<aside> ℹ️ At a glance Job: e.g. Loads and runs models, and computes the gradients evasion attacks use Learned in: M08 - AI Evasion - Foundations Install: e.g. pip install torch in a Python virtual env
</aside>
the ones you reach for first, best one on top
# command # what it does
| Option | What it does | When I use it |
|---|---|---|
| e.g. model.eval() | e.g. Switches the model to inference mode | e.g. Before every attack run |
one heading per job you use it for
Notes
Commands
# command # what it does
what a good result looks like, and what you do next
| Symptom | Likely cause | Fix or backup tool |
|---|---|---|
| e.g. Results change every run | e.g. Model left in training mode | e.g. Call model.eval() first |