-
**Describe the bug**
`ValueError: in user code:
/usr/local/lib/python3.7/dist-packages/ydata_synthetic/utils/gumbel_softmax.py:77 call *
cat_cols = [GumbelSoftmaxLayer(name=name)(col…
-
### 🐛 Describe the bug
`torch.nn.functional.gumbel_softmax` returns different results on cpu and on cuda with the same input
```
import torch
torch.random.manual_seed(420)
input = torch.randn(2…
-
Hi Phillip,
Thanks for sharing the code - I enjoyed the paper! I'm trying to reproduce the CITRIS-VAE (w/ autoregressive prior) experiments as part of a class project and just had a few questions.…
-
作者您好，据我的理解，训练时候不同图片裁剪的token数目不同，是通过网络学出来的，而测试的时候裁剪的比例是固定的。
那么会不会导致训练测试阶段不一致呢？而且测试阶段的裁剪比例影响是不是也挺大的？
-
I am reading the paper "DISCRETE GRAPH STRUCTURE LEARNING FOR FORECASTING MULTIPLE TIME SERIES". I compared it with the implemented model named "GTS" in LibCity and met one possible bug.
In LibCity…
-
Hello, I read you paper in CVPR 2022 .
I have a question about your implementation.
in `resnet_quan_imagenet.py` , The `one-hot` vector, which is the number of bits selection for each layer, se…
-
We need to understand fully what we gaining out of sampling. Broadly, it's the ability to have fewer edges and preserved, crisp, graph structures.
-
## ❓ Questions and Help
#### What is your question?
hey I tried to install the fairseq library, but there are some errors here. I don't know how to solve them. I have consulted many documents and …
-
Thanks for your amazing work! But where does the code reflect the process of obtaining subgraphs (Gs) through sampling.
If you see this issue, please tell me the answer.Thanks in advance!
-
Hi!
Great repo and very well documented!
I was wondering, you have implemented your own [Gumbel Softmax function](https://github.com/jxmorris12/categorical-vae/blob/dcb24a12a094a5ddcc91ceb8a116…