victor-yudin

INT8 engine building is too slow

2

Hi everyone, I faced the problem during the launching the YOLOv4 inference with INT8 precision on _RTX 3090_ GPU: the _buildEngineWithConfig()_ method is very slow (had been running for 1.5...

segfault while yolox engine making on TensorRT 8

3

**Describe the bug** I try to convert the _yolox_l_ based model to trt engine, but get the error: ``` load checkpoint from local path: epoch_60.pth The model and loaded state...

Problem with tracing the model

15

I'm trying to trace the model to use it later in c++ code by `torch::jit::load()`, but getting an error. Before running the tracing I modified the backbone.py and efficientdet/model.py like...