kunhe/fastap-metric-learning

Code for CVPR 2019 paper "Deep Metric Learning to Rank"

fastap-metric-learning's Issues

weights for network trained in paper

Hello, thanks for sharing your great work!

Would you consider sharing the weights of your network that you used to achieve state-of-the-art on SOP with me? I appreciate that one set of weights would not achieve the numbers in the paper as you used ensemble but that is OK :)

When released pytorch Code?

PPT in CVPR conference?

Thanks for your work.

I wonder can you provide the PPT in CVPR conference?

How to integrate the pytorch version

Hi Author,
Your work is awesome, I wish I could use it in my university project. May I know how to integrate the pytorch version using our own dataset? I'm currently working on rp2k_dataset which is mainly for product classification.

Also , which version of pytorch or any dependencies required to run your work ya?

Any help is greatly appreciated, thanks.

Regards ,
Alex

Results for CUB and CARS datasets

Hi,

Nice work!
Do you guys have any quantitative results for CUB200-2011 and CARS196 datasets?
Are there any limitations which doesn't allow to train FastAP on such small datasets?