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,在FCN.py中有一行代码不是很理解,请指教 #5

Open
rw1995 opened this issue Nov 28, 2019 · 3 comments
Open

你好,在FCN.py中有一行代码不是很理解,请指教 #5

rw1995 opened this issue Nov 28, 2019 · 3 comments

Comments

@rw1995
Copy link

rw1995 commented Nov 28, 2019

你好,在FCN.py中有一行代码不是很理解,请指教
for layer in range(begin, end): x = self.features[layer](x) # print(x.shape) output["x%d"%(idx+1)] = xx=self.featureslayer表示什么意思

@rw1995
Copy link
Author

rw1995 commented Nov 28, 2019

@yunlongdong

@weogen
Copy link

weogen commented Nov 29, 2019

@rw1995 ,您好,我在https://github.com/DetectionTeamUCAS/FPN_Tensorflow/issues/81中看到您遇到的问题,我把原生fpn+resnet移植到安卓上一张1280的图像需要20秒左右,完全没法使用,不知道你的fpn+mobilenet的效果和效率如何,不知可否分享一下您修改的方法呢,不胜感激。

@rw1995
Copy link
Author

rw1995 commented Dec 1, 2019

@rw1995 ,您好,我在https://github.com/DetectionTeamUCAS/FPN_Tensorflow/issues/81中看到您遇到的问题,我把原生fpn+resnet移植到安卓上一张1280的图像需要20秒左右,完全没法使用,不知道你的fpn+mobilenet的效果和效率如何,不知可否分享一下您修改的方法呢,不胜感激。

不好意思==,因为效果并不是很好,mobilenet+fpn检测效果仅68左右,所以我丢弃了这个代码

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

2 participants