Can I create a TensorRT engine using a Recurrent Neural Network that was created using PyTorch? From the documentation, it looks like its not possible. Any alternative approaches?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Converting TensorRT models to ONNX to TF/PyTorch | 3 | 1064 | October 12, 2021 | |
| Guidance for PyTorch to TensorRT Deployment | 1 | 424 | September 15, 2021 | |
| How to create a hidden ITensor in TensorRT to implement the recurrent connection | 0 | 732 | March 3, 2019 | |
| Best way to convert PyTorch to TensorRT model | 6 | 3029 | June 14, 2024 | |
| PyTorch to TensorRT engine with TensorRT 3.0 on Jetson TX2? | 2 | 2286 | October 18, 2021 | |
| Is it possible to save and load networkdefinition in different device? | 4 | 373 | March 27, 2020 | |
| Builder.build_cuda_engine fails to build engine but prints no errors | 3 | 992 | September 30, 2021 | |
| Creating a TensorRT engine from an ONNX model file | 1 | 5939 | November 11, 2019 | |
| TensorRT runtime engine compatibility between python API and C++ API | 3 | 366 | July 12, 2021 | |
| AttributeError: 'NoneType' object has no attribute 'create_execution_context' | 1 | 585 | February 11, 2021 |