Skip to content

O
opencv_contrib
Commit 12c9b0ea authored by vbystricky's avatar vbystricky Committed by Anna Petrovicheva
Browse files
Options

Add Eltwise layer. Add case of FCN8s into sample for semantic segmentation

parent 048c3fab
Hide whitespace changes
Inline Side-by-side
Showing with 855 additions and 25 deletions
modules/dnn/samples/fcn8s-heavy-pascal.prototxt 0 → 100755
View file @ 12c9b0ea
#
# This prototxt is based on voc-fcn8s/val.prototxt file from
# https://github.com/shelhamer/fcn.berkeleyvision.org, which is distributed under
# Caffe (BSD) license:
# http://caffe.berkeleyvision.org/model_zoo.html#bvlc-model-license
#
name: "voc-fcn8s"
input: "data"
input_dim: 1
input_dim: 3
input_dim: 500
input_dim: 500
layer {
name: "conv1_1"
type: "Convolution"
bottom: "data"
top: "conv1_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
pad: 100
kernel_size: 3
stride: 1
}
}
layer {
name: "relu1_1"
type: "ReLU"
bottom: "conv1_1"
top: "conv1_1"
}
layer {
name: "conv1_2"
type: "Convolution"
bottom: "conv1_1"
top: "conv1_2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
stride: 1
}
}
layer {
name: "relu1_2"
type: "ReLU"
bottom: "conv1_2"
top: "conv1_2"
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1_2"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv2_1"
type: "Convolution"
bottom: "pool1"
top: "conv2_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 128
pad: 1
kernel_size: 3
stride: 1
}
}
layer {
name: "relu2_1"
type: "ReLU"
bottom: "conv2_1"
top: "conv2_1"
}
layer {
name: "conv2_2"
type: "Convolution"
bottom: "conv2_1"
top: "conv2_2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 128
pad: 1
kernel_size: 3
stride: 1
}
}
layer {
name: "relu2_2"
type: "ReLU"
bottom: "conv2_2"
top: "conv2_2"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2_2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv3_1"
type: "Convolution"
bottom: "pool2"
top: "conv3_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
stride: 1
}
}
layer {
name: "relu3_1"
type: "ReLU"
bottom: "conv3_1"
top: "conv3_1"
}
layer {
name: "conv3_2"
type: "Convolution"
bottom: "conv3_1"
top: "conv3_2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
stride: 1
}
}
layer {
name: "relu3_2"
type: "ReLU"
bottom: "conv3_2"
top: "conv3_2"
}
layer {
name: "conv3_3"
type: "Convolution"
bottom: "conv3_2"
top: "conv3_3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
stride: 1
}
}
layer {
name: "relu3_3"
type: "ReLU"
bottom: "conv3_3"
top: "conv3_3"
}
layer {
name: "pool3"
type: "Pooling"
bottom: "conv3_3"
top: "pool3"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv4_1"
type: "Convolution"
bottom: "pool3"
top: "conv4_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
stride: 1
}
}
layer {
name: "relu4_1"
type: "ReLU"
bottom: "conv4_1"
top: "conv4_1"
}
layer {
name: "conv4_2"
type: "Convolution"
bottom: "conv4_1"
top: "conv4_2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
stride: 1
}
}
layer {
name: "relu4_2"
type: "ReLU"
bottom: "conv4_2"
top: "conv4_2"
}
layer {
name: "conv4_3"
type: "Convolution"
bottom: "conv4_2"
top: "conv4_3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
stride: 1
}
}
layer {
name: "relu4_3"
type: "ReLU"
bottom: "conv4_3"
top: "conv4_3"
}
layer {
name: "pool4"
type: "Pooling"
bottom: "conv4_3"
