Hi,
I would like to serialize my PyTorch model to use it with my C++ application in production. I came across the use of TorchScript (as documented in PyTorch) and torch2trt.
Is there a difference in the serialization achieved by the two?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Looking for examples of inference using C++ | 2 | 362 | October 18, 2021 | |
| C++ made '.trt' model feed into Python TRT API | 3 | 365 | October 12, 2021 | |
| Best way to convert PyTorch to TensorRT model | 6 | 3025 | June 14, 2024 | |
| Can I used model saved by torch2trt in a C++ environment? | 2 | 701 | October 18, 2021 | |
| Does Torch-TensorRT fall back to Torch supported in C++ also? | 0 | 403 | August 11, 2022 | |
| NVIDIA-AI-IOT/torch2trt vs NVIDIA / Torch-TensorRT | 1 | 2473 | May 4, 2022 | |
| TensorRT vS Torchscript for inference | 1 | 696 | February 5, 2021 | |
| Can I use tf-trt with C++ API? | 1 | 785 | November 11, 2019 | |
| What's the difference between engine file and trt file? | 4 | 8842 | October 12, 2021 | |
| TensorRT: Python vs C++ | 1 | 1569 | October 10, 2018 |