Skip to content
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.

Sign up for GitHub

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

Jump to bottom

Market1501+500K #107

Closed
KaiyangZhou opened this issue Jan 22, 2019 · 3 comments
Closed

Market1501+500K #107

KaiyangZhou opened this issue Jan 22, 2019 · 3 comments
Labels
new_feature New feature (finished)

Comments

@KaiyangZhou
Copy link
Owner

No description provided.

@KaiyangZhou
Copy link
Owner Author

Code updated, see ef2bacb

@KaiyangZhou KaiyangZhou added the new_feature New feature (finished) label Jan 22, 2019
@KaiyangZhou
Copy link
Owner Author

See here for how to use market1501+500k.

@KaiyangZhou
Copy link
Owner Author

Test result

Initializing model: resnet50_fc512
Initialized model with pretrained weights from https://download.pytorch.org/models/resnet50-19c8e357.pth
Model size: 24.558 M
Loaded pretrained weights from 'log/resnet50_fc512_market_xent/resnet50_fc512_market_xent.pth.tar'
Evaluate only
Evaluating market1501 ...
Extracted features for query set, obtained 3368-by-512 matrix
Extracted features for gallery set, obtained 515913-by-512 matrix
=> BatchTime(s)/BatchSize(img): 0.048/800
Computing CMC and mAP
Results ----------
mAP: 64.3%
CMC curve
Rank-1  : 83.6%
Rank-5  : 91.8%
Rank-10 : 94.8%
Rank-20 : 96.2%
------------------

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
new_feature New feature (finished)
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@KaiyangZhou