top: "pool4"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "conv5_1"
type: "Convolution"
bottom: "pool4"
top: "conv5_1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
stride: 1
}
}
layer {
name: "relu5_1"
type: "ReLU"
bottom: "conv5_1"
top: "conv5_1"
}
layer {
name: "conv5_2"
type: "Convolution"
bottom: "conv5_1"
top: "conv5_2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
stride: 1
}
}
layer {
name: "relu5_2"
type: "ReLU"
bottom: "conv5_2"
top: "conv5_2"
}
layer {
name: "conv5_3"
type: "Convolution"
bottom: "conv5_2"
top: "conv5_3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 512
pad: 1
kernel_size: 3
stride: 1
}
}
layer {
name: "relu5_3"
type: "ReLU"
bottom: "conv5_3"
top: "conv5_3"
}
layer {
name: "pool5"
type: "Pooling"
bottom: "conv5_3"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer {
name: "fc6"
type: "Convolution"
bottom: "pool5"
top: "fc6"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 4096
pad: 0
kernel_size: 7
stride: 1
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "fc7"
type: "Convolution"
bottom: "fc6"
top: "fc7"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 4096
pad: 0
kernel_size: 1
stride: 1
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "score_fr"
type: "Convolution"
bottom: "fc7"
top: "score_fr"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 21
pad: 0
kernel_size: 1
}
}
layer {
name: "upscore2"
type: "Deconvolution"
bottom: "score_fr"
top: "upscore2"
param {
lr_mult: 0
}
convolution_param {
num_output: 21
bias_term: false
kernel_size: 4
stride: 2
}
}
layer {
name: "score_pool4"
type: "Convolution"
bottom: "pool4"
top: "score_pool4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 21
pad: 0
kernel_size: 1
}
}
layer {
name: "score_pool4c"
type: "Crop"
bottom: "score_pool4"
bottom: "upscore2"
top: "score_pool4c"
crop_param {
axis: 2
offset: 5
}
}
layer {
name: "fuse_pool4"
type: "Eltwise"
bottom: "upscore2"
bottom: "score_pool4c"
top: "fuse_pool4"
eltwise_param {
operation: SUM
}
}
layer {
name: "upscore_pool4"
type: "Deconvolution"
bottom: "fuse_pool4"
top: "upscore_pool4"
param {
lr_mult: 0
}
convolution_param {
num_output: 21
bias_term: false
kernel_size: 4
stride: 2
}
}
layer {
name: "score_pool3"
type: "Convolution"
bottom: "pool3"
top: "score_pool3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 21
pad: 0
kernel_size: 1
}
}
layer {
name: "score_pool3c"
type: "Crop"
bottom: "score_pool3"
bottom: "upscore_pool4"
top: "score_pool3c"
crop_param {
axis: 2
offset: 9
}
}
layer {
name: "fuse_pool3"
type: "Eltwise"
bottom: "upscore_pool4"
bottom: "score_pool3c"
top: "fuse_pool3"
eltwise_param {
operation: SUM
}
}
layer {
name: "upscore8"
type: "Deconvolution"
bottom: "fuse_pool3"
top: "upscore8"
param {
lr_mult: 0
}
convolution_param {
num_output: 21
bias_term: false
kernel_size: 16
stride: 8
}
}
layer {
name: "score"
type: "Crop"
bottom: "upscore8"
bottom: "data"
top: "score"
crop_param {
axis: 2
offset: 31
}
}
modules/dnn/samples/fcn_semsegm.cpp
View file @ 12c9b0ea
......@@ -9,26 +9,28 @@ using namespace cv::dnn;
#include <cstdlib>
using namespace std;
static std::vector<cv::Vec3b> readColors(const string &filename = "d:/dnn_opencv/pascal-classes.txt")
static const string fcnType = "fcn8s";
static vector<cv::Vec3b> readColors(const string &filename = "pascal-classes.txt")
