HelloRicky123

理论上应该是可以的。应该是只用到了pytorch。代码可能需要调试一下修改路径什么的

可能是crop的时候没有越过图片边界了吧

过去太久了，不太能回忆细节了，可以调试一下bug。 可以在 File "/home/rlc/H_R-Siamese-RPN/lib/utils.py", line 131, in get_instance_image 这个错误的地方使用try，except，embed停一下，看看具体错误的(img, cx, cy, size_x, s_x, img_mean)是什么。

It is downloaded with the OTB dataset.

Just like the paper, this code use 255 to train and 271 to test.

No, I processed the ytb and put it in the dataset I uploaded.

I concerned many may have no vpn...

With padding

It is not convenient..

According to my experience, I can get about 0.53 AUC on OTB100 with only vid dataset and 0.63 AUC with vid and youtube-bb. So the gap is not small.