I'm running human pose estimation experiments from source code(https://github.com/opencv/openvino_training_extensions/blob/develop/pytorch_toolkit/human_pose_estimation/README_single.md).
I trained according to the author's instructions. The process of converting to onnx format also has no errors. However, when converting from onnx to openvino format, the following error occurs:
> Unexpected exception happened during extracting attributes for node 386.
Original exception message: Upsample mode bilinear for node 387 is not supported. Only nearest is supported.
> %387 : Float(1, 290, 16, 16) = onnx::Upsample[mode="bilinear"](%385, %386), scope: SinglePersonPoseEstimationWithMobileNet/RefinementStage/Sequential[trunk]/UShapedContextBlock[0]
I think the error is in the following code:
` d2 = self.decoder2(torch.cat([e1, F.interpolate(e2, size=(16, 16),
mode='bilinear', align_corners=False)], 1))`
` d1 = self.decoder1(torch.cat([x, F.interpolate(d2, size=(32, 32),
mode='bilinear', align_corners=False)], 1))`
I changed mode to `nearest` but Pytorch support only: `linear`, `bilinear`, `trilinear`.
