slalom/qai-cli
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

another update

Browse Source
This commit is contained in:
slalom
2026-06-12 12:17:02 -04:00
parent 53e886a535
commit 5211d0af14
6 changed files with 278 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
examples/meter-detection/README.md
View File

@@ -156,11 +156,17 @@ qc-cli train status qc-cli-YYYYMMDD-HHMMSS
To submit the job, wait for completion, and automatically import metrics and register the model, run:
```bash
qc-cli train start --wait
qc-cli train start --upload-metrics
```
The default polling interval is 30 seconds. It can be changed with `--poll-interval <seconds>`.
The metrics can be also submitted using:
```bash
qc-cli mlflow upload-metrics
```
## SageMaker Outputs
When the job completes, SageMaker packages the files written under `/opt/ml/model` into `model.tar.gz`.
@@ -176,7 +182,9 @@ training_metrics.json
The archive is stored under the configured `s3.model_prefix`.
During MLflow finalization, `training_metrics.json` provides per-epoch training and validation losses, precision, recall, mAP@0.50, mAP@0.50:0.95, and learning rates. For object detection, mAP and precision/recall are more meaningful than classification accuracy when assessing model quality.
The `mlflow upload-metrics` command imports `training_metrics.json`, which provides per-epoch training and validation
losses, precision, recall, mAP@0.50, mAP@0.50:0.95, and learning rates. For object detection, mAP and precision/recall
are more meaningful than classification accuracy when assessing model quality.
## 6. Configure Qualcomm AI Hub