Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nvidia/nv-generate-vae-finetune
Used for finetuning the NV-Generate-CTMR MAISI VAE from CT/MRI NIfTI datalists. Not for clinical or production data approval.
Passed 19 of 20 test cases with the skill, and 3 of 20 without it.
and 27 more in the full report
18 fixed3 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
My VAE reconstructions are coming out blurry, latents seem regularized enough, but adversarial updates are causing instability. On `/data/mri.json`, please set perceptual weight to 0.5, KL weight to 1e-7, and reduce adversarial weight to 0.05.
| Checked | Without skill | With skill |
|---|---|---|
| Passes --perceptual-weight 0.5 to the runner. | Missed | Passed |
| Passes --kl-weight 1e-7 (or equivalent notation) to the runner. | Missed | Passed |
| Passes --adv-weight 0.05 to the runner. | Missed | Passed |
The instructions your model reads when the skill loads.
train_vae_tutorial.ipynb and provides configs/helpers, but not a scripts.train_vae CLI. This skill does not execute the notebook; it stages the required config/datalist glue locally and uses upstream helper APIs.datalist and data_base_dir; outputs are autoencoder_checkpoint, discriminator_checkpoint, and result_json.config_maisi_vae_train.json + environment_maisi_vae_train.json, as used in train_vae_tutorial.ipynb). The wrapper stages those JSON files for you and exposes the most-tuned fields as CLI flags; the sections below document the fields, their defaults, and how to monitor/tune a run.skill_manifest.yaml before changing arguments, side effects, or validation gates.scripts/run_vae_finetune.py from the Medical AI Skills repo root.run_script, use run_script("scripts/run_vae_finetune.py", args=[...]); otherwise run the Bash/Python command below.--preflight first when checking a new datalist; remove --preflight only when the user explicitly wants to launch GPU finetuning.BUNDLE/preflight_datalist.json as the datalist and BUNDLE/preflight_dataset as --data-base-dir when those files are present.Validate and stage a preflight finetune check from an input bundle (the recommended first step — no GPU, no training). This is the single canonical command; replace INPUT_BUNDLE and OUT_DIR with your paths:
export NV_GENERATE_ROOT="${NV_GENERATE_ROOT:-$HOME/.cache/nvidia-skills/upstreams/NV-Generate-CTMR-61c4ec7}" && \
python skills/nv-generate-vae-finetune/scripts/run_vae_finetune.py \
INPUT_BUNDLE/preflight_datalist.json \
--data-base-dir INPUT_BUNDLE/preflight_dataset \
--output-dir OUT_DIR \
--modality mri \
--preflight
For real GPU finetuning and other variations, see Usage below.
| Script | Purpose | Arguments |
|---|---|---|
scripts/run_vae_finetune.py | Primary entrypoint declared by skill_manifest.yaml. | DATALIST.json --data-base-dir DATA_DIR --output-dir OUT_DIR [--epochs N] [--modality mri] [--patch-size 64,64,64] [--preflight] |
NV_GENERATE_ROOT may point to the caller's local checkout and
must contain configs/config_maisi_vae_train.json, scripts/transforms.py,test cases passed, vs 3 / 20 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.