checked it now it is working fine. Thanks for the help.

jakubczakon added a commit that referenced this issue Oct 13, 2018
@jakubczakon
Dev (#40)
0cbaa6a 
* added image channel and params to config (#29)

* exping

* added large kernel matters architecture, renamed stuff, generalized c… (#30)

* added large kernel matters architecture, renamed stuff, generalized conv2drelubn block

* exping

* exping

* copied the old ConvBnRelu block to make sure it is easy to finetune old models

* reverted main

* Depth (#31)

* exping

* exping

* added depth loaders, and depth_excitation layer, adjusted models and callbacks to deal with both

* fixed minor issues

* exping

* merged/refactored

* exping

* refactored architectures, moved use_depth param to main

* added dropout to lkm constructor, dropped my experiment dir definition

* Second level (#33)

* exping

* first stacked unet training

* fixed minor typo-bugs

* fixed unet naming bug

* added stacking preds exploration

* dropped redundant imports

* adjusted callbacks to work with stacking, added custom to_tensor_stacking

* Auxiliary data (#34)

* exping

* added option to use auxiliary masks

* Stacking (#35)

* exping

* exping

* fixed stacking postpro

* Stacking (#36)

* exping

* exping

* fixed stacking postpro

* exping

* added fully convo stacking, fixed minor issues with loader_mode: stacking

* Update architectures.py

import fix

* Update README.md

* Update models.py

reverted to default (current best) large kernel matters internal_channel_nr

* Stacking (#37)

Stacking

* Stacking depth (#38)

* exping

* added depth option to stacking model, dropped stacking unet from models

* Empty non empty (#39)

* exping

* added empty vs non empty loaders/models and execution

* changed to lovasz loss as default from bce

* reverted default callbacks target name
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@jakubczakon @ymittal23