Output for YOLO and LeNet

KleinYuan / Caffe2-iOS

Caffe2 on iOS Real-time Demo. Test with Your Own Model and Photos.

MIT License

227 stars 45 forks source link

Output for YOLO and LeNet #13

Open Shoshin23 opened 7 years ago

Shoshin23 commented 7 years ago

Hey!

Awesome job loading LeNet on the fly! On first run it seems to be loading fine but the output is something I'm not able to comprehend. If you can give me some idea about the issue itself I would love to fix it and submit a PR. :)

Thanks!

Shoshin23 commented 7 years ago

Attaching a pic for reference.

KleinYuan commented 7 years ago

@Shoshin23 Hey Great job! Yes, as you can see, it's impossible for us to map classes to each model. Therefore, by default we only enable the mapping for SqueezeNet and for others we will only show the raw result of the prediction.

What you see here is the raw result and you pbbly wanna edit the code to map it to make it look like better lol.

I will be happy to see your Pull Request. 👍

We merged feature-model branch into develop --> master and published 2-0-stable. Feel free to submit PR