-
Hi,
When I run the CROWN verified error with let's say \epsilon = 0.3, what's the exact meaning of the terms in the output like Loss, CE loss etc.? I'd like to estimate or desume a lower bound with…
-
When we run
```
Geokit::Geocoders::GoogleGeocoder3.geocode "1226 Lincoln Place, Brooklyn, NY, United States"
```
We get a return of @city=nil.
Is there something we can tweak on the Geokit side t…
-
Hi,
I've encountered a few issues while using alpha-beta-CROWN for verifying the output of a simple neural network. I would greatly appreciate your assistance in resolving these concerns.
I hav…
-
I seem to be having issues where my play space is always off centered and a few feet below me. I have tried using Continuous Calibration to try and re-center myself. I have tried to not use that and u…
-
I am trying to compute bounds on multiple models in parallel using the `multiprocessing` library. This works fine when using IBP or CROWN, but when using `alpha-CROWN`, I get very nondescript (fatal) …
-
Hi! Thank you for the reply to the question about the 'CROWN' repository!
I want to calculate the minimum r as the same as the 'CROWN', and I tried the code as follows:
def test(input,model):
eps =…
-
Hi!
Your work is so interesting! Thank you!
But is there the code written by pytorch?
-
**Describe the bug**
For the same model, I can compute output bounds successfully for some choices of epsilon-balls, but receive 2 different errors for some other choices of the epsilon-ball. These e…
-
error：
in "patches.py" line 380, in inplace_unfold
assert len(kernel_size) == 2 and len(padding) == 4 and len(stride) == 2
I just add my model in model_defs.py, but it will report the error a…
nbdyn updated
11 months ago
-
Hi All,
I think we may need to keep track somewhere of parameter relationships that will result in the model crashing or behaving in non-physically-meaningful ways. Lots of the parameters on their…