Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

SkyNet training #4

Open
dujuan1999 opened this issue Sep 28, 2019 · 4 comments
Open

SkyNet training #4

dujuan1999 opened this issue Sep 28, 2019 · 4 comments

Comments

@dujuan1999
Copy link

dujuan1999 commented Sep 28, 2019

Hello!I am a novice, I would like to ask if I can use my own dataset to do target detection training with skynet?I can't seem to find the code.
Thanks!@TomG008

@TomG008
Copy link
Owner

TomG008 commented Feb 28, 2020

@dujuan1999 Yes. You could use your own datasets. For object detection task, please refer to these training scripts. For tracking, you could refer to SkyNet/Tracking/tools/ in this repo.

@TomG008
Copy link
Owner

TomG008 commented Mar 1, 2020

@deepseek In iSmartDNN repo, DNN training is done by GPU. After training, you could import your model to different devices (GPU, FPGA, CPU) for inference.

@DeyanLan
Copy link

@deepseek In iSmartDNN repo, DNN training is done by GPU. After training, you could import your model to different devices (GPU, FPGA, CPU) for inference.

Hello, I want to train a new network for object detection task. I found that it isn't NAS but a fixed network structure in iSmartDNN repo. Could u please provide the related source-code for the CNN network searching project?
If convenience, you could contact me via the CAS-email : [email protected]

@SumantSakhalkar
Copy link

Hey @DeyanLan, thanks for the question. I had the same problem. I too was looking for NAS instead of the fixed n/w. Did you get any updates from the author? Any help would be appreciated.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants