iminfine

Error: Invalid use of operator.

3

hi body, I follow the instruction and add the code in the original OTB. After running the program,it shows: Load cache file D:\otb-toolkit\cache\sequences_cache.mat 1_Biker , 1_CSK Error using OPE_evaluate>OPE (line...

Thanks for your great work. I notice the training script mainfree.py of Pytorch version does not support multi-gpus training. Is there any technical issue?

The training speed.

2

I have the same hardware as yours i.e. 8 Tesla V100 16G gpus. I tried to train Stark-ST101 for GOT-10K using the default setting i.e. baseline_R101_got10k_only. ``` python tracking/train.py --script...

关于siamfcpp的训练速度

1

同学，你用siamfcpp官方代码训练过吗？我用一片V100在got10k上训练，速度感人，一个epoch要10个小时。你写的代码训练速度是怎样的？

As @wakanawakana said, I also meet the index problem of location refinement code. Besides, I just reproduced the results you did the experiment on BBS data without location refinement, the...

Bug report.

1

https://github.com/cplusx/QATM/blob/89b87287144ef1cd10028a0f506632f4faeed3e4/utils.py#L55 The w and h should be the width and height of the template(first) image instead of the searching(second) image. The same issue can be found on the function score...

How to use the converted model ?

1

I converted PyTorch model to MatConvNet successfully, however I can't use it. Because the structure of the converted model is different from the pertained model in MatConvNet model zoo. Could...

The training time on Imagenet.

14

Thanks for your great work! Could you please tell me how long does it take to train a model on Imagenet using 8 GPUs?

I have modified the code in train_gpt2.py to enable loading a pre-trained model and conveniently obtaining its evaluation loss by inserting a break statement at the beginning of the training...