Chiebot-Mirror
/
opencv_contrib
8
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Add Crop layer. Add sample of using FCN32s network for semantic sementation

Browse Source
pull/750/head
vbystricky 9 years ago committed by Anna Petrovicheva
parent 99d1e44a29
commit 048c3fab26
9 changed files with 879 additions and 1 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 502
      modules/dnn/samples/fcn32s-heavy-pascal.prototxt
  2. 150
      modules/dnn/samples/fcn_semsegm.cpp
  3. 21
      modules/dnn/samples/pascal-classes.txt
  4. BIN
      modules/dnn/samples/rgb.jpg
  5. 21
      modules/dnn/src/caffe/caffe.proto
  6. BIN
      modules/dnn/src/caffe/compiled/caffe.tar.gz
  7. 3
      modules/dnn/src/init.cpp
  8. 120
      modules/dnn/src/layers/crop_layer.cpp
  9. 63
      modules/dnn/src/layers/crop_layer.hpp

502
modules/dnn/samples/fcn32s-heavy-pascal.prototxt
Unescape View File

@ -0,0 +1,502 @@
#
# This prototxt is based on voc-fcn32s/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-fcn32s"
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: "upscore"
type: "Deconvolution"
bottom: "score_fr"
top: "upscore"
param {
lr_mult: 0
}
convolution_param {
num_output: 21
bias_term: false
kernel_size: 64
stride: 32
}
}
layer {
name: "score"
type: "Crop"
bottom: "upscore"
bottom: "data"
top: "score"
crop_param {
axis: 2
offset: 19
}
}

150
modules/dnn/samples/fcn_semsegm.cpp
Unescape View File

@ -0,0 +1,150 @@
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
using namespace cv;
using namespace cv::dnn;
#include <fstream>
#include <iostream>
#include <cstdlib>
using namespace std;
static std::vector<cv::Vec3b> readColors(const string &filename = "d:/dnn_opencv/pascal-classes.txt")
{
std::vector<cv::Vec3b> colors;
std::ifstream fp(filename);
if (!fp.is_open())
{
std::cerr << "File with colors not found: " << filename << std::endl;
exit(-1);
}
std::string line;
while (!fp.eof())
{
std::getline(fp, line);
if (line.length())
{
std::stringstream ss(line);
std::string name; ss >> name;
int temp;
cv::Vec3b color;
ss >> temp; color[0] = temp;
ss >> temp; color[1] = temp;
ss >> temp; color[2] = temp;
colors.push_back(color);
}
}
fp.close();
return colors;
}
static void colorizeSegmentation(dnn::Blob &score, const std::vector<cv::Vec3b> &colors, cv::Mat &segm)
{
const int rows = score.rows();
const int cols = score.cols();
const int chns = score.channels();
cv::Mat maxCl(rows, cols, CV_8UC1);
cv::Mat maxVal(rows, cols, CV_32FC1);
for (int ch = 0; ch < chns; ch++)
{
for (int row = 0; row < rows; row++)
{
const float *ptrScore = score.ptrf(0, ch, row);
uchar *ptrMaxCl = maxCl.ptr<uchar>(row);
float *ptrMaxVal = maxVal.ptr<float>(row);
for (int col = 0; col < cols; col++)
{
if (ptrScore[col] > ptrMaxVal[col])
{
ptrMaxVal[col] = ptrScore[col];
ptrMaxCl[col] = ch;
}
}
}
}
segm.create(rows, cols, CV_8UC3);
for (int row = 0; row < rows; row++)
{
const uchar *ptrMaxCl = maxCl.ptr<uchar>(row);
cv::Vec3b *ptrSegm = segm.ptr<cv::Vec3b>(row);
for (int col = 0; col < cols; col++)
{
ptrSegm[col] = colors[ptrMaxCl[col]];
}
}
}
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";
std::vector<cv::Vec3b> colors = readColors();
//! [Create the importer of Caffe model]
Ptr<dnn::Importer> importer;
try //Try to import Caffe GoogleNet model
{
importer = dnn::createCaffeImporter(modelTxt, modelBin);
}
catch (const cv::Exception &err) //Importer can throw errors, we will catch them
{
std::cerr << err.msg << std::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;
exit(-1);
}
//! [Initialize network]
dnn::Net net;
importer->populateNet(net);
importer.release(); //We don't need importer anymore
//! [Initialize network]
//! [Prepare blob]
Mat img = imread(imageFile);
if (img.empty())
{
std::cerr << "Can't read image from the file: " << imageFile << std::endl;
exit(-1);
}
resize(img, img, Size(500, 500)); //FCN accepts 500x500 RGB-images
dnn::Blob inputBlob = dnn::Blob(img); //Convert Mat to dnn::Blob image batch
//! [Prepare blob]
//! [Set input blob]
net.setBlob(".data", inputBlob); //set the network input
//! [Set input blob]
//! [Make forward pass]
net.forward(); //compute output
//! [Make forward pass]
//! [Gather output]
dnn::Blob score = net.getBlob("score");
cv::Mat colorize;
colorizeSegmentation(score, colors, colorize);
cv::Mat show;
cv::addWeighted(img, 0.4, colorize, 0.6, 0.0, show);
cv::imshow("show", show);
cv::waitKey(0);
return 0;
} //main

21
modules/dnn/samples/pascal-classes.txt
Unescape View File

@ -0,0 +1,21 @@
background 0 0 0
aeroplane 128 0 0
bicycle 0 128 0
bird 128 128 0
boat 0 0 128
bottle 128 0 128
bus 0 128 128
car 128 128 128
cat 64 0 0
chair 192 0 0
cow 64 128 0
diningtable 192 128 0
dog 64 0 128
horse 192 0 128
motorbike 64 128 128
person 192 128 128
pottedplant 0 64 0
sheep 128 64 0
sofa 0 192 0
train 128 192 0
tvmonitor 0 64 128

