Hello, How to convert the PTH model into an ONNX format model

[wangqingl]

When I train a PTH format model and hope to convert it into an ONNX model, using ONNXRuntime for inference and deployment, I always report an error.

[wangqingl]

When the code runs to
image = [x["iamge"].to(self.device) for x in batch_inputs]
Code error “too many indices for tensor of dimension 3”