FasterRCNN to ONNX model

Hi there,
I tried to convert a fasterrcnn model to onnx format, and followed the instruction from test/test_onnx.py https://github.com/pytorch/vision/blob/master/test/test_onnx.py.

Here is my code:
model=models.detection.faster_rcnn.fasterrcnn_resnet50_fpn(pretrained=True,min_size=800,max_size=1333)
image=cv2.imread("test.jpg")
image=cv2.resize(image,(1333,800))
image1 = Image.fromarray(cv2.cvtColor(image.copy(),cv2.COLOR_BGR2RGB))
image_tensor=to_tensor(image1)
model.eval()
onnx_io = io.BytesIO()
torch.onnx.export(model, [image_tensor], "faster_rcnn.onnx",do_constant_folding=True, opset_version=_onnx_opset_version)

I have succeed convert the model with the above code, however, when I tried to convert the tensor and model to cuda tensor with .to(device), there is an error that is line 359, in _get_top_n_idx r.append(top_n_idx + offset) RuntimeError: expected device cuda:0 but got device cpu.
I don't know how to solve it.

Please help me with that.

Cheers!

The report follows test/test_onnx.py and fails in _get_top_n_idx during CUDA conversion. Reproduce the Faster R-CNN export with the supplied model and image steps, compare CPU and CUDA tensor devices at that entry point, and confirm the conversion completes without the device mismatch.