Skip to content
This repository has been archived by the owner on Jul 2, 2023. It is now read-only.

why all my output results of the fcn32 is ZERO #113

Open
daiyp3360xxxxxisxxxxxxmine opened this issue Mar 28, 2019 · 16 comments
Open

why all my output results of the fcn32 is ZERO #113

daiyp3360xxxxxisxxxxxxmine opened this issue Mar 28, 2019 · 16 comments

Comments

@daiyp3360xxxxxisxxxxxxmine

after the fcn32 was trained for 9 epochs, the output value score of it is still zero.
however, the weight of each layers are not zero. i am wondering if somebody has suggestions to fix this problem.

@wkentaro
Copy link
Owner

wkentaro commented Apr 9, 2019

I think you should try using training data as validation data, and check if it works. If it doesn't work, that means you have a serious bug in your code.

@jdavidd
Copy link

jdavidd commented Apr 14, 2019

I have the sane problem with fcn8s, help anyone?

@BCWang93
Copy link

BCWang93 commented May 2, 2019

after the fcn32 was trained for 9 epochs, the output value score of it is still zero.
however, the weight of each layers are not zero. i am wondering if somebody has suggestions to fix this problem.

Hi,Did you solved this problem?I trained 50 epoch,but when I use the trained model to test,the output is zero.

@BCWang93
Copy link

BCWang93 commented May 2, 2019

I have the sane problem with fcn8s, help anyone?

Hi,Did you solved this problem?I trained 50 epoch,but when I use the trained model to test,the output is zero.

@wkentaro
Copy link
Owner

wkentaro commented May 2, 2019

I have the sane problem with fcn8s, help anyone?

For training fcn8s, you first start training fcn32s and fcn16s.

@BCWang93
Copy link

BCWang93 commented May 2, 2019

I have the sane problem with fcn8s, help anyone?

For training fcn8s, you first start training fcn32s and fcn16s.

Hi,I trained the fcn32 network,but I also has this problem,the output of the network is always zero.

@ShawnNew
Copy link

ShawnNew commented May 28, 2019

I found that in the initialization function, weights are initialized to zero, which may cause the problem. Does anyone knows why the fcn8s need to initialize all the weights to zero?

@wkentaro
Copy link
Owner

I found that in the initialization function, weights are initialized to zero, which may cause the problem. Does anyone knows why the fcn8s need to initialize all the weights to zero?

Because of this #40

@daiyp3360
Copy link

I didn't solve this problem yet, for these days I was tracked by some trifles, I am just going to resume this work. I do think this problem might caused by the initial strategy. i will response here as soon as i solve this problem.

@BCWang93
Copy link

BCWang93 commented Jun 3, 2019

I didn't solve this problem yet, for these days I was tracked by some trifles, I am just going to resume this work. I do think this problem might caused by the initial strategy. i will response here as soon as i solve this problem.

Hi,Did you solved this problem?Thanks!

@phucvu460
Copy link

I have the same problem with fcn32s, all output results are zeros. Anyone can help ?

@prfans
Copy link

prfans commented Nov 20, 2019

I have the same problem, all output results are zeros. Anyone can help ?

@songyuc
Copy link

songyuc commented Jan 17, 2020

Hi, @daiyp3360xxxxxisxxxxxxmine ,
have figure out the problem yet?

@songyuc
Copy link

songyuc commented Jan 17, 2020

Hi @wkentaro ,
I think #40 may have no relation to the initiation strategy, so it cannot account for the problem here.

@hylovezhang
Copy link

I have same problem, did you solve it? @daiyp3360xxxxxisxxxxxxmine

@liul-ing
Copy link

liul-ing commented Nov 6, 2021

can you run the code?i have lots of problems about this code.Could you please share me your code?My email:[email protected]。Thank you very much!!!

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

No branches or pull requests