noble action to open source such work , some suggestion to improve about siamese-rpn

[HelloRicky123]

Sorry, I have trouble increasing the accuracy recently.
Using different learning rate is just a trick I found useful sometimes.
My trouble now is the youtube-BB dataset. Due to the vpn's limit dosage, I can't download the dataset. And I'm trying to get the 0.3 EAO on VOT2015 without youtube-bb, but only 0.22 by now.

[HelloRicky123]

2, In the paper they say "Compared to ILSVRC [29] which consists of about 4,000 videos annotated frame-by-frame, Youtube-BB [25] consists of more than 100,000 videos annotated once in every 30 frames. " and the ILSVRC-VID dataset I used has about 4417 videos, so this may have no problem probably.
3, In my initial idea, I use the former 3 layers' weight in the model the paper's code provided. And leave the 4 and 5 layers inited by nn.init.kaiming_normal_. This will need some warm epochs training with small learning rate, and then with big learning rate.
4, This is to make the new boxes' center in the image.

[gjpicker]

Thanks a lot for your patent answer! I have gained more clear after your response.

However , can you show me more explanation about the third point or ,share some ref-links or paper birth to strengthen ? I'am very interesting in your idea ( a pretrained neural network ,joined with a initiate that replace its last layer, demand for multiple learning rates ). In my opinion , it's my first glance of
multiple learning rates in training period. maybe like TTUR

[gjpicker]

Your code's quality is so high that I can't wait to commit here again ,after reading your source code cautiously .

perfect work!

[zzpustc]

@HelloRicky123 How about using TrackinngNet which is released in ECCV2018 instead? It contains more videos than Youtube-BB.

[takecareofbigboss]

hi, maybe you can use some ideas from object detection to improve your performance.

[takecareofbigboss]

@HelloRicky123

[HelloRicky123]

@HelloRicky123 How about using TrackinngNet which is released in ECCV2018 instead? It contains more videos than Youtube-BB.

But this will make it not fair when compared with the paper's code.

[zzpustc]

@HelloRicky123 How much time have you spend to train the model with ILSVRC(VID)?

[HelloRicky123]

About 150 image/s with two 1080Ti GPU.