{
std::vector<cv::Vec3b> colors;
vector<cv::Vec3b> colors;
std::ifstream fp(filename);
ifstream fp(filename.c_str());
if (!fp.is_open())
{
std::cerr << "File with colors not found: " << filename << std::endl;
cerr << "File with colors not found: " << filename << endl;
exit(-1);
}
std::string line;
string line;
while (!fp.eof())
{
std::getline(fp, line);
getline(fp, line);
if (line.length())
{
std::stringstream ss(line);
stringstream ss(line);
std::string name; ss >> name;
string name; ss >> name;
int temp;
cv::Vec3b color;
ss >> temp; color[0] = temp;
......@@ -42,7 +44,7 @@ static std::vector<cv::Vec3b> readColors(const string &filename = "d:/dnn_opencv
return colors;
}
static void colorizeSegmentation(dnn::Blob &score, const std::vector<cv::Vec3b> &colors, cv::Mat &segm)
static void colorizeSegmentation(dnn::Blob &score, const vector<cv::Vec3b> &colors, cv::Mat &segm)
{
const int rows = score.rows();
const int cols = score.cols();
......@@ -83,11 +85,11 @@ static void colorizeSegmentation(dnn::Blob &score, const std::vector<cv::Vec3b>
int main(int argc, char **argv)
{
String modelTxt = "d:/dnn_opencv/fcn32s-heavy-pascal.prototxt";
String modelBin = "d:/dnn_opencv/fcn32s-heavy-pascal.caffemodel";
String imageFile = (argc > 1) ? argv[1] : "d:/dnn_opencv/rgb.jpg";
String modelTxt = fcnType + "-heavy-pascal.prototxt";
String modelBin = fcnType + "-heavy-pascal.caffemodel";
String imageFile = (argc > 1) ? argv[1] : "rgb.jpg";
std::vector<cv::Vec3b> colors = readColors();
vector<cv::Vec3b> colors = readColors();
//! [Create the importer of Caffe model]
Ptr<dnn::Importer> importer;
......@@ -97,17 +99,17 @@ int main(int argc, char **argv)
}
catch (const cv::Exception &err) //Importer can throw errors, we will catch them
{
std::cerr << err.msg << std::endl;
cerr << err.msg << endl;
}
//! [Create the importer of Caffe model]
if (!importer)
{
std::cerr << "Can't load network by using the following files: " << std::endl;
std::cerr << "prototxt: " << modelTxt << std::endl;
std::cerr << "caffemodel: " << modelBin << std::endl;
std::cerr << "fcn32s-heavy-pascal.caffemodel can be downloaded here:" << std::endl;
std::cerr << "http://dl.caffe.berkeleyvision.org/fcn32s-heavy-pascal.caffemodel" << std::endl;
cerr << "Can't load network by using the following files: " << endl;
cerr << "prototxt: " << modelTxt << endl;
cerr << "caffemodel: " << modelBin << endl;
cerr << fcnType << "-heavy-pascal.caffemodel can be downloaded here:" << endl;
cerr << "http://dl.caffe.berkeleyvision.org/" << fcnType << "-heavy-pascal.caffemodel" << endl;
exit(-1);
}
......@@ -121,7 +123,7 @@ int main(int argc, char **argv)
Mat img = imread(imageFile);
if (img.empty())
{
std::cerr << "Can't read image from the file: " << imageFile << std::endl;
cerr << "Can't read image from the file: " << imageFile << endl;
exit(-1);
}
......
modules/dnn/src/init.cpp
View file @ 12c9b0ea
......@@ -54,6 +54,7 @@
#include "layers/softmax_layer.hpp"
#include "layers/split_layer.hpp"
#include "layers/crop_layer.hpp"
#include "layers/eltwise_layer.hpp"
namespace cv
{
......@@ -100,6 +101,7 @@ void initModule()
REG_RUNTIME_LAYER_CLASS(Concat, ConcatLayer)
REG_RUNTIME_LAYER_CLASS(Crop, CropLayer)
REG_RUNTIME_LAYER_CLASS(Eltwise, EltwiseLayer)
init.status = true;
}
......
modules/dnn/src/layers/crop_layer.cpp
View file @ 12c9b0ea
......@@ -52,15 +52,15 @@ namespace dnn
start_axis = params.get<int>("axis");
if (4 <= start_axis)
CV_Error(Error::StsBadArg, "crop axis bigger than input dim");
DictValue paramOffset = params.get("offset");
offset.resize(4, 0);
if (1 < paramOffset.size())
{
if (4 - start_axis != paramOffset.size())
CV_Error(Error::StsBadArg, "number of offset values specified must be equal to the number of dimensions following axis.");
for (int i = start_axis; i < offset.size(); i++)
for (size_t i = start_axis; i < offset.size(); i++)
{
offset[i] = paramOffset.get<int>(i);
}
......@@ -68,7 +68,7 @@ namespace dnn
else
{
const int offset_val = paramOffset.get<int>(0);
for (int i = start_axis; i < offset.size(); i++)
for (size_t i = start_axis; i < offset.size(); i++)
{
offset[i] = offset_val;
}
......@@ -81,7 +81,7 @@ namespace dnn
const Blob &inpBlob = *inputs[0];
CV_Assert(inpBlob.dims() == 4 && inpBlob.type() == CV_32F);
const Blob &inpSzBlob = *inputs[1];
outSizes.resize(4, 0);
......
modules/dnn/src/layers/eltwise_layer.cpp 0 → 100755
View file @ 12c9b0ea
/*M///////////////////////////////////////////////////////////////////////////////////////
//
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
//
// By downloading, copying, installing or using the software you agree to this license.
// If you do not agree to this license, do not download, install,
// copy or use the software.
//
//
// License Agreement
// For Open Source Computer Vision Library
//
// Copyright (C) 2013, OpenCV Foundation, all rights reserved.
// Third party copyrights are property of their respective owners.
//
// Redistribution and use in source and binary forms, with or without modification,
// are permitted provided that the following conditions are met:
//
// * Redistribution's of source code must retain the above copyright notice,
// this list of conditions and the following disclaimer.
//
// * Redistribution's in binary form must reproduce the above copyright notice,
// this list of conditions and the following disclaimer in the documentation
// and/or other materials provided with the distribution.
//
// * The name of the copyright holders may not be used to endorse or promote products
// derived from this software without specific prior written permission.
//
// This software is provided by the copyright holders and contributors "as is" and
// any express or implied warranties, including, but not limited to, the implied
// warranties of merchantability and fitness for a particular purpose are disclaimed.
// In no event shall the Intel Corporation or contributors be liable for any direct,
// indirect, incidental, special, exemplary, or consequential damages
// (including, but not limited to, procurement of substitute goods or services;
// loss of use, data, or profits; or business interruption) however caused
// and on any theory of liability, whether in contract, strict liability,
// or tort (including negligence or otherwise) arising in any way out of
// the use of this software, even if advised of the possibility of such damage.
