tmp:tmp 源码

表彰 用法: python main_supcon . py - - batch_size 512 \ - - learning_rate 0.5 \ - - temp 0.5 \ - - cosine \ - - method SimCLR \ - - epochs 1000 \ \ - - model resnet50 \ - - dataset cifar10 \ - - imbalance_order ascent \ - - imbalance_ratio 1 \ - - total_data_num 10000 \ 模型:[resnet50,VGG]数据集:[cifar100,cifar10,SVHN]不平衡顺序:[上升,下降]不平衡比:浮动总数据量:int