Closed zhengxiawu closed 5 years ago
Your result is correct. I have updated the result in the paper and the website will refresh the paper later.
I did the same experiment with Resnet18 and evaluated the results with function in recall notebook, but I only got R@1 58.2%, Did I miss something?
@xialeiliu Did you run with exactly the same hyperparameters as provided in this source code?
One thing you can try is to not l2 normalized the feature vector in the line 22 of the Loss.py
I did same experiment with ResNet18 on CUB200 and CAR196. And also evaluated the results with your notebook. I verified the results on CUB200 is same with your paper, but the results on CAR196 are different with your paper. My result on R@2 is 87.3 but the result on paper is 91.7. I only changed the data directory and then, it well-worked on CUB200 but it didn't work on CAR196.
(I also changed line 6 in run.py Data='CAR' to work on CAR196.)
Is there any mistake, let me know.
thanks.
@BoseungJeong but did you get R@1=86.0% on CARS196?
I clone the project and running the code with the same hyperparameters in the paper. the result is here: CUB R@1 R@2 R@4 R@8 63.0 73.8 82.2 88.8 CAR R@1 R@2 R@4 R@8 80.3 87.3 92.1 95.4 the performance on CUB is basically consistent with the paper but the R@1 on CAR,i can't get R@1=86.0 Could you give me some details about the experiments?
One thing you can try is to not l2 normalized the feature vector in the line 22 of the Loss.py
@BoseungJeong but did you get R@1=86.0% on CARS196?
I got results like @945984093 . But I already revised the line 22 of the Loss.py then I got right results on CAR196. the L2 normalization doesn't need for training on CAR196.
@BoseungJeong @asanakoy I have ran again, the new results (without l2 normalize)is: CAR R@1 R@2 R@4 R@8 CAR 86.9 91.9 95.1 96.9 @littleredxh the result is nice. but i have a question how to explain the metric learning?
self.proxy = torch.eye(N).cuda()
the initial setup means the class center orthogonal. the feature without l2 normalize, it is a Classification problem
I clone the project and running the code with the same hyperparameters in the paper. The recall@1 on Cub200-2011 is 63.79%, which is far from the result in paper 80.5. P.S. the model is DREML(R,12,48). I wonder it may be caused by the different settings of hyperparameters, so would you give me a detailed parameter setting on CUB200-2011?