Flat outputs result for demo 2D representation about acorn HOT 3 CLOSED

Thanks for pointing this out-- I found a problem with one of the default config settings which was creating a network with far too many hidden layers. This was creating the flat output. I pushed a fix, so try pulling from the repo and running python train_img.py --config config_img/config_pluto_acorn_1k.ini from the experiment_scripts folder. Let me know if this works.

As far as the grid_sample gradient, this is doing bilinear interpolation so it is differentiable. The output is expressed as a weighted combination of features from the input feature grid, and then you can derive the gradient with respect to the input feature grid.

from acorn.

Now, it is working, very efficient, 200it/s in my machine, RTX2080ti

from acorn.

Great! I'll go ahead and close the issue then. Let us know if you see any other problems.

from acorn.