-
Hello @noveens,
Thank you for your excellent work and patience response before! I'm confused about the distilled dataset saved in './results/distilled_data' seems to contain continuous variables not …
-
The PixelDrawer currently has no support for limiting the colors - it only support full three channel RGB. It would be preferable to be able to limit the colorspace to either subsets of RGB or to a fi…
-
Hi,
I tried running the Gumbel-Softmax model with the following parameters:
GPU=0
DATASET=cifar10
MODEL=wresnet40_2
EPOCH=200
BATCH=128
LR=0.1
WD=0.0002
AWD=0.0
ALR=0.001
CUTOUT=16
SAV…
-
Are there plans to introduce differentiable samples?
Thanks!
-
Hi Eder,
Thanks for the Keras implementation! I'm excited about this idea as well. (Hopefully) quick question: I'm interested in learning an autoencoder for the output features of some other CNN …
-
-
https://github.com/facebookresearch/faiss/issues/2531#issuecomment-1280695975 some thoughts here
https://docs.google.com/document/d/1AryWpV0dD_r9x82I_quUzBuRyzDotL_HHnKuNB9H3Zc/edit?usp=drivesdk mo…
-
```
~/Documents/pro1/seg/utils/loss_gscnn.py in forward(self, inputs, targets)
344 losses['edge_loss'] = self.edge_weight * 20 * self.bce2d(edgein, edgemask)
345 losses['att…
-
Hi,
I was trying to understand your model better. In an experiment, I removed the traffic component. I used a dummy linear graph, i.e. nodes are 1,2,3,4...n+1 and a single edge between two consecu…
-
Hi, thanks for the great work.
I developed an autoregressive model that is somewhat similar to T2M-GPT. However, during sampling, I get better results when `if_categorical=False` compared to `if_ca…