Error compiling network

idata — Wed, 13 Dec 2017 15:59:46 GMT

Hi,

I'm trying to convert a Caffe network with AbsVal layer but getting an error.

Network git at: https://github.com/guozhongluo/head-pose-estimation-and-face-landmark

Can someone please advice ?

Thanks,

Tsahi.

Re: Error compiling network

idata — Fri, 15 Dec 2017 18:19:12 GMT

@tsahim I can't see AbsVal layer in this project as well as weight (.caffemodel file). Please explain how do you manage to convert this network for NCS so we can triage the problem.

Re: Error compiling network

idata — Wed, 20 Dec 2017 23:47:46 GMT

Wrong link sorry,

this is the library at: https://github.com/jiangwqcooler/face-landmark

and this is the orig proto.txt (before shape mod ):

input: "data"

input_dim: 1

input_dim: 60

the actual net

layer 1

layer {

type: "Convolution"

bottom: "data"

top: "Conv1"

param {

lr_mult: 1

decay_mult: 1

}

param {

lr_mult: 2

decay_mult: 0

}

convolution_param {

num_output: 20

pad: 2

kernel_size: 5

stride: 1

weight_filler {

type: "xavier"

std: 0.1

}

bias_filler {

type: "constant"

value: 0.2

}

layer {

bottom: "Conv1"

top: "ActivationTangH1"

type: "TanH"

}

layer {

bottom: "ActivationTangH1"

top: "Abs1"

type: "AbsVal"

}

layer {

type: "Pooling"

bottom: "Abs1"

top: "Pool1"

pooling_param {

pool: MAX

kernel_size: 2

stride: 2

}

layer {

type: "Convolution"

bottom: "Pool1"

top: "Conv2"

param {

lr_mult: 1

decay_mult: 1

}

param {

lr_mult: 2

decay_mult: 0

}

convolution_param {

num_output: 48

pad: 2

kernel_size: 5

stride: 1

weight_filler {

type: "xavier"

std: 0.1

}

bias_filler {

type: "constant"

value: 0.2

}

layer {

bottom: "Conv2"

top: "ActivationTangH2"

type: "TanH"

}

layer {

bottom: "ActivationTangH2"

top: "Abs2"

type: "AbsVal"

}

layer {

type: "Pooling"

bottom: "Abs2"

top: "Pool2"

pooling_param {

pool: MAX

kernel_size: 2

stride: 2

}

layer 3

layer {

type: "Convolution"

bottom: "Pool2"

top: "Conv3"

param {

lr_mult: 1

decay_mult: 1

}

param {

lr_mult: 2

decay_mult: 0

}

convolution_param {

num_output: 64

pad: 0

kernel_size: 3

stride: 1

weight_filler {

type: "xavier"

std: 0.1

}

bias_filler {

type: "constant"

value: 0.2

}

layer {

bottom: "Conv3"

top: "ActivationTangH3"

type: "TanH"

}

layer {

bottom: "ActivationTangH3"

top: "Abs3"

type: "AbsVal"

}

layer {

type: "Pooling"

bottom: "Abs3"

top: "Pool3"

pooling_param {

pool: MAX

kernel_size: 3

stride: 2

}

layer 4

layer {

type: "Convolution"

bottom: "Pool3"

top: "Conv4"

param {

lr_mult: 1

decay_mult: 1

}

param {

lr_mult: 2

decay_mult: 0

}

convolution_param {

num_output: 80

pad: 0

kernel_size: 3

stride: 1

weight_filler {

type: "xavier"

std: 0.1

}

bias_filler {

type: "constant"

value: 0.2

}

layer {

bottom: "Conv4"

top: "ActivationTangH4"

type: "TanH"

}

layer {

bottom: "ActivationTangH4"

top: "Abs4"

type: "AbsVal"

}

layer {

type: "InnerProduct"

bottom: "Abs4"

top: "Dense1"

param {

lr_mult: 1

decay_mult: 1

}

param {

lr_mult: 2

decay_mult: 0

}

inner_product_param {

num_output: 512

weight_filler {

type: "xavier"

}

bias_filler {

type: "constant"

value: 0

}

layer {

bottom: "Dense1"

top: "ActivationTangH5"

type: "TanH"

}

layer {

bottom: "ActivationTangH5"

top: "Abs5"

type: "AbsVal"

}

layer {

type: "InnerProduct"

bottom: "Abs5"

top: "Dense3"

param {

lr_mult: 1

decay_mult: 1

}

param {

lr_mult: 2

decay_mult: 0

}

inner_product_param {

num_output: 136

weight_filler {

type: "xavier"

}

bias_filler {

type: "constant"

value: 0

}

Re: Error compiling network

idata — Fri, 22 Dec 2017 06:45:16 GMT

@tsahim I believe that we may not yet support the Absolute Value layer. Can you post the error that you are receiving?

topic Re: Error compiling network in Intel® Distribution of OpenVINO™ Toolkit

Error compiling network

Re: Error compiling network

Re: Error compiling network

Re: Error compiling network