-
I use your training code with pretrained AlexNet to train SiamRPN, but the performance is pretty bad when only using VID dataset. I use the test code provided by [arbitularov](https://github.com/arbit…
-
-
As a sanity check, using ground truth files as tracking results and evaluating against them should supposedly yield perfect scores. However, the code actually gives a success score of 0.952 (=20/21) i…
-
Hello, that is a really nice tracking project. Good work!
I am playing for a while with this tracking framework.
While training SiamRPN++ with ResNet as backbone, I am plotting the losses in tenso…
-
Hi. I downloaded your code and paper.
As you paper says: “Siamese-based feature extraction and matching”.How to do feature extraction and matching in paper? Can you explain it in detail?
Look forwa…
-
您好博主，请问哪里可以拿到SiamPRN和SiamVGG的原始数据，写论文需要作对比，但是我复现的结果跟原论文结果不一样。
-
Hello
Thanks for your code.
I followed your code and trained ResNet22 on GOT10k.
No modification were done. At the end I got 64.7 on OTB15
How did you get 65.4?
-
I will be appreciated if you can offer that because I can not use the model offered by pytorch model zoo.
-
I trained the model with your tarin code, then I tested it with your VOT code and the following error occurred：
python test_otb.py
Traceback (most recent call last):
File "test_otb.py", line 102…
-
I used the siamese_rpn_r50_20e_lasot_20220420_181845-dd0f151e.pth to inference the demo_sot.py. But when object misses in the
screen, the tracker will track other object which is similar to the orig…