v0.1.0
What's Changed
- add version by @thibo73800 in #154
- Trt export from onnx by @thibo73800 in #155
- add
skip_adapt_graph
option to not adapt the graph before to export to TensorRT. - Fix issue when calling
TRTExecutor()
without engine, its nowTRTExecutor(stream=cuda.Stream())
- Automatically adapt graph by default: handle clip operations + simplify onnx graph. Is is not mandatory to override this method anymore. This change will not affect the current trt exporter since the
adapt_graph
method is supposed to be override.
Full Changelog: v0.0.1...v0.1.0