search

isarsoft / yolov4-triton-tensorrt

This repository deploys YOLOv4 as an optimized TensorRT engine to Triton Inference Server
http://www.isarsoft.com
Other
276 stars 63 forks source link

how to get the “.engine” file from the model trained by myself #27

Closed michaelwithu closed 3 years ago

michaelwithu commented 3 years ago

When using the ".wts" file downloaded from Google Driver,I can get the yolov4.engine successfully.

However when change the weight file to mine, I got error while running the ./main The error is : main: /yolov4-triton-tensorrt/networks/../utils/weights.h:17: std::map<std::__cxx11::basic_string, nvinfer1::Weights> loadWeights(std::__cxx11::string): Assertion `count > 0 && "Invalid weight map file."' failed.

By the way. it is error when uisng the weight downloaded from "https://github.com/AlexeyAB/darknet" which size is 246MB.

What should i do to transform my model to ".engine"

philipp-schmidt commented 3 years ago

Have a closer look into the readme, there is a link to a tutorial on creating your own wts file