-
Notifications
You must be signed in to change notification settings - Fork 61
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
Test accuracy is low on cub #14
Comments
If you could point me to a repo, I could probably help to figure out the issue. Otherwise, I don't have any clues.... |
@sandareka I'm not really able to help if you don't provide exact steps to reproduce your problem. |
Hi @gy20073 , Thank you very much for your prompt reply. This is my approach. I'm trying to classify CUB bird dataset. For that I integrated your new caffe layers to my version of caffe as you have explained in the readme. I added all the files and rebuilt. Build was sucessful. Then I tried to use your model(provided prototxt file and .caffemodel from google drive) to classify images. However, classification is almost always incorrect. What I want to confirm is if the .caffemodel files given in the google drive are weights of the compact bilear model trained for classification of CUB birds dataset? I hope I'm clear now. Your help with this regard is highly appreciated. Thank you! |
ok, I understand your steps now.
Have you tried using the old version of Caffe that comes with my repo?
If you could try that and get normal accuracy, then it indicates that the weights are not compatible with newer version of Caffe.
Otherwise there might be some details we are missing.
… On Oct 9, 2017, at 7:55 PM, Sandareka Wickramanayake ***@***.***> wrote:
fy CUB bird dataset. For that I integrated your new caffe layers to my version of caffe as you have explained in the readme. I added all the files a
|
@gy20073 @sandareka .I found that it worked well in cuda7-5 ,cudnnv4,but failed in cuda 8 with cudnn v4 or v5.Beside, I try to upgrade the caffe version and it works in cuda8 ,cudnnv5. |
Hi @gy20073 , No I didn't try with your version of caffe. I will give it a try. But as per my understanding .caffemodel contains weights (numbers) and they shouldn't depend on caffe version. Please correct me if I'm wrong. Further, I have used pretrained models trained with earlier caffe versions with my current version of caffe and they worked perfectly. Anyway I will try with your older version. Thank you very much for your cooperation. |
@MyChocer Did you mean when you upgrade caffe version it worked well? May I please know your caffe version? I have cuda 8 and cuddn v5. |
I download the provided trained model from the website
(https://drive.google.com/open?id=0B0ldy05JZFSaS1pIUjBaSUxMTUU)
and test the cub dataset. But I get only 0.003 test accuracy and high loss up to 5.29.
And, I used the script in the folder(examples/compact_bilinear) and I didn't modify anything.
Could you help me to solve this problem?
The text was updated successfully, but these errors were encountered: