TracKit issues

PyTorch Ocean model link does not work

2

Hello I was trying to use your ocean model but I think the link does not work. Thank you!

train的时候出现问题

Traceback (most recent call last): File "./tracking/train_ocean.py", line 259, in main() File "./tracking/train_ocean.py", line 199, in main model = models.__dict__[config.OCEAN.TRAIN.MODEL](align=True).cuda() # build model File "/home/bpc/fh/TracKit/tracking/../lib/models/models.py", line 30, in __init__ self.align_head...

fangh026

Ocean 训练问题

7

您好，请教个问题，我按照教程运行python tracking/onekey.py（单独运行train_ocean.py 错误一样）的时候遇到下面报错，不知道是什么问题? Traceback (most recent call last): File "./tracking/train_ocean.py", line 259, in main() File "./tracking/train_ocean.py", line 250, in main model, writer_dict = ocean_train(train_loader, model, optimizer, epoch + 1, curLR,...

tm9161

Row Results download link is not working

Hi, Would you please provide the raw results of Ocean-online on LaSOT and GOT-10k benchmarks? Row Results download link is not working Thanks in advance!

JananiKugaa

OTB50、UAV123一些算法的txt测试结果

2

您好，因为接触跟踪较晚，matlab使用不熟练，所以使用的是pysot画图工具，但是各数据集的txt结果相对难找。目前其他数据集的结果已经找到，还剩两个数据集，请问您能否分享OTB50、UAV123数据集相关算法txt结果的链接，或者邮件分享（[email protected]），麻烦了，感谢！

hongtaofly

修改batch问题

2

你好，我在修改Ocean.yaml的时候发现，将batch设为32或64能正常运行，如果继续调大（如128或192）则会出现如下错误 > `Traceback (most recent call last): File "./tracking/train_ocean.py", line 259, in main() File "./tracking/train_ocean.py", line 250, in main model, writer_dict = ocean_train(train_loader, model, optimizer, epoch + 1, curLR, config,...

n1-k0

单卡训练问题

1

首先在Ocean下问siamban训练的问题有点冒昧，但确实经验不足，忘见谅！由于整个实验室共用两个卡，而其他同门的任务默认卡0，导致出现卡0显存已满，卡1还有很多显存的情况。而算法在第11个epoch开始解冻backbone时，显存溢出，所以请问siamban单卡训练时的训练命令是怎样的？原多卡训练命令： CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch \ --nproc_per_node=2 \ --master_port=2333 \ ../../tools/train.py --cfg config.yaml

hongtaofly