huanglianghua / siamrpn-pytorch Goto Github PK

How can I test on my own data?

Thank you for your contributions! 👍 You are really admirable!

• Would you please tell me exactly which datasets did you use to train the model? Actually, I'm not sure about the meaning of 'SiamRPN is trained on 4 extra datasets'.

Thanks a lot! 😄

Best regards!

hello, i want to ask whether your training code will release? I want to study your training code, thank you for your answer

您好，感谢分享！
请问能否提供训练代码呢？

Hi, sorry to bother you.
When I use torchsummary to show the network, there is a bug about the size. Could you please explain the reason? maybe bug?

model.pthpretrained/siamrpn

这个模型是万能的吗？不管什么数据集都可以用吗？

In your code, the numbers of kernels of five convolutional layers are 192, 512, 768, 768, 512, respectively. How did you get these numbers?
In the SiamRPN paper, the authors say that they use the AlexNet for extracting features of template branch and detection branch, but the numbers of convolutional kernels of the AlexNet isn't same as yours. So, I am confused.
I am looking forward to your reply, thank you!

Hi,

Thanks for the super clean implementation!
I noticed a discrepancy in the code and what is written in the SiamRPN paper.
Specifically you have: penalty = np.exp(-(change_ratio * change_sz - 1) * self.cfg.penalty_k)
but the paper seems to have penalty = np.exp(-(change_ratio * change_sz) * self.cfg.penalty_k), where did the -1 come from? Also in the paper they write: "After these operations, the top K proposals are re-ranked after multiply the classification score by the temporal penalty." However in your code there is no "top-K" you re-rank all proposals. The performance on VOT2018 seems to agree with SiamRPN nevertheless.

thanks,
Ross

This is a great resource! Thanks so much for making this public.

However, I was wondering if you could add a LICENSE file specifying the license for this repository. I suggest using the MIT or Apache licenses.

Thanks!
Jonathan

Create a symbolic link data to your datasets folder
what should I do?？