search

ardianumam / Tensorflow-TensorRT

This repository is for my YT video series about optimizing a Tensorflow deep learning model using TensorRT. We demonstrate optimizing LeNet-like model and YOLOv3 model, and get 3.7x and 1.5x faster for the former and the latter, respectively, compared to the original models.
303 stars 110 forks source link

how to get tf format for custom yolo weights #3

Closed LukeAI closed 5 years ago

LukeAI commented 5 years ago

Thanks a lot for this highly educational repo!

I would like to train my own Yolov3 model and try implementing as a TRT engine in the way that you have. How would you recommend doing so? Did you use a TF implementation of Yolov3 to generate your weights or did you convert from the darknet .weights / .cfg ? Whichever approach, I'd be interested to know which specific repos / tools you used to do it?

ardianumam commented 5 years ago

It's generated using this repo, which is forked from someone repo mentioned there in the readme file. It converts original darknet weights (as described in the repo). If you wanna train your own YOLOv3 and wanna optimize it using TensorRT, you can just store your YOLOv3 model in frozen model, then optimize that frozen model to TensorRT. Please see the video series for the detail. I already show and explain the detail there :)

LukeAI commented 5 years ago

I'm closing this issue, but this is a question I can imagine others asking so could also be useful info for the Readme? :)