Don Mathis

Results 5 issues of Don Mathis

The 'Expand' operator doc says: "this operator is similar to numpy.broadcast_to(input, shape), but the major difference is numpy.broadcast_to() does not allow shape to be smaller than input.size(). It is possible...

spec clarification
contributions welcome

Hi, I am able to run abcrown.py in Linux on the tutorial_examples, but I can't find an explanation of what I see in the file "out.txt". I unpickled the file...

Hi, I can run abcrown.py by following your tutorial_examples and calling it like this from the Linux command line: `python abcrown.py --config exp_configs/tutorial_examples/cifar_resnet_2b.yaml` But is there a recommended way to...

# Bug Report ### Is the issue related to model conversion? no ### Describe the bug Shape inference for Reshape does not infer rank when it could. I have a...

bug
shape inference
contributions welcome

https://github.com/Verified-Intelligence/alpha-beta-CROWN/blob/main/complete_verifier/bab.py In bab.py, in function general_bab, there is a loop over bab "rounds" (lines 295-330). In that loop, one termination condition is that all nodes have been split, in which...