Closed yhifny closed 3 years ago
Hello! Could you provide the command you ran to run your script? If it's not an official example script, do you have the code you used handy? Thanks!
This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.
Please note that issues that do not follow the contributing guidelines are likely to be ignored.
I subclassed Trainer class to implement the supervised constructive loss function (code found using google search). The code is running but it does not save the models checkpoints ` class SupervisedContrastiveLoss(nn.Module): def init(self, temperature, device): """ Implementation of the loss described in the paper Supervised Contrastive Learning : https://arxiv.org/abs/2004.11362 :param temperature: int """ super(SupervisedContrastiveLoss, self).init() self.temperature = temperature self.device = device
class SCLTrainer(Trainer):
` can you please let me know where is the problem?