Multi-Task-Learning-PyTorch

Multi-Task-Learning-PyTorch copied to clipboard

Hi, It's a great piece of work and thanks for making the code puclic! Do you have any plan to release the implementaion, hyper-parameters, and pretrained weights for the decoder...

backseason

[question] where is hrnet_w18_small_model_v2.pth?

2

sorry for my disturbance. in , hrnet_w18_small_model_v2.pth doesn't exist. There only exist - HRNet_W18_C_cosinelr_cutmix_300epoch.pth.tar - HRNet_W18_C_pretrained.pth - HRNet_W18_C_ssld_pretrained.pth so which pth is right?

Freed-Wu

Hi, Thanks for your code! Could you provide your code of MTI-Net with Resnet FPN backbone in you paper? BTW, did you use pretrained weight in your of resnet18-fpn? If...

vincentt1999

Thank you for sharing the code. During multi-task learning, I encountered the following error while training ResNet50 on NYUD dataset. _RuntimeError:_ Given groups=1, weight of size 64 3 7 7,...

yyyaaaaaaa

Hello, thanks for sharing your work. In your paper _Multi-Task Learning for Dense Prediction Tasks: A Survey_, I found that you've tried PAP-Net, but I can't find the code in...

Asagami-Fujino

Dataset URL

2

It looks like the URL specified in `data/google_drive.py` is not accessible anymore. download_file_from_google_drive fails with `UnboundLocalError: local variable 'token' referenced before assignment` since `response.cookies` is empty for the NYU dataset.

mike-shvets

Is mtl training done sequentially on multiple datasets? Won't this lead to sub-optimization of some tasks?

yuan243212790

Hello SimonVandenhende, Kudos to the great work. I just want to know if we can use this repo to train multiple classification tasks. For example Vehicle Make ,Color,Orientation,Model - each...

akirs82

Using dataloader by dataloader, sometimes memory is limited, so only little batch for each dataloader. It will disadvantage the performance of batch normalization? how to fix this problem?

kellenf

Hello, thank you very much for your outstanding contribution. I easily found the method of coloring the semantic segmentation prediction map on the Internet, but there are few methods for...

187185537