Forums - UDL tutorial produced an error message

Hi all,

I encountered a problem when converting caffemodel to dlc using the example provided by UDL tutorial.

F1120 20:23:22.949683 13044 layer_factory.hpp:81] Check failed: registry.count(type) == 1 (0 vs. 1) Unknown layer type: MyCustomScale (known types: AbsVal, Accuracy, ArgMax, BNLL, BatchNorm, BatchReindex, Bias, Concat, ContrastiveLoss, Convolution, Crop, Data, Deconvolution, Dropout, DummyData, ELU, Eltwise, Embed, EuclideanLoss, Exp, Filter, Flatten, HDF5Data, HDF5Output, HingeLoss, Im2col, ImageData, InfogainLoss, InnerProduct, Input, LRN, LSTM, LSTMUnit, Log, MVN, MemoryData, MultinomialLogisticLoss, PReLU, Parameter, Pooling, Power, Python, RNN, ReLU, Reduction, Reshape, SPP, Scale, Sigmoid, SigmoidCrossEntropyLoss, Silence, Slice, Softmax, SoftmaxWithLoss, Split, TanH, Threshold, Tile, WindowData)
*** Check failure stack trace: ***
Aborted (core dumped)

The message above appearred after I typed in the following commands:

:~/snpe-1.6.0/examples/Python/UdlExample$ python snpe-caffe-to-dlc-udl  --caffe_txt $CAFFE_HOME/examples/mnist/mycustomlenet.prototxt --caffe_bin $CAFFE_HOME/examples/mnist/mycustomlenet_iter_10000.caffemodel --dlc mycustomlenet.dlc

Does anyone have any thoughts on how to correct this issue?

Thanks,

A complete output log:

-----------------------------------------------------------------------------------------------------------

