# Active Learning

> Orchestrate the full active learning loop: train, analyze, push to CVAT, wait for review, pull, merge, retrain.

- **Type:** Skill
- **Install:** `agentstack add skill-macroman5-autotrain-yolo-active-learning`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [MacroMan5](https://agentstack.voostack.com/s/macroman5)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [MacroMan5](https://github.com/MacroMan5)
- **Source:** https://github.com/MacroMan5/autotrain-yolo/tree/master/.claude/skills/active-learning

## Install

```sh
agentstack add skill-macroman5-autotrain-yolo-active-learning
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Active Learning Loop

Orchestrate the complete cycle of model improvement through human feedback:
train -> analyze -> push uncertain images to CVAT -> wait for human review ->
pull corrections -> merge -> retrain.

## Workflow

### 1. Check Current State
Determine where we are in the loop:

```
Has baseline run?
├── No → Run: /experiment baseline
└── Yes → Continue

Has analysis been run?
├── No → Run: /analyze
└── Yes → Continue

Has uncertain_images.txt?
├── No → Run: yolo-analyze --model  --dataset 
└── Yes → Continue
```

### 2. Push Uncertain Images to CVAT
Use the /cvat-push skill:
```bash
yolo-cvat push --from-analysis reports/uncertain_images.txt
```

### 3. Wait for Human Review
Tell the user:
```
Images have been pushed to CVAT for review.
Please annotate/correct the images in CVAT, then tell me when you're done.

CVAT tasks: [list task IDs and URLs]
Images to review: [count]
Priority: [false negatives first, then uncertain]
```

**Do NOT proceed until the user confirms annotations are complete.**

### 4. Pull Corrected Annotations
When the user says annotations are done:
```bash
yolo-cvat pull --task  --output datasets/corrected_batch_N
yolo-validate datasets/corrected_batch_N
```

### 5. Merge with Existing Dataset
```bash
yolo-merge --sources   --output 
yolo-validate 
```

### 5b. Re-Profile After Merge
Run `/review-dataset` to update the dataset profile in training-plan.md.
The profile may have changed (new class distribution, different object sizes).
The experiment reasoning loop needs current data.

### 6. Retrain
Delegate training decisions to the refactored `/experiment` skill.
The reasoning loop will use the updated dataset profile to decide what to try.
```bash
/experiment
```

### 7. Compare Before/After
Compare metrics from before and after the new data:
- Overall mAP50-95 change
- Per-class AP changes
- Specifically check classes that had false negatives

### 8. Write Active Learning Report
Create `experiments/active_learning_log.md`:
```markdown
## Active Learning Iteration N
- Date: YYYY-MM-DD
- Images added/corrected: X
- mAP50-95 before: X.XXXX
- mAP50-95 after: X.XXXX
- Delta: +/- X.XXXX
- Classes most improved: [list]
- Next action: [recommendation]
```

## Decision Tree

```
First iteration ever?
├── Yes → Establish baseline first, then analyze
└── No → Check if previous iteration improved metrics

Metrics improved after new data?
├── Yes → Deploy updated model to CVAT (/cvat-deploy)
│         Continue to next iteration
└── No → Investigate:
         ├── Data quality issue? → Review annotations more carefully
         ├── Overfitting to corrections? → Increase augmentation
         └── Plateaued? → Suggest dataset expansion or architecture change

More than 3 iterations with <0.5% improvement?
├── Yes → Suggest stopping: diminishing returns
└── No → Continue loop
```

## Guardrails
- NEVER skip the merge validation step — corrupted merges ruin models
- ALWAYS compare metrics before and after new data is added
- Document every iteration in `experiments/active_learning_log.md`
- If metrics regress after adding data, STOP and investigate before continuing
- Maximum recommended batch: 200 images per iteration (annotator fatigue)
- Wait for user confirmation at every human-in-the-loop step

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [MacroMan5](https://github.com/MacroMan5)
- **Source:** [MacroMan5/autotrain-yolo](https://github.com/MacroMan5/autotrain-yolo)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-macroman5-autotrain-yolo-active-learning
- Seller: https://agentstack.voostack.com/s/macroman5
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.