Deep learning 在[base\u conv\u layer.cpp:122]检查中获取错误失败:通道\u%group\u==0(1对0),如何解决?

Deep learning 在[base\u conv\u layer.cpp:122]检查中获取错误失败:通道\u%group\u==0(1对0),如何解决?,deep-learning,caffe,convolution,pycaffe,matcaffe,Deep Learning,Caffe,Convolution,Pycaffe,Matcaffe,当我尝试对自己的数据进行FCN32培训时,我遇到以下错误: I0106 12:57:53.273977 19825 net.cpp:100] Creating Layer upscore_sign I0106 12:57:53.273982 19825 net.cpp:434] upscore_sign <- score_fr_sign I0106 12:57:53.274001 19825 net.cpp:408] upscore_sign -> upsc

当我尝试对自己的数据进行
FCN32
培训时,我遇到以下错误:

    I0106 12:57:53.273977 19825 net.cpp:100] Creating Layer upscore_sign 
    I0106 12:57:53.273982 19825 net.cpp:434] upscore_sign <- score_fr_sign
    I0106 12:57:53.274001 19825 net.cpp:408] upscore_sign -> upscore_sign
    F0106 12:57:53.274119 19825 base_conv_layer.cpp:122] Check failed: channels_ % group_ == 0 (1 vs. 0) 
    *** Check failure stack trace: ***
        @     0x7f2602e525cd  google::LogMessage::Fail()
        @     0x7f2602e54433  google::LogMessage::SendToLog()
        @     0x7f2602e5215b  google::LogMessage::Flush()
        @     0x7f2602e54e1e  google::LogMessageFatal::~LogMessageFatal()
        @     0x7f260350701b  caffe::BaseConvolutionLayer<>::LayerSetUp()
        @     0x7f26033ee557  caffe::Net<>::Init()
        @     0x7f26033efde1  caffe::Net<>::Net()
        @     0x7f26033c5d4a  caffe::Solver<>::InitTrainNet()
        @     0x7f26033c7157  caffe::Solver<>::Init()
        @     0x7f26033c74fa  caffe::Solver<>::Solver()
        @     0x7f2603400353  caffe::Creator_SGDSolver<>()
        @           0x40c07a  train()
        @           0x408748  main
        @     0x7f26014f3830  __libc_start_main
        @           0x409019  _start
        @              (nil)  (unknown)
我将输出的数量从60更改为5(基于数据中的类的数量):
convolution\u param{num\u output:5}

有人能对此提出任何解决方案或想法吗?我设置/更改了什么错误?我的错在哪里


感谢您的帮助。

检查失败:频道组=0(1对0)
这句话真的很重要!您应该检查您的num_输出和组,并确定频道是否为0。

非常感谢您的帮助
net: "train_val.prototxt"
#test_net: "val.prototxt"
test_iter: 200 #3000 #5105
# make test net, but don't invoke it from the solver itself
test_interval: 1000
display: 20
average_loss: 20
lr_policy: "step" #"fixed"
# lr for unnormalized softmax
base_lr: 1e-10
# high momentum
momentum: 0.99
# no gradient accumulation
iter_size: 1
max_iter: 300000
weight_decay: 0.0005
snapshot: 2000 #10000
snapshot_prefix: "snapshot/FCN32s_train"
test_initialization: false
solver_mode: GPU   #+