BIN
modules/dnn/samples/rgb.jpg
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 46 KiB

21
modules/dnn/src/caffe/caffe.proto
Unescape View File

@ -73,6 +73,24 @@ message BlobProtoVector {
repeated BlobProto blobs = 1;
}
message CropParameter {
// To crop, elements of the first bottom are selected to fit the dimensions
// of the second, reference bottom. The crop is configured by
// - the crop `axis` to pick the dimensions for cropping
// - the crop `offset` to set the shift for all/each dimension
// to align the cropped bottom with the reference bottom.
// All dimensions up to but excluding `axis` are preserved, while
// the dimensions including and trailing `axis` are cropped.
// If only one `offset` is set, then all dimensions are offset by this amount.
// Otherwise, the number of offsets must equal the number of cropped axes to
// shift the crop in each dimension accordingly.
// Note: standard dimensions are N,C,H,W so the default is a spatial crop,
// and `axis` may be negative to index from the end (e.g., -1 for the last
// axis).
optional int32 axis = 1 [default = 2];
repeated uint32 offset = 2;
}
message Datum {
optional int32 channels = 1;
optional int32 height = 2;
@ -317,7 +335,7 @@ message ParamSpec {
// NOTE
// Update the next available ID when you add a new LayerParameter field.
//
// LayerParameter next available layer-specific ID: 137 (last added: reduction_param)
// LayerParameter next available layer-specific ID: 138 (last added: crop_param)
message LayerParameter {
optional string name = 1; // the layer name
optional string type = 2; // the layer type
@ -369,6 +387,7 @@ message LayerParameter {
optional ConcatParameter concat_param = 104;
optional ContrastiveLossParameter contrastive_loss_param = 105;
optional ConvolutionParameter convolution_param = 106;
optional CropParameter crop_param = 137;
optional DataParameter data_param = 107;
optional DropoutParameter dropout_param = 108;
optional DummyDataParameter dummy_data_param = 109;

BIN
modules/dnn/src/caffe/compiled/caffe.tar.gz
View File

Binary file not shown.

3
modules/dnn/src/init.cpp
Unescape View File

@ -53,6 +53,7 @@
#include "layers/slice_layer.hpp"
#include "layers/softmax_layer.hpp"
#include "layers/split_layer.hpp"
#include "layers/crop_layer.hpp"
namespace cv
{
@ -98,6 +99,8 @@ void initModule()
REG_RUNTIME_LAYER_CLASS(Deconvolution, DeConvolutionLayer)
REG_RUNTIME_LAYER_CLASS(Concat, ConcatLayer)
REG_RUNTIME_LAYER_CLASS(Crop, CropLayer)
init.status = true;
}

120
modules/dnn/src/layers/crop_layer.cpp
Unescape View File

@ -0,0 +1,120 @@
/*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 "crop_layer.hpp"
namespace cv
{
namespace dnn
{
CropLayer::CropLayer(LayerParams &params) : Layer(params)
{
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++)
{
offset[i] = paramOffset.get<int>(i);
}
}
else
{
const int offset_val = paramOffset.get<int>(0);
for (int i = start_axis; i < offset.size(); i++)
{
offset[i] = offset_val;
}
}
}
void CropLayer::allocate(const std::vector<Blob *> &inputs, std::vector<Blob> &outputs)
{
CV_Assert(2 == inputs.size());
const Blob &inpBlob = *inputs[0];
CV_Assert(inpBlob.dims() == 4 && inpBlob.type() == CV_32F);
const Blob &inpSzBlob = *inputs[1];
outSizes.resize(4, 0);
for (int i = 0; i < 4; i++)
{
if (i < start_axis)
outSizes[i] = inpBlob.size(i);
else
outSizes[i] = inpSzBlob.size(i);
if (offset[i] + outSizes[i] > inpBlob.size(i))
CV_Error(Error::StsBadArg, "invalid crop parameters");
}
outputs.resize(1);
outputs[0].create(BlobShape(outSizes));
}
void CropLayer::forward(std::vector<Blob *> &inputs, std::vector<Blob> &outputs)
{
Blob input = *inputs[0];
Blob output = outputs[0];
for (int num = 0; num < outSizes[0]; ++num)
{
for (int ch = 0; ch < outSizes[1]; ++ch)
{
for (int row = 0; row < outSizes[2]; ++row)
{
float *srcData = input.ptrf(num + offset[0], ch + offset[1], row + offset[2]);
float *dstData = output.ptrf(num, ch, row);
memcpy(dstData, srcData + offset[3], sizeof(float) * outSizes[3]);
}
}
}
}
}
}

63
modules/dnn/src/layers/crop_layer.hpp
Unescape View File

@ -0,0 +1,63 @@
/*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_CROP_LAYER_HPP__
#define __OPENCV_DNN_LAYERS_CROP_LAYER_HPP__
#include "../precomp.hpp"
namespace cv
{
namespace dnn
{
class CropLayer : public Layer
{
int start_axis;
std::vector<int> offset;
std::vector<int> outSizes;
public:
CropLayer(LayerParams& params);
void allocate(const std::vector<Blob*> &inputs, std::vector<Blob> &outputs);
void forward(std::vector<Blob*> &inputs, std::vector<Blob> &outputs);
};
}
}
#endif
Write Preview
Loading…
Cancel
Save