WARNING: Logging before InitGoogleLogging() is written to STDERR
W1120 20:23:22.592881 13044 _caffe.cpp:139] DEPRECATION WARNING - deprecated use of Python interface
W1120 20:23:22.592921 13044 _caffe.cpp:140] Use this instead (with the named "weights" parameter):
W1120 20:23:22.592923 13044 _caffe.cpp:142] Net('/home/yihangrd/caffe/examples/mnist/mycustomlenet.prototxt', 1, weights='/home/yihangrd/caffe/examples/mnist/mycustomlenet_iter_10000.caffemodel')
I1120 20:23:22.594035 13044 net.cpp:51] Initializing net from parameters:
name: "LeNet"
state {
  phase: TEST
  level: 0
}
layer {
  name: "data"
  type: "Input"
  top: "data"
  input_param {
    shape {
      dim: 64
      dim: 1
      dim: 28
      dim: 28
    }
  }
}
layer {
  name: "conv1"
  type: "Convolution"
  bottom: "data"
  top: "conv1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 20
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv2"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 50
    kernel_size: 5
    stride: 1
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "ip1"
  type: "InnerProduct"
  bottom: "pool2"
  top: "ip1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 500
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "relu1"
  type: "ReLU"
  bottom: "ip1"
  top: "ip1"
}
layer {
  name: "scale"
  type: "MyCustomScale"
  bottom: "ip1"
  top: "scale"
  scale_param {
    bias_term: false
  }
}
layer {
  name: "ip2"
  type: "InnerProduct"
  bottom: "scale"
  top: "ip2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 10
    weight_filler {
      type: "xavier"
    }
    bias_filler {
      type: "constant"
    }
  }
}
layer {
  name: "prob"
  type: "Softmax"
  bottom: "ip2"
  top: "prob"
}
I1120 20:23:22.594142 13044 layer_factory.hpp:77] Creating layer data
I1120 20:23:22.594148 13044 net.cpp:84] Creating Layer data
I1120 20:23:22.594166 13044 net.cpp:380] data -> data
I1120 20:23:22.594178 13044 net.cpp:122] Setting up data
I1120 20:23:22.594185 13044 net.cpp:129] Top shape: 64 1 28 28 (50176)
I1120 20:23:22.594188 13044 net.cpp:137] Memory required for data: 200704
I1120 20:23:22.594203 13044 layer_factory.hpp:77] Creating layer conv1
I1120 20:23:22.594209 13044 net.cpp:84] Creating Layer conv1
I1120 20:23:22.594225 13044 net.cpp:406] conv1 <- data
I1120 20:23:22.594229 13044 net.cpp:380] conv1 -> conv1
I1120 20:23:22.947041 13044 net.cpp:122] Setting up conv1
I1120 20:23:22.947059 13044 net.cpp:129] Top shape: 64 20 24 24 (737280)
I1120 20:23:22.947062 13044 net.cpp:137] Memory required for data: 3149824
I1120 20:23:22.947077 13044 layer_factory.hpp:77] Creating layer pool1
I1120 20:23:22.947087 13044 net.cpp:84] Creating Layer pool1
I1120 20:23:22.947089 13044 net.cpp:406] pool1 <- conv1
I1120 20:23:22.947093 13044 net.cpp:380] pool1 -> pool1
I1120 20:23:22.947103 13044 net.cpp:122] Setting up pool1
I1120 20:23:22.947106 13044 net.cpp:129] Top shape: 64 20 12 12 (184320)
I1120 20:23:22.947108 13044 net.cpp:137] Memory required for data: 3887104
I1120 20:23:22.947110 13044 layer_factory.hpp:77] Creating layer conv2
I1120 20:23:22.947118 13044 net.cpp:84] Creating Layer conv2
I1120 20:23:22.947121 13044 net.cpp:406] conv2 <- pool1
I1120 20:23:22.947124 13044 net.cpp:380] conv2 -> conv2
I1120 20:23:22.947962 13044 net.cpp:122] Setting up conv2
I1120 20:23:22.947973 13044 net.cpp:129] Top shape: 64 50 8 8 (204800)
I1120 20:23:22.947975 13044 net.cpp:137] Memory required for data: 4706304
I1120 20:23:22.947983 13044 layer_factory.hpp:77] Creating layer pool2
I1120 20:23:22.947988 13044 net.cpp:84] Creating Layer pool2
I1120 20:23:22.947991 13044 net.cpp:406] pool2 <- conv2
I1120 20:23:22.947995 13044 net.cpp:380] pool2 -> pool2
I1120 20:23:22.948002 13044 net.cpp:122] Setting up pool2
I1120 20:23:22.948006 13044 net.cpp:129] Top shape: 64 50 4 4 (51200)
I1120 20:23:22.948009 13044 net.cpp:137] Memory required for data: 4911104
I1120 20:23:22.948011 13044 layer_factory.hpp:77] Creating layer ip1
I1120 20:23:22.948016 13044 net.cpp:84] Creating Layer ip1
I1120 20:23:22.948019 13044 net.cpp:406] ip1 <- pool2
I1120 20:23:22.948022 13044 net.cpp:380] ip1 -> ip1
I1120 20:23:22.949455 13044 net.cpp:122] Setting up ip1
I1120 20:23:22.949463 13044 net.cpp:129] Top shape: 64 500 (32000)
I1120 20:23:22.949466 13044 net.cpp:137] Memory required for data: 5039104
I1120 20:23:22.949473 13044 layer_factory.hpp:77] Creating layer relu1
I1120 20:23:22.949478 13044 net.cpp:84] Creating Layer relu1
I1120 20:23:22.949481 13044 net.cpp:406] relu1 <- ip1
I1120 20:23:22.949484 13044 net.cpp:367] relu1 -> ip1 (in-place)
I1120 20:23:22.949654 13044 net.cpp:122] Setting up relu1
I1120 20:23:22.949661 13044 net.cpp:129] Top shape: 64 500 (32000)
I1120 20:23:22.949662 13044 net.cpp:137] Memory required for data: 5167104
I1120 20:23:22.949666 13044 layer_factory.hpp:77] Creating layer scale
F1120 20:23:22.949683 13044 layer_factory.hpp:81] Check failed: registry.count(type) == 1 (0 vs. 1) Unknown layer type: MyCustomScale (known types: AbsVal, Accuracy, ArgMax, BNLL, BatchNorm, BatchReindex, Bias, Concat, ContrastiveLoss, Convolution, Crop, Data, Deconvolution, Dropout, DummyData, ELU, Eltwise, Embed, EuclideanLoss, Exp, Filter, Flatten, HDF5Data, HDF5Output, HingeLoss, Im2col, ImageData, InfogainLoss, InnerProduct, Input, LRN, LSTM, LSTMUnit, Log, MVN, MemoryData, MultinomialLogisticLoss, PReLU, Parameter, Pooling, Power, Python, RNN, ReLU, Reduction, Reshape, SPP, Scale, Sigmoid, SigmoidCrossEntropyLoss, Silence, Slice, Softmax, SoftmaxWithLoss, Split, TanH, Threshold, Tile, WindowData)
*** Check failure stack trace: ***
Aborted (core dumped)