Open yu1206 opened 2 weeks ago
训练时 ,bn层 lr_mult 为什么是0
layer { bottom: "conv1" top: "conv1" name: "bn_conv1" type: "BatchNorm" batch_norm_param { use_global_stats: false } param { lr_mult: 0 } param { lr_mult: 0 } param { lr_mult: 0 } }
训练时 ,bn层 lr_mult 为什么是0
layer { bottom: "conv1" top: "conv1" name: "bn_conv1" type: "BatchNorm" batch_norm_param { use_global_stats: false } param { lr_mult: 0 } param { lr_mult: 0 } param { lr_mult: 0 } }