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

关于ZF模型不能实现目标检测 #2

Open
ZoneLai opened this issue Jan 16, 2018 · 7 comments
Open

关于ZF模型不能实现目标检测 #2

ZoneLai opened this issue Jan 16, 2018 · 7 comments

Comments

@ZoneLai
Copy link

ZoneLai commented Jan 16, 2018

您好,使用该工程进行VGG16模型可以准确的进行目标检测,同时比之前一个版本的性能提示了很多,但是我在进行ZF模型测试的时候发现使用博主你上一个版本可以对目标物体进行检测,这个版本无法实现目标检测,同时使用的是(windows-caffe-faster-rcnn\models\FRCNN\zf\test.prototxt)目录下的配置文件和,博主你自带的default_config.json只对里面训练的目标种类进行修改

@huaze555
Copy link
Owner

@ZoneLai 嗯,ZF模型确实有bug,暂时还没去找。

@freedenS
Copy link

@huaze555 我这边用zf执行测试的时候是正常的,训练时total_loss也正常收敛,但是训练完的模型结果很差,而用python版本的结果正常,您用vgg16模型执行训练、测试都是正常的么?

@huaze555
Copy link
Owner

@freedenS ZF模型是有点问题没有解决。最好用vgg_m或者vgg16吧,训练测试都是没问题的。

@freedenS
Copy link

@huaze555 看了下D-X-Y的linux版本的说明,ZF模型训练完毕后使用这个py文件做一个转换之后就可以了,我这边测试通过了。
examples/FRCNN/convert_model.py transform the parameters of bbox_pred layer by mean and stds values, because the regression value is normalized during training and we should recover it to obtain the final model.

@taotaoyuhust
Copy link

@freedenS 用examples/FRCNN/convert_model.py转换的时候报错?
Check failed: registry.count(type) == 1 (0 vs. 1) Unknown layer type: FrcnnProposal

@roywang2011
Copy link

我的是在py-faster-rcnn下训练的,用的zf模型,训练完成后用convert_model.py转换后还是不行,有遇到相同问题的么

@roywang2011
Copy link

@taotaoyuhust caffe编译的版本不对

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

5 participants