This PR adds two ONNX exports of `model_best_bp2_serialize.pth` under `onnx/`. Both have a dynamic batch axis.
| File | Input shape | Size (bytes) | sha256 |
|---|---|---:|---|
| `onnx/c_fast_foundationstereo_bp2_dynbatch_480x736.onnx` | `[B, 3, 480, 736]` (H/W fixed) | 103,228,520 | `794647dc718c9564d5ccb56d15527b70a9267e8ddfbd5ecb1e784b323fbd60ed` |
| `onnx/c_fast_foundationstereo_bp2_dynbatch_dynhw.onnx` | `[B, 3, H, W]` (H/W dynamic) | 103,228,473 | `2c79bbb274dc0aef687a8732b987077e9e3aa26ff9dd653141cda48c57dad5d3` |
## Inputs and outputs
| Tensor | Type | Shape | Dynamic axes |
|---|---|---|---|
| `left_image` | float32 | `[B, 3, H, W]` | `batch_size`, plus `height`/`width` in the dyn-H/W file |
| `right_image` | float32 | `[B, 3, H, W]` | same as `left_image` |
| `disparity` | float32 | `[B, 1, H, W]` | follows the inputs |
- The inputs are a rectified stereo pair in RGB, NCHW layout. Both inputs must have the same shape.
- **Normalization is not part of the graph.** Before i…
