Add ONNX exports (dynamic batch; static 480x736 and dynamic H/W)

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 inference, scale pixels to `[0, 1]`, then normalize with the ImageNet mean `(0.485, 0.456, 0.406)` and std `(0.229, 0.224, 0.225)`. TAO `depth_net` uses this same preprocessing for training and inference.
- The output is the disparity of the left image, in pixels, at the input resolution.
- H and W must be multiples of 32. Other sizes fail at a `Concat` in the feature decoder. Pad the pair up to the next multiple of 32 and crop the output back to the original size. The static file accepts only 480x736.

## Provenance

- Both files were exported from this repo's `model_best_bp2_serialize.pth` (sha256 `7aee85948373da62b0503c2542507129a3e7cab9d97d10e6790d89512a7db214`).
- Export settings: TAO Toolkit `depth_net export` (`torch.onnx.export`), opset 17, traced at 1x3x480x736, `valid_iters: 8`. Each graph has 22,792 nodes and no custom ops.
- The export source includes two fixes:
- [NVIDIA-TAO/tao-pytorch#152](https://github.com/NVIDIA-TAO/tao-pytorch/pull/152) keeps the batch axis truly dynamic.
- [NVIDIA-TAO/tao-pytorch#153](https://github.com/NVIDIA-TAO/tao-pytorch/pull/153) replaces the correlation-pyramid AveragePool. Without it, batch >= 3 fails to build. PyTorch (eager) outputs are bitwise identical with and without the change.

## Validation

- **TensorRT 10.16 on an A100 80GB PCIe:**
- Both files build and run at 480x736 in fp16 and fp32 (TF32) for batch 1, 2, 4, 8, 16 and 32.
- Each engine used a single shape, `min = opt = max`.
- fp16 throughput: 49.3 img/s at batch 1 and 54.2 img/s at batch 32 (static file); 48.5 and 54.4 img/s (dyn-H/W file).
- **ONNX Runtime CUDA EP:**
- Batch 3, 4 and 8 run at 480x736.
- The dyn-H/W file also runs at 256x320 with batch 39 and 48.
- At batch 4 and 8, changing other images in the batch did not change any image's output.
- **ONNX Runtime CPU:**
- `onnx.checker` passes for both files.
- Batch-2 smoke runs complete, with finite outputs of the expected shape: 480x736 for both files, and 256x320 for the dyn-H/W file.
- With a synthetic pair shifted by 16 px, the dyn-H/W file predicts 16.0 px of disparity.
- TensorRT was benchmarked at 480x736 only. Other resolutions were checked only with ONNX Runtime.

## TensorRT tips

```bash
trtexec --onnx=onnx/c_fast_foundationstereo_bp2_dynbatch_dynhw.onnx --fp16 \
--minShapes=left_image:4x3x480x736,right_image:4x3x480x736 \
--optShapes=left_image:4x3x480x736,right_image:4x3x480x736 \
--maxShapes=left_image:4x3x480x736,right_image:4x3x480x736 \
--memPoolSize=workspace:24576 --saveEngine=c_fast_foundationstereo_fp16_b4.engine
```

- Give both `left_image` and `right_image` in every shape flag.
- **Builder workspace:**
- 8 GiB is enough for fp16 up to batch 8 and fp32 up to batch 2.
- fp16 at batch 16 and 32 needs about 11 GB and 22 GB; `--memPoolSize=workspace:24576` (24 GiB) covers fp16 batch 1-32.
- fp32 needs about 17 GB at batch 4-8 and 34 GB at batch 16. At batch 32 it needs a 64 GiB workspace, and its execution context uses about 78 GB, which is the limit of an 80 GB GPU.
- If the workspace is too small, the build fails with `Could not find any implementation for node {ForeignNode[...Concat_387]}`. A `Skipping tactic ... insufficient memory` warning on its own is harmless if the build succeeds.

## Verify the download

```bash
sha256sum onnx/*.onnx
# 794647dc718c9564d5ccb56d15527b70a9267e8ddfbd5ecb1e784b323fbd60ed onnx/c_fast_foundationstereo_bp2_dynbatch_480x736.onnx
# 2c79bbb274dc0aef687a8732b987077e9e3aa26ff9dd653141cda48c57dad5d3 onnx/c_fast_foundationstereo_bp2_dynbatch_dynhw.onnx
```

onnx/c_fast_foundationstereo_bp2_dynbatch_480x736.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:794647dc718c9564d5ccb56d15527b70a9267e8ddfbd5ecb1e784b323fbd60ed
+size 103228520

onnx/c_fast_foundationstereo_bp2_dynbatch_dynhw.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c79bbb274dc0aef687a8732b987077e9e3aa26ff9dd653141cda48c57dad5d3
+size 103228473