Machine learning caffe“消息类型”;caffe.ParamSpec“;没有名为“的字段”;传播“向下”;
我想在训练时修复一些层的参数,所以我在这样的层中使用Machine learning caffe“消息类型”;caffe.ParamSpec“;没有名为“的字段”;传播“向下”;,machine-learning,computer-vision,caffe,Machine Learning,Computer Vision,Caffe,我想在训练时修复一些层的参数,所以我在这样的层中使用propagate\u down:0: layer { name: "conv5_2" type: "Eltwise" bottom: "conv5_1" bottom: "conv5_2_1x1_increase" top: "conv5_2" param{ propagate_down:0 } eltwise_param { operation: SUM } } 我想在这层之前修正参
propagate\u down:0
:
layer {
name: "conv5_2"
type: "Eltwise"
bottom: "conv5_1"
bottom: "conv5_2_1x1_increase"
top: "conv5_2"
param{
propagate_down:0
}
eltwise_param {
operation: SUM
}
}
我想在这层之前修正参数,在这层之后只微调参数
但我遇到了一个错误:
I0316 15:08:21.036813 20524 solver.cpp:81] Creating training net from train_net file: /home/muses/WSnet/C_coarse2fine/config/pspnet101_ele_8s_train.prototxt
[libprotobuf ERROR google/protobuf/text_format.cc:274] Error parsing text-format caffe.NetParameter: 6595:19: Interpreting non ascii codepoint 239.
[libprotobuf ERROR google/protobuf/text_format.cc:274] Error parsing text-format caffe.NetParameter: 6595:19: Message type "caffe.ParamSpec" has no field named "propagate_down".
F0316 15:08:21.039957 20524 upgrade_proto.cpp:88] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: /home/muses/WSnet/C_coarse2fine/config/pspnet101_ele_8s_train.prototxt
如何解决这个问题?该参数用于指示是否将渐变反投影到层的输入。它是非表示是否更新参数。要在caffe中修复参数,您需要为该特定参数设置
param{lr_mult:0}
。通常,当我需要修复某些层的权重时,而不是使用propagate_down
,我在这些层上设置lr_mult:0
。这将该特定层的学习率乘以0,这意味着权重根本不会更新。你试过了吗?