-
Hi, thank you for the nice implementation!
I have been trying to run the method for perturbation sets other than Linf by changing the input perturbation layer:
```
if args.norm == "Linf":
…
-
微博内容精选
-
Hi, thanks for your great work in this field. I was trying to use the `abcrown.py` file with a ResNet18 adversarially pretrained model (from the Fast Adversarial Training repo). But I'm seeing interme…
-
This was reported on http://groups.google.com/group/sage-support/msg/6a7c93ad16b892bf:
```
sage: from sage.rings.polynomial.real_roots import real_roots
sage: x = polygen(QQ)
sage: f = 2503841067*x…
-
In running the sample code `auto_LiRPA/examples/vision/simple_training.py --bound_type IBP`, I was trying to test whether {the bound of the margin between classes} is equal to {the difference between …
-
I am trying to `compute_bounds` on some feedforward networks and getting an error. Here is a minimal failing example:
```
import torch
import torch.nn as nn
from auto_LiRPA import BoundedModule,…
-
Hello,
I am wondering if the library provides access to intermediate bounds too?
Thanks,
Zhak
-
# 概要
ルートAPIを色々試してみる
※ わかりやすくするため改行しているが、実行しても動かないので要注意
```sh
https://maps.googleapis.com/maps/api/directions/json?
origin=Adelaide, SA
destination=Adelaide, SA
waypoints=optimize:true|Barossa Valley,…
-
Hello,
Thank you for the great implementations.
I am trying to train a ResNet-50 model, as defined in PyTorch, with 100 classes from the entire ImageNet dataset, at the original resolution of 224x…
-
Hi authors,
There are two bound_forward functions in the BoundConv class:
1. https://github.com/KaidiXu/auto_LiRPA/blob/master/auto_LiRPA/operators/convolution.py#L155
2. https://github.com/Kai…