Sambit Mohapatra

I also face the same issue. No module named second

I want only lidar and annotations. On Mon, 8 Aug, 2022, 16:23 Benjamin Wilson, ***@***.***> wrote: > Hi @SM1991CODES , > > Are you trying to load only lidar +...

Thanks a lot for that quick response. I think I have seen this in one of the posts in this repo. What I was actually requesting is some full example...

```c++ try { // Deserialize the ScriptModule from a file using torch::jit::load(). trt_ts_mod_cnn = torch::jit::load(trt_ts_module_path); trt_ts_mod_cnn.to(torch::kCUDA); cout

Thank you for your quick response. Here is what I did: **1) Converting to torch-tensorrt via Python: FP16** - I removed the explicit dtype specification def convert_trained_model_to_tensorrt_script_fp16(network, path_weights, trt_ts_save_path): """...

Hi, Thanks for your quick response. Please find attached the file after step 1. Best Regards Sambit argodet_qat.jit.pt On Tue, 13 Sept 2022 at 12:42, Zero Zeng ***@***.***> wrote: >...

Here is the original pth file. argo_det_020922_zdirb_416x416_50mx2_e_80.pth On Tue, 13 Sept 2022 at 13:28, Sambit Mohapatra < ***@***.***> wrote: > Hi, > > Thanks for your quick response. Please find...

No, I use torch-tensorrt and torchscript. Onnx export is not needed in this case, isn't it? I shall check the permission issue. On Wed, 14 Sep, 2022, 07:58 Zero Zeng,...

Okay, well, this is new info. Though I tend to agree with you - regarding performance, I see Torch-Tensorrt C++ performance seems to be not as good as other libraries...

Hello, Thanks for the reply. So are you suggesting that I first train using Pytorch amp in FP32 and finally save the model after casting all it to FP16 as...