qoherent/RIA_Example
19
0
Fork 0
Code Issues Pull Requests Workflows Packages Projects Releases Wiki Activity

Update Model Builder instructions to use checkpoint (.ckpt) files

Browse Source
This commit is contained in:
L lswersk 2026-04-21 15:12:57 -04:00
parent ab23ee50f0
commit 5b94865b86
1 changed files with 9 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
README.md
View File

@ -31,7 +31,7 @@ RIA_Example/
│ └── example_synthetic_dataset.h5 # Synthetically generated dataset (Generator output) │ └── example_synthetic_dataset.h5 # Synthetically generated dataset (Generator output)
│ │
├── models/ ├── models/
│ ├── example_model.pt # PyTorch Module (Model Trainer input / output) │ ├── example_model.ckpt # PyTorch Module (Model Trainer input / output)
│ └── example_model.onnx # Exported ONNX model (Screens / Application Packager input) │ └── example_model.onnx # Exported ONNX model (Screens / Application Packager input)
│ │
├── applications/ ├── applications/
@ -67,9 +67,9 @@ The Library is a cross-repository browser for all RF and ML assets on the platfo
|------|-----------|-------------| |------|-----------|-------------|
| Recording | `.h5` / `.hdf5` | Raw IQ capture files | | Recording | `.h5` / `.hdf5` | Raw IQ capture files |
| Radio Dataset | `.h5` / `.hdf5` | Labelled, curated training datasets | | Radio Dataset | `.h5` / `.hdf5` | Labelled, curated training datasets |
| PyTorch Module | `.pt` / `.pth` | Serialized PyTorch models | | PyTorch Module | `.py` | PyTorch model definitions with a nn.Module class |
| PyTorch State Dict | `.pt` / `.pth` | Model weight dictionaries | | PyTorch State Dict | `.pt` / `.pth` | Model weights / state dictionaries |
| PyTorch Checkpoint | `.pt` / `.pth` | Mid-training checkpoints | | PyTorch Checkpoint | `.ckpt` | Training checkpoints with weights, optimizer state, and metadata |
| ONNX Graph | `.onnx` | Portable inference models | | ONNX Graph | `.onnx` | Portable inference models |
--- ---
@ -153,13 +153,13 @@ The Generator creates synthetic labelled datasets from a parameter sweep without
The Model Trainer builds a training workflow YAML and commits it to your repository. A Gitea Actions runner then executes the training job. The Model Trainer builds a training workflow YAML and commits it to your repository. A Gitea Actions runner then executes the training job.
**Example files:** `datasets/example_radio_dataset.h5`, `models/example_model.pt` (optional pre-trained start) **Example files:** `datasets/example_radio_dataset.h5`, `models/example_model.ckpt` (optional pre-trained start)
**Expected output:** `.riahub/workflows/train.yaml` in your repository, plus a trained `example_model.pt` artifact **Expected output:** `.riahub/workflows/train.yaml` in your repository, plus a trained `example_model.ckpt` artifact
**Steps:** **Steps:**
1. Go to **Model Builder → Model Trainer**. 1. Go to **Model Builder → Model Trainer**.
2. In **Repository**, select the repository where you want to store the workflow and output artifacts. 2. In **Repository**, select the repository where you want to store the workflow and output artifacts.
3. In **Model**, choose an architecture (e.g. `ResNet1D`) or use `example_model.pt` as a starting checkpoint. 3. In **Model**, choose an architecture (e.g. `ResNet1D`) or use `example_model.ckpt` as a starting checkpoint.
4. In **Dataset**, select `example_radio_dataset.h5` from the Library. 4. In **Dataset**, select `example_radio_dataset.h5` from the Library.
5. Configure training: 5. Configure training:
- **Optimizer:** `Adam`, learning rate `1e-3` - **Optimizer:** `Adam`, learning rate `1e-3`
@ -197,12 +197,12 @@ HPO runs a sweep over a configurable search space, training multiple model varia
Compression applies pruning and/or quantization to reduce model size for edge deployment. The output is an ONNX file. Compression applies pruning and/or quantization to reduce model size for edge deployment. The output is an ONNX file.
**Example files:** `models/example_model.pt`, `datasets/example_radio_dataset.h5` **Example files:** `models/example_model.ckpt`, `datasets/example_radio_dataset.h5`
**Expected output:** `models/example_model.onnx` **Expected output:** `models/example_model.onnx`
**Steps:** **Steps:**
1. Go to **Model Builder → Compression**. 1. Go to **Model Builder → Compression**.
2. Select `example_model.pt` as the source model and `example_radio_dataset.h5` as the calibration dataset. 2. Select `example_model.ckpt` as the source model and `example_radio_dataset.h5` as the calibration dataset.
3. Configure the compression pipeline (pruning ratio, quantization bits). 3. Configure the compression pipeline (pruning ratio, quantization bits).
4. Click **Commit Workflow**. The Actions job exports the compressed model to ONNX automatically. 4. Click **Commit Workflow**. The Actions job exports the compressed model to ONNX automatically.
5. The resulting `.onnx` file is committed back to your repository. 5. The resulting `.onnx` file is committed back to your repository.