Michael Farnsworth comments

Repositories
Issues
Comments

Results 4 comments of


                                            Michael Farnsworth

GPU Memory error when running DenseFlow

I've tried to set the batch size to 32, but unfortunately to no avail. This is a bit of a differant beast when it comes to setup, as it is...

Interpolate through a set of latent values?

Cheers!, I've implemented a hack using as you described using the two latents a and b. I just have one or two questions. The latent_n from my point of view...

why the result of my eval sample looks very bad with load the best_model.pth?

Same issue it seems as well, not sure why though?

RuntimeError: Attempted to set the storage of a tensor on device "cuda:0" to a storage on different device "cpu". This is no longer allowed; the devices must match.

See: https://github.com/dbolya/yolact/issues/755#issuecomment-1141917563 Solved same issue for me.