Could you tell the order of the output for each model?
Thanks

Where is the view label for wider ?
Can you share ?

Which version of caffe do you use? Thank you

Hi, I read the paper and can not figure out the way your get xxx_ratio.txt. Is there any magic trick or something? The paper just said its deducted by prior distribution and use a exponents to get. Could your please take an example to show how to do that?
Thanks a lot!

@asc-kit I want to select some properties in the attribute dataset for training and testing. How do I modify and select the attributes I need to train in train.prototxt and deploy.prototxt? thank you very much

Hi,
Thank you for this very usefull repository.
I would like to reproduce VeSPA train with RAP dataset without using Python layers. I suppose that the layers of Python type in train_vespa_rap.prototxt have to be replaced, but I don't know how to do it.
regards

HI ，I found that your PETA attribute only contains 35 attributese, but the offical PETA has 61 attributes, Can you share the meaning of 35 attributes,, Thank you!

Thank you for sharing your models. Apologies if I missed it, but I don't see a license specified. Could you please let us know what license this is shared under, and if it can be used commercially?

I am learning this algorithm recently. Thank you very much for your great work. I tried to train my own data set. Can you provide the init model file "googlenet_after_surgery-vespa.caffemodel"?

Hi
I discovered your results and it's seem interesting !
If i was able to test on particular image, it will be great.
Could you please provide a script to do this ?
regards

Could you provide the init model file "googlenet_after_surgery-vespa.caffemodel"? I want to train my own dataset