MultiObjectiveOptimization

MultiObjectiveOptimization copied to clipboard

Depth loss

6

There is a bug in the depth loss. All entries smaller than zero are masked. This causes most of the entries to be excluded in the loss, as the depth...

SimonVandenhende

two times if 'D' in params['tasks'], first one always ignored

1

https://github.com/intel-isl/MultiObjectiveOptimization/blob/1c6d0d503ccf33cc83d5b6c356ca2fc2bf255606/multi_task/losses.py#L79

msseibel

If I want to train the 3D image data using MTL by MGDA do I have to change the code min_norm_solver.py?

1

QianMuXiao

Algorithm 2 line 10

1

https://github.com/isl-org/MultiObjectiveOptimization/blob/d45eb262ec61c0dafecebfb69027ff6de280dbb3/multi_task/min_norm_solvers.py#L121-L122 Are these lines corresponding to algorithm 2 line 10? For e_{\hat_{t}} ?

854768750

local variable 'sol' referenced before assignment

1

I encounter an error UnboundLocalError: local variable 'sol' referenced before assignment In min_norm_solvers.py, def _min_norm_2d(vecs, dps): """ Find the minimum norm solution as combination of two points This is correct...

lskdream

Hi First of all, thanks for the great work. Recently I've been dive into this research, notice that we need multi backward among shared model. This is not allowed in...

ytwanghaoyu