Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

你好,我运行eval_mot.py后得出了在5个val set上的评估结果,但是为何没有使用batchnorm层,有warning如下,望解答。 #26

Open
feixiaoyu2223 opened this issue Apr 2, 2019 · 4 comments

Comments

@feixiaoyu2223
Copy link

No description provided.

@feixiaoyu2223 feixiaoyu2223 changed the title 你好,我运行eval_mot.py后得出了在5个val set上的评估结果,但是为何没有使用batchnorm层,有warning如下,望解答: 你好,我运行eval_mot.py后得出了在5个val set上的评估结果,但是为何没有使用batchnorm层,有warning如下,望解答。 Apr 2, 2019
@feixiaoyu2223
Copy link
Author

先是在运行sh make.sh后有如下warning:
/home/wr506/Documents/flyfly/MOTDT/models/psroi_pooling/src/psroi_pooling_cuda.c:23:6: warning: unused variable ‘batch_size’ [-Wunused-variable]
int batch_size = THCudaTensor_size(state, features, 0);

然后运行eval_mot.py后显示没有使用batchnorm层,有warning如下:
loading layers from squeezenet1_1...
2019-04-02 14:55:27 [WARNING]: No layer: upconv_1.1.num_batches_tracked
2019-04-02 14:55:27 [WARNING]: No layer: proj_1.2.num_batches_tracked
2019-04-02 14:55:27 [WARNING]: No layer: upconv_2.1.num_batches_tracked
2019-04-02 14:55:27 [WARNING]: No layer: proj_2.2.num_batches_tracked
2019-04-02 14:55:27 [WARNING]: No layer: cls_conv.1.num_batches_tracked
load cls model from: data/squeezenet_small40_coco_mot16_ckpt_10.h5

我用的是pyrorch0.4.1+python3.6版本,急求解答方案,谢谢。

@longcw
Copy link
Owner

longcw commented Apr 2, 2019

num_batches_tracked 是pytorch后来加入的参数,不影响实际的计算。

@feixiaoyu2223
Copy link
Author

真是太感谢作者的回复了!

@ubuntuyumiao
Copy link

真是太感谢作者的回复了!

你好 你跑通了吗? 我的错误和你一样 我想用笔记本的cpu做实验,把程序中的cuda全注释换成了cpu ,也有和你一样的问题

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants