VSAG/amadeus_26_fb
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

重新整理文件夹结构，并添加CNN训练代码。

Browse Source
This commit is contained in:
xinyang
2019-04-25 12:39:38 +08:00
parent 5c7317140a
commit ecbee8b24c
25 changed files with 325 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
armor/include/armor_finder/classifier/classifier.h
View File

@@ -32,7 +32,8 @@ private:
MatrixXd relu(const MatrixXd &input);
vector<vector<MatrixXd>> apply_bias(const vector<vector<MatrixXd>> &input, const vector<double> &bias);
vector<vector<MatrixXd>> relu(const vector<vector<MatrixXd>> &input);
vector<vector<MatrixXd>> pool(const vector<vector<MatrixXd>> &input, int size);
vector<vector<MatrixXd>> max_pool(const vector<vector<MatrixXd>> &input, int size);
vector<vector<MatrixXd>> mean_pool(const vector<vector<MatrixXd>> &input, int size);
vector<vector<MatrixXd>> pand(const vector<vector<MatrixXd>> &input, int val);
MatrixXd conv(const MatrixXd &filter, const MatrixXd &input);
vector<vector<MatrixXd>> conv2(const vector<vector<MatrixXd>> &filter, const vector<vector<MatrixXd>> &input);

35
armor/src/armor_finder/classifier/classifier.cpp
View File

@@ -2,6 +2,7 @@
// Created by xinyang on 19-4-19.
//
//#define LOG_LEVEL LOG_NONE
#include <armor_finder/classifier/classifier.h>
#include <log.h>
#include <cstdio>
@@ -91,7 +92,33 @@ MatrixXd Classifier::softmax(const MatrixXd &input){
return tmp.array().exp() / tmp.array().exp().sum();
}
vector<vector<MatrixXd>> Classifier::pool(const vector<vector<MatrixXd>> &input, int size){
vector<vector<MatrixXd>> max_pool(const vector<vector<MatrixXd>> &input, int size){
vector<vector<MatrixXd>> output;
for(int sample=0; sample<input.size(); sample++) {
vector<MatrixXd> sub;
for (int channel = 0; channel < input[0].size(); channel++) {
MatrixXd tmp(input[0][0].rows() / size, input[0][0].cols() / size);
for (int row = 0; row < input[0][0].rows() / size; row++) {
for (int col = 0; col < input[0][0].cols() / size; col++) {
double max = 0;
for (int x = 0; x < size; x++) {
for (int y = 0; y < size; y++) {
if(max < input[sample][channel](row * size + x, col * size + y)){
max = input[sample][channel](row * size + x, col * size + y);
}
}
}
tmp(row, col) = max;
}
}
sub.emplace_back(tmp);
}
output.emplace_back(sub);
}
return output;
}
vector<vector<MatrixXd>> Classifier::mean_pool(const vector<vector<MatrixXd>> &input, int size){
vector<vector<MatrixXd>> output;
for(int sample=0; sample<input.size(); sample++) {
vector<MatrixXd> sub;
@@ -240,9 +267,9 @@ Classifier::Classifier(const string &folder) : state(true){
MatrixXd Classifier::calculate(const vector<vector<MatrixXd>> &input) {
vector<vector<MatrixXd>> conv1_result = relu(apply_bias(conv2(conv1_w, input), conv1_b));
vector<vector<MatrixXd>> pool1_result = pool(conv1_result, 2);
vector<vector<MatrixXd>> pool1_result = mean_pool(conv1_result, 2);
vector<vector<MatrixXd>> conv2_result = relu(apply_bias(conv2(conv2_w, pool1_result), conv2_b));
vector<vector<MatrixXd>> pool2_result = pool(conv2_result, 2);
vector<vector<MatrixXd>> pool2_result = mean_pool(conv2_result, 2);
MatrixXd flattened = flatten(pool2_result);
MatrixXd y1 = fc1_w * flattened;
y1.colwise() += fc1_b;
@@ -260,7 +287,7 @@ Classifier::operator bool() const {
int Classifier::operator()(const cv::Mat &image) {
MatrixXd x;
cv2eigen(image, x);
x /= 255;
x /= 255.0;
vector<MatrixXd> sub = {x};
vector<vector<MatrixXd>> in = {sub};
MatrixXd result = calculate(in);