Skip to content

fix benchmark category examples #177

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
tiramitree wants to merge 1 commit into
base: main
Choose a base branch
from
+4 −4
Open

fix benchmark category examples #177

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions source/geniesim_benchmark/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,13 +61,13 @@ backward compatible with existing inference servers.
```bash
geniesim benchmark categories # show category counts
geniesim benchmark robots # show robot counts
geniesim benchmark list --robot=g2op --category=instruction_following
geniesim benchmark list --robot=g2op --category=if
```

### Batch-evaluate a sweep

```bash
geniesim benchmark batch --category=instruction_following --robot=g2op
geniesim benchmark batch --category=if --robot=g2op
```

### Convert collected datasets between formats
Expand Down
4 changes: 2 additions & 2 deletions source/geniesim_benchmark/USAGE.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ The whole benchmark is driven by the `geniesim benchmark` CLI verb:
# 1. Discover what's available
geniesim benchmark categories # category counts (instruction / manipulation / spatial / …)
geniesim benchmark robots # robot/embodiment counts
geniesim benchmark list --robot=g2op --category=instruction_following
geniesim benchmark list --robot=g2op --category=if

# 2. Probe your inference server BEFORE launching a sim (catches protocol / NaN issues early)
geniesim benchmark check-inference --infer-host=<IP>:8999
Expand All @@ -39,7 +39,7 @@ geniesim benchmark run g2op_if_pick_block_color --infer-host=<IP>:8999 \
--app.headless=true --benchmark.record=true --benchmark.num_episode=20 --benchmark.seed=0

# 4. Batch-evaluate a whole sweep (one category × robot)
geniesim benchmark batch --category=instruction_following --robot=g2op
geniesim benchmark batch --category=if --robot=g2op
```

> 🖼️ **History image observations (corobot):** the runtime will feed a rolling
Expand Down