search

SimonVandenhende / Multi-Task-Learning-PyTorch

PyTorch implementation of multi-task learning architectures, incl. MTI-Net (ECCV2020).
Other
752 stars 114 forks source link

MTI-NET NYUD task，some files lost #7

Closed TianhaoFu closed 3 years ago

TianhaoFu commented 3 years ago

Hi，I'm running your code,but i find some files is not included in your respository:

_FileNotFoundError: [Errno 2] No such file or directory: './results/NYUD/hrnet_w18/single_task/semseg/re sults/NYUD_testsemseg.json'

could you please provide these files? thanks a lot!

SimonVandenhende commented 3 years ago

Could you specify what script you are trying to run exactly?

TianhaoFu commented 3 years ago

thanks for your reply. I'm using _python main.py --config_env configs/env.yml --config_exp configs/nyud/hrnet18/mtinet.yml, and i came across that problem.

SimonVandenhende commented 3 years ago

The multi-task learning performance is calculated using Equation 10 from https://arxiv.org/pdf/2004.13379.pdf Note that this requires the performance of a set of single-tasking baselines, therefore in order to determine the multi-task learning performance for MTI-Net, it requires to train the single-tasking models first. You could still run the code, if you decide to only report segmentation and depth, and ignore the multi-tasking performance for MTI-Net.