transfer onnx to tensorRT error

Aim : i tried to convert an pytorch model to tensort.
solver : 1. using torch.onnx to get the onnx mode.The file ended with .ptoto.
2. using the onnx_mnist.py located in your example file dir.
Then when i run the code:

‘’’
parser.convert_to_trtnetwork()
‘’’
that i got the result.
what(): No converter registered for op type: Slice.

how can i avoid this error, any example to convert pytroch to tensorrt freely. For example, that i can decide which layer to convert and which not to .

Hi,

Please remember that ONNX is supported until TensorRT 4.0 and it is not available for Jetson yet.

Based on your log, you may use the non-supported operation.
Could you confirm this with our document first?
https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html

Thanks.