Command
vraven certify
Run formal local L-infinity verification for supported operators
Minimal form
vraven certify <model>Arguments and options
| Option | Meaning | Default |
|---|---|---|
model | PyTorch model file | None |
--model-format | Model storage format. VRAVEN instrumentation supports state_dict and trusted pickle models; TorchScript can be loaded but cannot expose PyTorch hooks. | state_dict |
--model-factory, --factory | Import path such as my_project.models:Classifier | None |
--factory-kwargs | JSON object passed to the model factory | {} |
--state-dict-key | — | None |
--strip-prefix | — | None |
--device | — | cpu |
--non-strict | — | False |
--trusted-model | Allow Python-pickle model loading | False |
--input | Input tensor file | None |
--sample-index | — | 0 |
--target | — | None |
--model-name | — | None |
--epsilon-grid | — | 0,0.001,0.005,0.01,0.05,0.1 |
--clip-min | — | None |
--clip-max | — | None |
--radius-search-steps | — | 24 |
--format | — | json |
--output | Output path; defaults to the selected format | None |
Exact local helpRun
vraven certify --help against your installed version before automating a release workflow.