tiny-tensorrt
tiny-tensorrt copied to clipboard
Deploy your model with TensorRT quickly.
When I increase batch size, the inference time on TensorRT does not change. Basically if inference time on the batch with size 8 took 20ms. Inference on batch size 16...
Add `target_include_directories` to `CMakeLists.txt` so that `Trt.h` can be automatically added to include path when `tinytrt` be in `target_link_libraries` 在 `CMakeLists.txt` 中使用 `target_include_directories` 来 include 根目录,这样使用 `target_link_libraries` 链接到 `tinytrt` 时会自动将(含有...
提供tinytrt-yolov5作为一个示例,很多人可以进行参考。trt很大一部分用户都是用于目标检测的。 Provide yolov5 as an example, many people can refer to. A large portion of trt users are used for object detection.
please descript your problem in **English** if possible. it will to helpful to more people **Describe the bug** A clear and concise description of what the bug is. **To Reproduce**...
Hi大佬,可以提供一下readme中描述的测试代码和模型吗,感谢! 这是我的邮箱 [email protected]
can I get help on how to run with dynamic shape input in python? can you add an example in python? ```py import cv2 import tritonclient.grpc as grpc_client import time...
the model is resnet50 from TensorRT8 folder. onnx can produce the correct result, but tinytrt can't.  the onnx result  the tinytrt result 
please descript your problem in **English** if possible. it will to helpful to more people **Describe the bug** A clear and concise description of what the bug is. **To Reproduce**...
Thanks for your nice work! Is there any plan for supporting trt8.5 and recently released trt8.6?