Sunand Raghupathi
Sunand Raghupathi
Yeah, I'll check it out
@CW-Huang I'm getting NaN losses trying to run an experiment with lbidd: `2020-08-30 23:56:24.873470 / Iteration 200: nan nan 2020-08-30 23:56:25.062086 / Iteration 200 valid loss nan` Here is the...
Good call, that was it. I'm able to run an exp in ~8 min on CPU with this script: `python train_generator.py --dataroot=/Users/Sunsmeister/Desktop/Research/Causal/causal-benchmark/datasets --data=lbidd_quadratic_50k --dist='FactorialGaussian' --dim_h=256 --n_hidden_layers=2 --batch_size=128 --lr=0.0005`
Is the code currently set up to train on GPU? If not, I can work on that
Alright it's finally ready to review. Try running it before approving, just to make sure nothing is broken...
Temporary solution is modifying the architecture when changing the number of downsampling layers
I'm still investigating, but I believe it's an issue on the dataloading side. Interestingly, I noticed this in my latest MaskGenerator experiments. Would it make sense that resizing/transforming a very...
Currently I'm experimenting with different discriminators (such as PatchGAN) to try to improve the water quality
Haha yes, I see your point. I actually have this implemented locally and it runs, but haven't put too much effort into producing good results
Actually I haven't tried the patch idea yet. What did produce interesting results was using perceptual loss on the reconstructed region, but I haven't yet found a counterpart for the...