search

kjunelee / MetaOptNet

Meta-Learning with Differentiable Convex Optimization (CVPR 2019 Oral)
Apache License 2.0
529 stars 97 forks source link

RuntimeError with qpth #35

Closed lhfowl closed 4 years ago

lhfowl commented 4 years ago

Hello,

I've been trying to run some MetaOptNet experiments. I've created a conda environment with the packages you list as required. However, when I try to train MetaOptNet with SVM head, I'm getting the error:

"RuntimeError: Incompatible matrix sizes for lu_solve: each A matrix is 25 by 25 but each b matrix is 8 by 25"

I've tried using environments with different versions of python, but can't seem to get around this issue. I'm at a loss. Have you run into this issue before? Any advice would be greatly appreciated.

kjunelee commented 4 years ago

I guess the issue has to do with package versions. I am able to run under the following configuration:

Python 3.6.8 qpth 0.0.13 PyTorch 1.1.0a0+b75a525

Hope this helps.

lhfowl commented 4 years ago

Okay, thanks!