Multi-Task-Learning-PyTorch

Multi-Task-Learning-PyTorch copied to clipboard

hrnet18+padnet

1

Thank you very much for sharing the wonderful code! Your work is definitely very helpful for MTL community. I am contacting you because I try to reproduce the result of...

hanxuel

Hi! Thanks for sharing the code. I had one problem that when I trained the model 'PADNet', is that the 'seism' necessary？Can I not use the seism? Thank u for...

BanaBanaBanaa

About task balancing

2

Thank you for your excellent work and open-source code. Could you please provide some code about task balancing, such as uncertainty weight, GradNorm multi-object Optim? Your paper has some experimental...

lelan-li

Hello, thanks for your great work. Could you please tell me how do you get the label for edge prediction in datasets like NYUD?

kejie-cn

Thank you very much for sharing the wonderful code! I meet a question when running the code: while I can get a similar accuracy on Segmentation (43.5 on mIoU) using...

Simon4Yan

[Question] About dataset condition for MTL

3

Thank you for your awesome work. Your work might be greatly helpful to all people who interest in the MTL. I'm about to study MTL and have one question. I...

qjadud1994

Hey, you reported the best result of NYUD with MTI-Net(HRNet-48), and in your code, the backbone in configs is HRNet-w18. If I want to reproduce the best result, is just...

PaulTHong

the trained model

3

Hi, could you please release the trained model? Thank you!

Xuanmeng-Zhang

PADNet paper mentions that the intermediate loss functions L1 to L4 are done by re-scaling the ground truth map to 1/4 resolution in page 3. However, the implementation of the...

NareshGuru77

Cityscapes depth estimation

2

Could you please support with the following questions: 1. In the survey paper (Revisiting Multi-Task Learning in the Deep Learning Era), it is mentioned that depth maps of cityscapes were...

NareshGuru77