//
//M*/
#include "../precomp.hpp"
#include "layers_common.hpp"
#include "eltwise_layer.hpp"
namespace cv
{
namespace dnn
{
EltwiseLayer::EltwiseLayer(LayerParams &params) : Layer(params)
{
if (params.has("operation"))
{
String operation = params.get<String>("operation").toLowerCase();
if (operation == "prod")
op = PROD;
else if (operation == "sum")
op = SUM;
else if (operation == "max")
op = MAX;
else
CV_Error(cv::Error::StsBadArg, "Unknown operaticon type \"" + operation + "\"");
}
else
{
op = SUM;
}
if (params.has("coeff"))
{
DictValue paramCoeff = params.get("coeff");
coeffs.resize(paramCoeff.size(), 1);
for (int i = 0; i < paramCoeff.size(); i++)
{
coeffs[i] = paramCoeff.get<int>(i);
}
}
}
void EltwiseLayer::allocate(const std::vector<Blob *> &inputs, std::vector<Blob> &outputs)
{
CV_Assert(2 <= inputs.size());
CV_Assert(coeffs.size() == 0 || coeffs.size() == inputs.size());
CV_Assert(op == SUM || coeffs.size() == 0);
const BlobShape &shape0 = inputs[0]->shape();
for (size_t i = 1; i < inputs.size(); ++i)
{
CV_Assert(shape0 == inputs[i]->shape());
}
outputs.resize(1);
outputs[0].create(shape0);
}
void EltwiseLayer::forward(std::vector<Blob *> &inputs, std::vector<Blob> &outputs)
{
switch (op)
{
case SUM:
{
CV_Assert(coeffs.size() == 0 || coeffs.size() == inputs.size());
Mat& output = outputs[0].matRef();
output.setTo(0.);
if (0 < coeffs.size())
{
for (size_t i = 0; i < inputs.size(); i++)
{
output += inputs[i]->matRefConst() * coeffs[i];
}
}
else
{
for (size_t i = 0; i < inputs.size(); i++)
{
output += inputs[i]->matRefConst();
}
}
}
break;
case PROD:
{
Mat& output = outputs[0].matRef();
output.setTo(1.);
for (size_t i = 0; i < inputs.size(); i++)
{
output = output.mul(inputs[i]->matRefConst());
}
}
break;
case MAX:
{
Mat& output = outputs[0].matRef();
cv::max(inputs[0]->matRefConst(), inputs[1]->matRefConst(), output);
for (size_t i = 2; i < inputs.size(); i++)
{
cv::max(output, inputs[i]->matRefConst(), output);
}
}
break;
default:
CV_Assert(0);
break;
};
}
}
}
modules/dnn/src/layers/eltwise_layer.hpp 0 → 100755
View file @ 12c9b0ea
/*M///////////////////////////////////////////////////////////////////////////////////////
//
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
//
// By downloading, copying, installing or using the software you agree to this license.
// If you do not agree to this license, do not download, install,
// copy or use the software.
//
//
// License Agreement
// For Open Source Computer Vision Library
//
// Copyright (C) 2013, OpenCV Foundation, all rights reserved.
// Third party copyrights are property of their respective owners.
//
// Redistribution and use in source and binary forms, with or without modification,
// are permitted provided that the following conditions are met:
//
// * Redistribution's of source code must retain the above copyright notice,
// this list of conditions and the following disclaimer.
//
// * Redistribution's in binary form must reproduce the above copyright notice,
// this list of conditions and the following disclaimer in the documentation
// and/or other materials provided with the distribution.
//
// * The name of the copyright holders may not be used to endorse or promote products
// derived from this software without specific prior written permission.
//
// This software is provided by the copyright holders and contributors "as is" and
// any express or implied warranties, including, but not limited to, the implied
// warranties of merchantability and fitness for a particular purpose are disclaimed.
// In no event shall the Intel Corporation or contributors be liable for any direct,
// indirect, incidental, special, exemplary, or consequential damages
// (including, but not limited to, procurement of substitute goods or services;
// loss of use, data, or profits; or business interruption) however caused
// and on any theory of liability, whether in contract, strict liability,
// or tort (including negligence or otherwise) arising in any way out of
// the use of this software, even if advised of the possibility of such damage.
//
//M*/
#ifndef __OPENCV_DNN_LAYERS_ELTWISE_LAYER_HPP__
#define __OPENCV_DNN_LAYERS_ELTWISE_LAYER_HPP__
#include "../precomp.hpp"
namespace cv
{
namespace dnn
{
class EltwiseLayer : public Layer
{
enum EltwiseOp
{
PROD = 0,
SUM = 1,
MAX = 2,
};
EltwiseOp op;
std::vector<int> coeffs;
public:
EltwiseLayer(LayerParams& params);
void allocate(const std::vector<Blob*> &inputs, std::vector<Blob> &outputs);
void forward(std::vector<Blob*> &inputs, std::vector<Blob> &outputs);
};
}
}
#endif
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment