amirstan_plugin icon indicating copy to clipboard operation
amirstan_plugin copied to clipboard

Useful tensorrt plugin. For pytorch and mmdetection model conversion.

Results 15 amirstan_plugin issues
Sort by recently updated
recently updated
newest added

CMake Error at CMakeLists.txt:103 (if): if given arguments: "CUDA_VERSION" "VERSION_GREATER_EQUAL" "10.0" Unknown arguments specified -- Configuring incomplete, errors occurred!

when i make your project, it seams that i meet a unknown problem(my gcc version is 7(7.1)) ![image](https://user-images.githubusercontent.com/27887548/96873999-37504200-14a8-11eb-8556-a2cbbcb05de9.png)

I have a deepstream pipeline running on deepstream-5.0 (on a docker container). So far, I have been working on Jetpack 4.4 (with the amirstan_plugin on the v0.2.0, and using the...

Thanks for your good job! When converting my backbone resnet101 into trt using mmdet2trt, batchsize=1 is ok. But when batchsize >1, I find only the first images of each batch...

Hi, i am using MMdet to create a detection model (mmdet 2.25.1, mmcv-full 1.6.1). I now want to convert it to TensorRT to use it on deepstream. I have been...