-
Hi there,
I added a BatchNorm2d layer in the model and auto-LiRPA failed to parse the graph. Is it a bug?
```console
$ python simple_training.py --num_epochs 3 --scheduler_opts "start=2,length=…
-
您好！
我想用‘simple_verification.py’中代码计算的lp和Up实现您在CROWN那篇论文中实现的二分查找法，并尝试更改如下：
def test(input,model):
eps = 0
gap_gx = 100
eps_LB = -1
eps_UB = 1
counter = 0
is_pos = True
…
-
Do you do last layer elision similar to the original IBP? I saw some references to `C_merged`, is it doing something similar?
if yes it'd be great if you could describe that bit of the code a littl…
-
Hi,
Recently I am using your auto_LiRPA to compute the perturbation bound of hidden features. However, I found that the ub and lb are always exactly the same.
```
eps = 0.012
actions = actions.c…
-
Hi there,
I was trying to reproduce Table 2 in https://openreview.net/pdf?id=Skxuk1rFwB
I was able to produce the same results as in CROWN-IBP on three models, but failed on this one:
```cons…
-
## System
* Version: 0.19.1
* Platform: macOS
* Firefox: 57.0.4
* Selenium: Java 3.8.1
## Behavior
1. Some text input is changed (with sendKeys)
2. Blur the text input (e.g. click another ele…
-
After pushing optimized code for KL/symmetrized KL/Jensen-Shannon-divergence of Categorical distributions, @johnmyleswhite an I have been discussing the possibilty of generic analytical code for finit…
-
On pr1013, the power_monitor reports a change level of 13%, even though the robot has been plugged in for almost 45 minutes. The IBPS battery levels report ~90% for IBPS 0 and 1, and ~54% for IBPS 2 a…