코드 : facebookresearch/swav def train(train_loader, model, optimizer, epoch, lr_schedule, queue): batch_time = AverageMeter() data_time = AverageMeter() losses = AverageMeter() softmax = nn.Softmax(dim=1).cuda() model.train() use_the_queue = False end = time.time() for it, inputs in enumerate(train_loader): # measure data loading time data_time.update(time.time() - end) # update learning rate ite..

Paper Arxiv 링크 저자 github Contribution simultaneously clusters the data "swapped" prediction memory efficient multi-crop Loss $$L(\boldsymbol{z}_{t},\boldsymbol{z}_{s})=\mathit{l}(\boldsymbol{z}_{t},\boldsymbol{q}_{s})+\mathit{l}(\boldsymbol{z}_{s},\boldsymbol{q}_{t})$$ Online clustering $\boldsymbol{z}_{t}$가 $C$를 지남. (fc layer랑 하는 역할이 비슷, but 훈련이 $f_{\theta}$와 다르게 됨.) 그다음 $\boldsymbol{q}_{s}$를 예..