Skip to content

Issues: MarvinTeichmann/tensorflow-fcn

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.

Sign up for GitHub

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

21 Open 31 Closed
21 Open 31 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

What the speed it can reach?
#59 opened Apr 5, 2019 by ming71
The weight decay (the regularization loss) is not applied for the fc_layer and upscore_layer
#58 opened Aug 3, 2018 by SpinachR
Hello, could you tell me how to modify to achieve the effect in the article, you can run but the result is very poor.
#57 opened Jun 8, 2018 by linydf
convert the ckpt model to movidius graph
#56 opened May 31, 2018 by zhanghanbin3159
1
What does the "use_dilated" mean in "build" function?
#54 opened May 5, 2018 by VincentFEI
1
is the vgg16.npy random weights or trained weights....?
#52 opened Mar 23, 2018 by ChinmayKalyankar
The problem about fcn8_vgg.py
#51 opened Feb 11, 2018 by SmmileIU
An example of images with shape [None, h, w, 3]
#49 opened Jan 6, 2018 by GeorgiAngelov
A problem with fcn8_vgg.py
#47 opened Dec 14, 2017 by jionie
A problem about the deconvolution
#46 opened Nov 10, 2017 by GZHermit
3
I train datasets "ADEChallengeData2016",But loss is almost the same
#45 opened Nov 6, 2017 by lily10086
3
Extend your get_deconv_filter from 2D to 3D. How?
#44 opened Sep 21, 2017 by John1231983
A problem about fcn8_vgg.py
#43 opened Sep 6, 2017 by liuzhisheng1226
2
Memory error
#41 opened Aug 14, 2017 by ztyxd
test_fcn32 fails, but test_fcn8 and test_fcn16 complete
#39 opened Jul 25, 2017 by bgr33r
can't download vgg16.npy file
#36 opened Jul 4, 2017 by jm-huang
7
Model initialization from scratch
#34 opened Jun 25, 2017 by aleksandrmelnyk
2
why kSize of 64 in upscore_layer
#32 opened Jun 16, 2017 by yzhang123
train just for segmentation
#29 opened May 30, 2017 by bhralzz
5
Implementation for fully connected layer.
#27 opened May 16, 2017 by eveningdong
4
Training code
#26 opened May 7, 2017 by amirabs
4
ProTip! Mix and match filters to narrow down what you’re looking for.