batra-mlp-lab / visdial

[CVPR 2017] Torch code for Visual Dialog

Home Page:https://arxiv.org/abs/1611.08669

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Models for Android Use?

vyse8 opened this issue · comments

commented

Hi all,

I was hoping to find out more information regarding using your model in my current standalone android app. I'm interested in keeping the same domain initially as I'm only attempting to incorporate this model within Android. Would I just need the data.h5, params.json, and img.h5 files or would I be able to skip that step since my domain is the same?

Thanks.

Interesting. data.h5 and img.h5 have extracted features for dialogs and COCO images respectively. You probably wouldn't need that, but you would need a CNN to extract image features and plug into our VisDial language model.

You should take a look at the prediction script from our demo. That loads a CNN (VGG-16), runs the image through it, and generates dialog predictions from our VisDial language model. Let me know if you have questions.

Also, I have no prior experience running Torch models on Android. So if there's something I'm missing, let me know :)

Closing due to inactivity. Feel free to reopen if you're still working on this.