the deployment problem of O.W, O.F

[Mr-Da-Yang]

First of all thank you very much for your outstanding contribution！ In the paper, you have deployed O.M and O.F many times. I have been searching for a long time and have not found the deployment py file for deploying O.M and O.F. Can you give me some guidance? best wishs

[young169]

First of all thank you very much for your outstanding contribution！ In the paper, you have deployed O.M and O.F many times. I have been searching for a long time and have not found the deployment py file for deploying O.M and O.F. Can you give me some guidance? best wishs

I think it's in the torchreid/models/resnet.py for example. there is a 'ShallowCAM' imported from 'torchreid.components.shallow_cam'. And have you run the training as well as testing both successfully?

[Mr-Da-Yang]

1. ShallowCAM is the attention module，O.M is a kind of regularization, which should appear in the process of network backpropagation, but it has not been found yet
2. Currently not running this project

[shuaizzZ]

@Mr-Da-Yang if not fixbase: reg = regularizer(model) # ow loss += reg if not fixbase and args.use_of and epoch >= args.of_start_epoch:

        penalty = of_penalty(outputs)  # of
        loss += penalty

[Mr-Da-Yang]

@Mr-Da-Yang if not fixbase: reg = regularizer(model) # ow loss += reg if not fixbase and args.use_of and epoch >= args.of_start_epoch:

        penalty = of_penalty(outputs)  # of
        loss += penalty

Thank you very much! I get it.

[shuaizzZ]

@Mr-Da-Yang 方便交流一下吗，我也刚刚开始学习这篇文章，[email protected]