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

update

Browse Source
This commit is contained in:
samirodr
2026-06-08 14:59:44 -04:00
parent 6a560a8610
commit 5360a482fc
3 changed files with 21 additions and 216 deletions
Download Patch File Download Diff File Expand all files Collapse all files

81
examples/ai-hub/README.md
View File

@@ -13,18 +13,10 @@ This example takes the ONNX model produced by the SageMaker training example and
Run the training example first and wait for it to complete:
```bash
bash examples/training/run_training.sh --config config.yaml --wait
examples/training/run_training.sh --wait
```
If the dataset is already uploaded to S3, use:
```bash
bash examples/training/run_training.sh --config config.yaml --skip-upload --wait
```
The training artifact must contain a static-shape `model.onnx`. The training example exports an input named `input` with shape `1x3x160x160`.
Your `config.yaml` must include AI Hub settings:
The `config.yaml` file must include AI Hub settings:
```yaml
aihub:
@@ -36,16 +28,20 @@ aihub:
output_dir: build/qai-hub
```
You also need local Qualcomm AI Hub SDK authentication configured.
Finally, the user needs to authenticate with Qualcomm AI Hub using:
```bash
qai-hub configure --api_token
```
## Prepare Inputs
AI Hub does not consume the raw JPG training images directly. It needs NumPy tensors that match the ONNX model input shape and preprocessing.
Generate calibration and validation inputs:
To generate calibration and validation inputs:
```bash
uv run python examples/ai-hub/prepare_inputs.py
python examples/ai-hub/prepare_inputs.py
```
This writes:
@@ -61,58 +57,23 @@ The script applies the same image preprocessing used by the training example:
- convert to channel-first `1x3x160x160`
- normalize with ImageNet mean and standard deviation
Useful options:
## Upload Model to Qualcomm Workbench
The model can be uploaded to Qualcomm Workbench using:
```bash
uv run python examples/ai-hub/prepare_inputs.py \
--dataset-dir examples/training/data/flower_photos_sagemaker \
--calibration-dir examples/training/data/aihub_calibration \
--input-file examples/training/data/inputs.npz \
--samples 16
qc-cli ai-hub upload examples/training/data/aihub_calibration examples/training/data/inputs.npz
```
## Run AI Hub
The first argument is the calibration path for the model and the second argument is the input file, both of which were created by the `prepare_inputs.py` script. For more details, add `--help` after the `upload` command.
After training completes and inputs are prepared:
The `upload` command runs the following commands in order:
1. `qc-cli ai-hub quantize`
2. `qc-cli ai-hub compile`
3. `qc-cli ai-hub validate`
4. `qc-cli ai-hub profile`
Finally the user can download the model from AI Workbench using the command
```bash
bash examples/ai-hub/run_ai_hub.sh --config config.yaml
qc-cli ai-hub download
```
By default, the script uses the last SageMaker training job recorded in `.qc-cli.json`. It downloads that job's `model.tar.gz`, extracts `model.onnx`, runs the AI Hub workflow, and downloads the compiled artifact.
To use a specific training job:
```bash
bash examples/ai-hub/run_ai_hub.sh \
--config config.yaml \
--from-job qc-cli-YYYYMMDD-HHMMSS
```
To resume from a later Workbench step:
```bash
bash examples/ai-hub/run_ai_hub.sh \
--config config.yaml \
--from-step validate
```
To skip downloading the compiled artifact:
```bash
bash examples/ai-hub/run_ai_hub.sh \
--config config.yaml \
--skip-download
```
## Troubleshooting
If AI Hub reports dynamic input shapes, rerun training with the current training source. AI Hub quantization requires the exported ONNX model to use static input shapes.
If `run_ai_hub.sh` reports missing calibration or input files, run:
```bash
uv run python examples/ai-hub/prepare_inputs.py
```
If validation fails with a missing input name, make sure `config.yaml` and the generated `.npz` both use `input` as the input name.