torch.nn.functional.batch_norm¶

torch.nn.functional.batch_norm(input, running_mean, running_var, weight=None, bias=None, training=False, momentum=0.1, eps=1e-05)[source][source]¶

对每个通道在数据批次上应用批量归一化。

请参阅 BatchNorm1d ， BatchNorm2d ， BatchNorm3d 以获取详细信息。