-
Hello,
With this repo, is there an easy way to get the local Lipschitz constant of a customized Pytorch CNN on a given image, using the RecurJac method? Thanks.
-
Hello,
Thank you for sharing this codebase! Is it possible to estimate the Lipschitz constant of the proposed network and its components? (specifically including the self-attention mechanism)
-
### 🐛 Describe the bug
I would like to raise a concern about the spectral_norm parameterization.
I strongly believe that Spectral-Normalization Parameterization introduced several versions ago do…
-
Your spectral normalization normalizes the spectral norm of the weight matrix W so that it satisfies the Lipschitz constraint = 1. So we consider whether to combine the wasserstein gan with spectral n…
-
Hi,
I am wondering if it is possible to apply your method to a single layer, i.e., **relu(Wx + b)**. When I try to give LipSDP one layer, I get an "Inner matrix dimensions must agree." error. More …
-
Hi again,
I was able to reconstruct Figure 9 and the corresponding lines in Figure 8 (not exactly but closely)
(MaxMin Hinge 0.1, MaxMin Hinge 0.3, ReLU Hinge 0.1 and ReLU Hinge 0.3) by using `fc_c…
-
Hi, really amazing work.
I have some questions about the convergence:
1. Why set sigma = 0 in BN layer：layers.append(bn_layer(features, 0.0)) # bn layer. Is it because that BN is not recommended …
-
### 論文へのリンク
[[arXiv:1906.01529] Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy](https://arxiv.org/abs/1906.01529)
### 著者・所属機関
Zhengwei Wang, Qi She, Tomas E. Ward
…
-
Dear users & developers, especially to authors of this repository
I encountered the following error message while solve_sdp.py and stuck.
Please save me solve this problem.
python solve_sdp.py…
-
Thank you very much for sharing the code, I have a few questions that I want to bother you
1. Glow is structurally reversible, that is, it is a reversible network without training, and your work is s…