Skip to content

support evaluation on vehicleid #38

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

Open
wants to merge 14 commits into
base: master
Choose a base branch
from

Conversation

zzw-zwzhang
Copy link
Collaborator

No description provided.

@zzw-zwzhang
Copy link
Collaborator Author

improve codes for supporting vehicleid

@zzw-zwzhang zzw-zwzhang reopened this Mar 12, 2021
@@ -311,7 +314,7 @@ def save(self, mAP=None):
self._best_mAP = max(self._best_mAP, mAP)
print(
bcolors.OKGREEN
+ "\n * Finished epoch {:3d} mAP: {:5.1%} best: {:5.1%}{}\n".format(
+ "\n * Finished epoch {:3d} current: {:5.1%} best: {:5.1%}{}\n".format(
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

"current" here is not so good, please specify whether the metric is mAP or CMC here.



@torch.no_grad()
def final_test(cfg, model, cmc_topk=(1, 5, 10)):
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The module name "final_test" is somehow confusing. Maybe you could modify the original "test_reid" into "test_reid_once" and "final_test" into "test_reid".

for idx in range(len(runner.model)):
print("==> Test on the no.{} model".format(idx))
# test_reid() on self.model[idx] will only evaluate the 'mean_net'
# for testing 'net', use self.model[idx].module.net
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The comments need to be modified accordingly.

@@ -50,6 +50,9 @@ TRAIN:
datasets: {'market1501': 'trainval', 'dukemtmcreid': 'trainval'}
unsup_dataset_indexes: [1,]

# repeated number of evaluation
num_repeat: 10 # 10 only for vehicleid dataset, otherwise 1
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Here should be "1" I guess?

epochs: 50
iters: 400
iters: 800
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

As you use market-1501 in this config, the iters should be 400.

@yxgeee
Copy link
Contributor

yxgeee commented Apr 15, 2021

Hi Zhiwei, thanks for your pulling requests. I have made some comments, please check and modify the requests accordingly.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants