[5868890][ONNX][Autocast] Fix: failure when checking input shape with unknown dimension (#859)

## What does this PR do?

**Type of change:** Bug fix

**Overview:** Skip unknown dimensions when comparing input shape in
model vs calibration data.

## Usage

```python
$ python -m modelopt.onnx.autocast --onnx_path=$MODEL_NAME.onnx --calibration_data=calib_data_10.npz
```

## Testing
See bug 5868890.

## Before your PR is "*Ready for review*"
<!-- If you haven't finished some of the above items you can still open
`Draft` PR. -->

- **Make sure you read and follow [Contributor
guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md)**
and your commits are signed.
- **Is this change backward compatible?**: Yes
- **Did you write any new necessary tests?**: No
- **Did you add or update any necessary documentation?**: No
- **Did you update
[Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?**:
No

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

## Bug Fixes
* Enhanced input shape validation to properly handle dynamic tensor
dimensions, allowing more flexible dimension checking while maintaining
validation accuracy.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

## Aditional info
Regression introduced in
#652.

---------

Signed-off-by: gcunhase <4861122+gcunhase@users.noreply.github.com>

Author: gcunhase

modelopt/onnx/autocast/referencerunner.py

@@ -89,7 +89,16 @@ def _validate_inputs(self, data_loader):
             if sorted(self.input_names) != sorted(data_loader[0].keys()):
                 raise ValueError("Input names from ONNX model do not match provided input names.")
             for inp_name, inp_shape in data_loader[0].items():
-                if self.input_shapes[inp_name] != list(inp_shape.shape):
+                # Get model and data shapes as numpy arrays
+                inp_shape_model = np.array(self.input_shapes[inp_name])
+                inp_shape_data = np.array(inp_shape.shape)
+                # Compare input rank
+                raise_value_error = len(inp_shape_model) != len(inp_shape_data)
+                if not raise_value_error:
+                    # Compare input shape, skipping check for unknown dimensions
+                    mask = inp_shape_model > 0
+                    raise_value_error = np.any(inp_shape_model[mask] != inp_shape_data[mask])
+                if raise_value_error:
                     raise ValueError(
                         f"Input shape from '{inp_name}' does not match provided input shape: "
                         f"{self.input_shapes[inp_name]} vs {list(inp_shape.shape)}. "