yaringal multi-task-learning-example issues

yaringal / multi-task-learning-example

A multi-task learning example for the paper https://arxiv.org/abs/1705.07115

MIT License

835 stars 204 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

log_var_a and log_var_b

#18 Yybuser closed 1 year ago
0
How can I use the trained model for prediction? is it right to use prediction_model.predict(new_x) ?

#17 Qianqian-Yang opened 2 years ago
2
Why return torch.mean(loss)?

#16 edshkim98 opened 3 years ago
1
Calculating back to actual weights of loss functions

#15 edshkim98 closed 3 years ago
0
Log var can become negative and explode

#14 snie2012 opened 3 years ago
1
Question about the loss

#13 caishiqing opened 3 years ago
0
This is a lucky demo When I change the data generation process, the prediction of the variance is wrong

#12 conan-ux opened 3 years ago
2
uncertainty for self-supervised learning

#11 griffintin opened 4 years ago
1
some questions about formulation 10 in paper

#10 neil-yc opened 4 years ago
0
Sounds like a lucky result comes from a wrong formula deduction

#9 edfall opened 4 years ago
2
Question on relative weights

#8 kmbmjn opened 4 years ago
0
Any way to incorporate these methods in other tasks easily?

#7 Jacobew opened 4 years ago
7
The loss might be nagative value

#6 begeekmyfriend opened 5 years ago
11
multi-task-learning-example pytorch notebook

#5 RagMeh11 closed 4 years ago
1
MergeLoss with regular item is \log_{sigma} in paper but \log_{sigma}^2 in code

#4 songzeballboy opened 5 years ago
3
about σ

#3 zhangxixi0904 opened 5 years ago
1
Code Doesn't Agree with Paper

#2 divyansha closed 5 years ago
1
Final Loss equation

#1 hardianlawi closed 6 years ago
12