大意果汁
pytorch中BatchNorm1d、BatchNorm2d、BatchNorm3d的区别
1.nn.BatchNorm1d(num_features)1.对小批量(mini-batch)的2d或3d输入进行批标准化(Batch Normalization)操作2.num_features：来自期望输入的特征数，该期望输入的大小为’batch_size x num_features [x width]’意思即输入大小的形状可以是’batch_size x num_features’ 和 ‘batch_size x num_features x width’ 都可以。（输入输出相同）输入
