search

Qengineering / YoloFastest-ncnn-Jetson-Nano

YoloFastestV2 for a Jetson Nano
https://qengineering.eu/deep-learning-examples-on-raspberry-32-64-os.html
BSD 3-Clause "New" or "Revised" License
15 stars 1 forks source link

How to train on one more additional object #3

Open raghavzns opened 2 years ago

raghavzns commented 2 years ago

Hi Sir, I would like to train on an additional object also . How to do that in this same code of yours ? So that it retains same speed

Qengineering commented 2 years ago

With the so-called transfer training you can adapt the deep learning network without changing the topography too much. So the speed will be more or less the same. Google is your friend if you are looking for ways to train your network online.

raghavzns commented 2 years ago

Thanks Sir, I just looked up @dog-qiuqiu (https://github.com/dog-qiuqiu/Yolo-FastestV2). And I'd try to follow the training instructions mentioned over there.