-
Notifications
You must be signed in to change notification settings - Fork 253
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
Can you release detailed configuration? #2
Comments
Hi, I got the same as @csyanbin with python 3.5, cuda 8 and pytorch 0.3 |
@bertinetto @jakesnell |
Hello, I just want to add that I implemented the same algorithm in a slight different way (here), and I got the same as @csyanbin too (except for the 20way1shot where I obtained 95.1%). Edit / Side Note: just read this paper: https://arxiv.org/pdf/1711.04043v3.pdf and it seems they are reporting different accuracies with ProtoNet too (97.4 | 99.3 | 95.4 | 98.8) (page 8). |
@dnlcrl I think the results above (97.4 | 99.3 | 95.4 | 98.8) cite the original prototypical paper of ICLR (https://openreview.net/references/pdf?id=BJ-3bnVmg), which is different setting with this git repo. This is also given in appendix A of https://arxiv.org/pdf/1703.05175.pdf, in line1 and line2 of table4. |
@csyanbin Oh I got it, thank you, I must have missed it. |
Hi, The results I get are closer to the reported ones but still different:
|
Hi, Although the performance is slightly better, I think this is not fair for comparison. |
This is for the mini-ImageNet experiments.
This corresponds to the trainval split. The train split has only 1028 unique characters. |
@yannlif |
Hi Guys, |
Hi Jake,
Prototypical networks is really a nice work.
I have run this code to reproduce the results in NIPS paper. However, it seems the results have some differences with the paper.
NIPS2017 paper:
Reproduced results:
I run this code several times and get similar results.
Can you release your hyper-parameter setting? Or is there any technical trick that may impact the performance?
Here is the cmds I used in 20way-1shot setting:
Thanks.
The text was updated successfully, but these errors were encountered: