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

Feature: Import darknet weights instead of pytorch .wts #53

Closed philipp-schmidt closed 2 years ago

philipp-schmidt commented 2 years ago

Current implementation relies on a pytorch implementation of yolov4 to import darknet weights and export to .wts weights. This format has the benefit of an additional dictionary to look up values, which makes it more convenient to parse.

It should be possible to read the weights directly from the darknet weight file, considering that darknet is written in C and all necessary functions are implemented there and can be looked up. Darknet has a simple way of serializing weights, it simply writes all weights in order of the layer definitions into the file.

philipp-schmidt commented 2 years ago

Will no longer be implemented. We recommend to train the networks in the pytorch versions of yolo. Datasets are somewhat compatible.