Personalised FedReID #10
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 30 commits
December 30, 2020 15:50
weimingwill
requested changes
May 11, 2021
| # inputs = Variable(inputs.cuda().detach()) | ||
| # labels = Variable(labels.cuda().detach()) | ||
| # else: | ||
| # inputs, labels = Variable(inputs), Variable(labels) |
There was a problem hiding this comment.
Can just remove these comments
| optimizer = get_optimizer(self.model, self.lr) | ||
| scheduler = lr_scheduler.StepLR(optimizer, step_size=40, gamma=0.1) | ||
| # scheduler = lr_scheduler.StepLR(optimizer, step_size=40, gamma=0.1) |
There was a problem hiding this comment.
Why we don't need the scheduler anymore?
| # parser = argparse.ArgumentParser(description='Training') | ||
| # parser.add_argument('--result_dir', default='.', type=str) | ||
| # parser.add_argument('--dataset', default='no_dataset', type=str) | ||
| # args = parser.parse_args() |
| gallery_label = np.array(result['gallery_label']) | ||
| # print(type(query_feature),query_feature[:3]) | ||
| # print(type(query_cam),query_cam[:3]) | ||
| # print(type(query_label),query_label[:3]) |
There was a problem hiding this comment.
Remove these debugging prints
| # result = scipy.io.loadmat(file_path) | ||
| # print("========= after loading ==========") | ||
| # for i in result: | ||
| # print(i, np.array(result[i]).shape) |
| if args.regularization: | ||
| reg = "reg" | ||
| else: | ||
| reg = "Nreg" |
There was a problem hiding this comment.
Are these if else from line 95 - 110 only for setting the name for the checkpoint? It would be better to put them into a function.
| @@ -53,24 +54,87 @@ | |||
| parser.add_argument('--multiple_scale',default='1', type=str,help='multiple_scale: e.g. 1 1,1.1 1,1.1,1.2') | |||
| parser.add_argument('--test_dir',default='all',type=str, help='./test_data') | |||
|
|
|||
| parser.add_argument('--resume_epoch', default=0, type=int, help='resume from which epoch, if 0, no resume') | |||
There was a problem hiding this comment.
Shouldn't it be resume round?
| @@ -0,0 +1,4 @@ | |||
| export PYTHONPATH=$PYTHONPATH:$pwd | |||
There was a problem hiding this comment.
Put all these scripts for running into a separate folder script
| import torch.optim as optim | ||
| from torchvision import datasets | ||
| # from finch import FINCH |
| if epoch==0: | ||
| self.L0 = torch.Tensor(loss) | ||
|
|
||
| avg_loss = sum(loss) / self.num_of_clients | ||
|
|
||
| print("==============================") | ||
| print("number of clients used:", len(models)) | ||
| # print("number of clients used:", len(models)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
support personalised clustering training for FedReID