Simon Jégou

Hi, thanks a lot for your message, it's a very important feedback as the method needs different to be validated on different datasets. Unfortunately I don't have a lot of...

Hi Barryjui, I updated the README to answer your question. Unfortunately, we can't release the data loader immediately, but if you do want to run the code now you can...

Yes you're right! Sorry for the typo Le 14 janv. 2017 09:40, "rozefeld" a écrit : > Hello. > > I am trying to apply your network on my data....

It seems you have to cast your data in float32 (by default it's float64) Le 4 févr. 2017 16:45, "Tien" a écrit : Hello, I'm also trying to use your...

Hi, can you try to set cnmem=1 in your theanorc? cnmem=0.8 means you only use 80% of your GPU's memory Le 6 févr. 2017 05:42, "Tien" a écrit : Hi,...

Hi, did you try to reduce the batch size / crop size? With crops (224, 224) you should be able to train with batch size 3, with no crops (None),...

You're welcome. Please also note that there is a parameter for cropping in the config file so you don't need to do it manualy Le 9 févr. 2017 07:11, "Tien"...

Thank you for your quick reply @rom1504 For my use case I have to detect small objects on high resolution images, so the multiple crops strategy would be the most...

Thank you for your detailed comments. I may compare the different strategies and post results here if I get interesting insights. So far I have results aligned with the CLIP...

Hello, I did not have time to investigate the performances of the different models on higher image resolutions (e.g. 512x512). I used a multi-crop strategy and get a significant boost...