Fix output_names to include masks when exporting segmentation models.

[Abdul-Mukit]

Description

Closes: #401
When exporting RFDETRSegPreview model, the output_names doesn't contain "masks" in

rf-detr/rfdetr/main.py

Line 543 in 9fd9789

output_names = ['features'] if backbone_only else ['dets', 'labels']

Fixes:

If args.segmentation_head == True add "masks" to output_names before calling export_onnx.

Type of change

Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• This change requires a documentation update

How has this change been tested, please provide a testcase or example of how you tested the change?

Run the following code snippet. Optionally change RFDETRSegPreview with any other model.

from rfdetr import RFDETRSegPreview
import onnxruntime as ort

model = RFDETRSegPreview()
model.export(verbose=False)

session = ort.InferenceSession("output/inference_model.onnx")

inputs = session.get_inputs()
print("ONNX input details: ")
for input in inputs:
    print(input.name, input.shape, input.type)

print("ONNX output details: ")
outputs = session.get_outputs()
for output in outputs:
    print(output.name, output.shape, output.type)

Output with this PR is the same as expected output:

ONNX export completed successfully
ONNX input details:
input [1, 3, 432, 432] tensor(float)
ONNX output details:
dets [1, 200, 4] tensor(float)
labels [1, 200, 91] tensor(float)
masks [1, 200, 108, 108] tensor(float)

Any specific deployment considerations

None

Docs

None

[Abdul-Mukit]

I have read the CLA Document and I sign the CLA.