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
Poor results #4
Comments
Are you using the latest master? Which network are you using vgg, res101? |
@ruotianluo Yes. I am using latest master(commit 7aa7cda). My network is res101. |
This is really weird. |
Ok, I will try it. By the way, I will get nan in the beginning with a probability about 0.5. |
I have run this for many times, this never happens to me. |
I test your pretrained model and get |
This number sounds reasonable (The numbers haven't been updated). (Although the number is a little different from what I got.) |
I verified, the master branch is the same as the code I'm running. |
It's strange. Can you tell me the information your environment? |
TITANX PASCAL, python 2.7, cuda8.0, cudnn6.0, ubuntu16.04 |
Can you check the intermediate results when the nan emerge. |
For example? Now, I upgrade to cudnn 6.0 and still encounter nan. |
Add assert like, the asserterror will be triggered when the data has nan. |
It throws AssertionError.
|
Which pretrained resnet model did you download? |
The recommended one. |
That's the reason. Please follow the instruction.......... https://drive.google.com/open?id=0B7fNdx_jAqhtaXZ4aWppWV96czg |
Thanks a lot. |
Hi,
I using TITANX, Ubuntu 16.04, Cuda8, Cudnn 5, and train the model as readme. However, I can not get the result mentioned in README. I have two problems.
nan
, it seems there are something wrong in initialization, but I can not find the bug in the code.nan
, I get pool results:Mean AP = 0.6542
orMean AP = 0.5809
. Train on VOC 2007+2012 trainval and test on VOC 2007 by using default config.Can you help me?
The text was updated successfully, but these errors were encountered: