使用旧版候选区寻找方式。

armor/include/show_images/show_images.h

@@ -13,8 +13,7 @@
 void showArmorBoxVector(std::string windows_name, const cv::Mat &src, const std::vector<cv::Rect2d> &armor_box);
 void showArmorBox(std::string windows_name, const cv::Mat &src, cv::Rect2d armor_box);
 void showContours(std::string windows_name, const cv::Mat &src, const std::vector<LightBlob> &light_blobs);
-void showArmorBoxClass(std::string window_names, const cv::Mat &src, vector<cv::Rect2d> boxes_one,
+void showArmorBoxClass(std::string window_names, const cv::Mat &src, vector<cv::Rect2d> boxes[10]);
-                       vector<cv::Rect2d> boxes_two, vector<cv::Rect2d> boxes_three);
 
 
 #endif /* _SHOW_IMAGES_H_ */

armor/src/armor_finder/armor_finder.cpp

@@ -1,6 +1,7 @@
 //
 // Created by xinyang on 19-3-27.
 //
+#define LOG_LEVEL LOG_NONE
 #include <log.h>
 #include <options/options.h>
 #include <show_images/show_images.h>
@@ -40,14 +41,14 @@ void ArmorFinder::run(cv::Mat &src) {
                     tracker = TrackerToUse::create();
                     tracker->init(src_use, armor_box);
                     state = TRACKING_STATE;
-                    LOGW("into track");
+                    LOGM(STR_CTR(WORD_LIGHT_CYAN, "into track"));
                 }
             }
             break;
         case TRACKING_STATE:
             if(!stateTrackingTarget(src_use)){
                 state = SEARCHING_STATE;
-                //std::cout << "into search!" << std::endl;
+                LOGM(STR_CTR(WORD_LIGHT_YELLOW ,"into search!"));
             }
             break;
         case STANDBY_STATE:
@@ -59,11 +60,14 @@ void ArmorFinder::run(cv::Mat &src) {
 #define FOCUS_PIXAL      (0.36/0.48*640)
 
 bool ArmorFinder::sendBoxPosition() {
+    static int dx_add = 0;
     auto rect = armor_box;
-    double dx = rect.x + rect.width/2 - 320;
+    double dx = rect.x + rect.width/2 - 320 - 8;
-    double dy = rect.y + rect.height/2 - 240;
+    dx_add += dx;
+    dx = dx + dx_add * 0;
+    double dy = rect.y + rect.height/2 - 240 - 30;
     double yaw   = atan(dx / FOCUS_PIXAL) * 180 / 3.14159265459;
     double pitch = atan(dy / FOCUS_PIXAL) * 180 / 3.14159265459;
-    uart.sendTarget(yaw, pitch, 0);
+    uart.sendTarget(yaw, -pitch, 0);
     return true;
 }

armor/src/armor_finder/classifier/classifier.cpp

@@ -92,7 +92,7 @@ MatrixXd Classifier::softmax(const MatrixXd &input){
     return tmp.array().exp() / tmp.array().exp().sum();
 }
 
-vector<vector<MatrixXd>> max_pool(const vector<vector<MatrixXd>> &input, int size){
+vector<vector<MatrixXd>> Classifier::max_pool(const vector<vector<MatrixXd>> &input, int size){
     vector<vector<MatrixXd>> output;
     for(int sample=0; sample<input.size(); sample++) {
         vector<MatrixXd> sub;

armor/src/armor_finder/state_machine/searching_state/searching_state.cpp

@@ -31,10 +31,15 @@ static void pipelineLightBlobPreprocess(cv::Mat &src) {
 }
 
 static bool findLightBlobs(const cv::Mat &src, LightBlobs &light_blobs) {
-//    static cv::Mat src_bin;
+    static cv::Mat src_gray, src_bin;
+    if(src.type() == CV_8UC3){
+        cvtColor(src, src_gray, CV_BGR2GRAY);
+    }else if(src.type() == CV_8UC1){
+        src_gray = src.clone();
+    }
 
     std::vector<std::vector<cv::Point> > light_contours;
-    cv::findContours(src, light_contours, CV_RETR_EXTERNAL, CV_CHAIN_APPROX_NONE);
+    cv::findContours(src_gray, light_contours, CV_RETR_EXTERNAL, CV_CHAIN_APPROX_NONE);
     for (auto &light_contour : light_contours) {
         cv::RotatedRect rect = cv::minAreaRect(light_contour);
         if(isValidLightBlob(rect)){
@@ -114,8 +119,8 @@ static bool findArmorBoxes(LightBlobs &light_blobs, std::vector<cv::Rect2d> &arm
             double min_x, min_y, max_x, max_y;
             min_x = fmin(rect_left.x, rect_right.x);
             max_x = fmax(rect_left.x + rect_left.width, rect_right.x + rect_right.width);
-            min_y = fmin(rect_left.y, rect_right.y) - 5;
+            min_y = fmin(rect_left.y, rect_right.y) - 3;
-            max_y = fmax(rect_left.y + rect_left.height, rect_right.y + rect_right.height);
+            max_y = fmax(rect_left.y + rect_left.height, rect_right.y + rect_right.height) + 3;
             if (min_x < 0 || max_x > 640 || min_y < 0 || max_y > 480) {
                 continue;
             }
@@ -147,31 +152,42 @@ bool judge_light_color(std::vector<LightBlob> &light, std::vector<LightBlob> &co
 }
 
 bool ArmorFinder::stateSearchingTarget(cv::Mat &src) {
-    cv::Mat split, pmsrc=src.clone(), src_bin;
+    cv::Mat split, src_bin;
-    LightBlobs light_blobs, pm_light_blobs, light_blobs_real;
+    LightBlobs light_blobs, light_blobs_, light_blobs_real;
-    std::vector<cv::Rect2d> armor_boxes, boxes_one, boxes_two, boxes_three;
+    std::vector<cv::Rect2d> armor_boxes, boxes_number[9];
+    armor_box = cv::Rect2d(0,0,0,0);
 
-//    cv::resize(src, pmsrc, cv::Size(320, 240));
+    cv::cvtColor(src, src_gray, CV_BGR2GRAY);
-    imageColorSplit(src, split, enemy_color);
+//    pipelineLightBlobPreprocess(src_gray);
-    cv::threshold(split, src_bin, 130, 255, CV_THRESH_BINARY);
+    cv::threshold(src_gray, src_bin, 120, 255, CV_THRESH_BINARY);
-    imagePreProcess(src_bin);
-//    cv::imshow("bin", src_bin);
-//    cv::resize(split, split, cv::Size(640, 480));
-//    pipelineLightBlobPreprocess(pmsrc);
-//    if(!findLightBlobs(pmsrc, pm_light_blobs)){
-//        return false;
-//    }
     if(!findLightBlobs(src_bin, light_blobs)){
         return false;
     }
-//    if(!judge_light_color(light_blobs, pm_light_blobs, light_blobs_real)){
-//        return false;
-//    }
     if(show_light_blobs){
-        showContours("blobs", split, light_blobs);
+        showContours("blobs", src_bin, light_blobs);
         cv::waitKey(1);
     }
-    if(!findArmorBoxes(light_blobs, armor_boxes)){
+
+    imageColorSplit(src, split, enemy_color);
+    imagePreProcess(split);
+    cv::threshold(split, src_bin, 120, 255, CV_THRESH_BINARY);
+    if(!findLightBlobs(src_bin, light_blobs_)){
+        return false;
+    }
+    if(show_light_blobs){
+        showContours("blobs_", src_bin, light_blobs_);
+        cv::waitKey(1);
+    }
+
+    if(!judge_light_color(light_blobs, light_blobs_, light_blobs_real)){
+        return false;
+    }
+    if(show_light_blobs){
+        showContours("blobs_real", src, light_blobs_real);
+        cv::waitKey(1);
+    }
+
+    if(!findArmorBoxes(light_blobs_real, armor_boxes)){
         return false;
     }
     if(show_armor_boxes){
@@ -183,29 +199,21 @@ bool ArmorFinder::stateSearchingTarget(cv::Mat &src) {
             cv::Mat roi = src(box).clone();
             cv::resize(roi, roi, cv::Size(48, 36));
             int c = classifier(roi);
-            switch(c){
+            if(c){
-                case 1:
+                boxes_number[c-1].emplace_back(box);
-                    boxes_one.emplace_back(box);
-                    break;
-                case 2:
-                    boxes_two.emplace_back(box);
-                    break;
-                case 3:
-                    boxes_three.emplace_back(box);
-                    break;
             }
         }
-        if(!boxes_one.empty()){
+        for(auto box : boxes_number){
-            armor_box = boxes_one[0];
+            if(!box.empty()){
-        }else if(!boxes_two.empty()){
+                armor_box = box[0];
-            armor_box = boxes_two[0];
+            }
-        }else if(!boxes_three.empty()){
+        }
-            armor_box = boxes_three[0];
+
-        } else{
+        if(armor_box == cv::Rect2d(0,0,0,0)){
             return false;
         }
-        if(show_armor_box){
+        if(show_armor_boxes){
-            showArmorBoxClass("class", src, boxes_one, boxes_two, boxes_three);
+            showArmorBoxClass("class", src, boxes_number);
         }
     }else{
         armor_box = armor_boxes[0];

armor/src/show_images/show_images.cpp

@@ -18,8 +18,7 @@ void showArmorBoxVector(std::string windows_name, const cv::Mat &src, const std:
     imshow(windows_name, image2show);
 }
 
-void showArmorBoxClass(std::string windows_name, const cv::Mat &src, vector<cv::Rect2d> boxes_one,
+void showArmorBoxClass(std::string window_names, const cv::Mat &src, vector<cv::Rect2d> boxes[10]){
-        vector<cv::Rect2d> boxes_two, vector<cv::Rect2d> boxes_three){
     static Mat image2show;
     if (src.type() == CV_8UC1) // 黑白图像
     {
@@ -28,16 +27,32 @@ void showArmorBoxClass(std::string windows_name, const cv::Mat &src, vector<cv::
     {
         image2show = src.clone();
     }
-    for (auto &box:boxes_one) {
+    if(!boxes[0].empty()){
-        rectangle(image2show, box, Scalar(255, 0, 0), 1);
+        for(auto box : boxes[0]){
+            cv::rectangle(image2show, box, Scalar(255, 0, 0), 1);
         }
-    for (auto &box:boxes_two) {
+    }else if(!boxes[1].empty()){
-        rectangle(image2show, box, Scalar(0, 255, 0), 1);
+        for(auto box : boxes[1]){
+            cv::rectangle(image2show, box, Scalar(0, 255, 0), 1);
         }
-    for (auto &box:boxes_three) {
+    }else if(!boxes[2].empty()){
-        rectangle(image2show, box, Scalar(0, 0, 255), 1);
+        for(auto box : boxes[2]){
+            cv::rectangle(image2show, box, Scalar(0, 0, 255), 1);
         }
-    imshow(windows_name, image2show);
+    }else if(!boxes[3].empty()){
+        for(auto box : boxes[3]){
+            cv::rectangle(image2show, box, Scalar(0, 255, 255), 1);
+        }
+    }else if(!boxes[4].empty()){
+        for(auto box : boxes[4]){
+            cv::rectangle(image2show, box, Scalar(255, 0, 255), 1);
+        }
+    }else if(!boxes[5].empty()){
+        for(auto box : boxes[5]){
+            cv::rectangle(image2show, box, Scalar(255, 255, 0), 1);
+        }
+    }
+    imshow(window_names, image2show);
 }
 
 void showArmorBox(std::string windows_name, const cv::Mat &src, cv::Rect2d armor_box) {

main.cpp

@@ -15,7 +15,7 @@
 #include <options/options.h>
 #include <thread>
 
-//#define DO_NOT_CNT_TIME
+#define DO_NOT_CNT_TIME
 #include <log.h>
 
 #define PATH PROJECT_DIR
@@ -33,12 +33,23 @@ int mark = 0;
 
 void uartReceive(Uart* uart);
 
+thread* create_data_recv_thread(Uart *uart){
+    thread *thread1 = new thread([uart](){
+        LOGM("Start receiving!");
+        while(1){
+            uart->debugUart();
+        }
+    });
+    return thread1;
+}
+
+
 int main(int argc, char *argv[]){
     process_options(argc, argv);
     Uart uart;
     thread receive(uartReceive, &uart);
 	bool flag = true;
-
+//    create_data_recv_thread(&uart);
 	while (flag){
         int ally_color = ALLY_RED;
         int energy_part_rotation = CLOCKWISE;
@@ -55,8 +66,8 @@ int main(int argc, char *argv[]){
             video_armor = new CameraWrapper(0);
 //            video_energy = new CameraWrapper(1);
         }else {
-            video_armor = new VideoWrapper("/home/xinyang/Desktop/Video.mp4");
+            video_armor = new VideoWrapper("/home/xinyang/Desktop/Video0.mp4");
-            video_energy = new VideoWrapper("/home/xinyang/Desktop/Video.mp4");
+            video_energy = new VideoWrapper("/home/xinyang/Desktop/Video0.mp4");
         }
 		if (video_armor->init()) {
 			cout << "Video source initialization successfully." << endl;
@@ -74,11 +85,10 @@ int main(int argc, char *argv[]){
 
 		while (ok){
 		    CNT_TIME(WORD_LIGHT_CYAN, "Total", {
-                ok = video_armor->read(energy_src) && video_armor->read(armor_src);
+		        CNT_TIME(WORD_LIGHT_PURPLE, "Read", {
-                if (show_origin) {
+                    ok = video_armor->read(armor_src);
-                    imshow("enery src", energy_src);
+//                    ok &&= video_energy->read(energy_src);
-                    imshow("armor src", armor_src);
+                });
-                }
                 if (state == ENERGY_STATE) {
                     if (from_camera == 0) {
                         energy.extract(energy_src);
@@ -112,6 +122,7 @@ void uartReceive(Uart* uart){
             buffer[cnt++] = data;
             if(cnt >= 100){
 //                LOGE("data receive over flow!");
+                cnt = 0;
             }
         }
         if(cnt == 10){
@@ -131,7 +142,6 @@ void uartReceive(Uart* uart){
                     mark_yaw = curr_yaw;
                     mark_pitch = curr_pitch;
                 }
-
 //                LOGM("Marked");
             }
         }

others/include/uart/uart.h

@@ -36,6 +36,7 @@ public:
 
     uint8_t receive();
     void receive_data();
+    bool debugUart();
 };
 
 

others/src/camera/camera_wrapper.cpp

@@ -65,11 +65,14 @@ stop:
             tCapability.sResolutionRange.iWidthMax * 3);
     if(mode == 0){
         // 不使用自动曝光
-        CameraSetAeState(h_camera, true);
+        CameraSetAeState(h_camera, false);
         // 曝光时间10ms
-//        CameraSetExposureTime(h_camera, 10000);
+        CameraSetExposureTime(h_camera, 10000);
+        double t;
+        CameraGetExposureTime(h_camera, &t);
+        LOGM("Exposure time: %lfms", t/1000.0);
         // 模拟增益4
-        CameraSetAnalogGain(h_camera, 64);
+        CameraSetAnalogGain(h_camera, 55);
         // 使用预设LUT表
         CameraSetLutMode(h_camera, LUTMODE_PRESET);
         // 抗频闪
@@ -90,7 +93,7 @@ stop:
     /*其他的相机参数设置
     例如 CameraSetExposureTime   CameraGetExposureTime  设置/读取曝光时间
          CameraSetImageResolution  CameraGetImageResolution 设置/读取分辨率
-         CameraSetGamma、CameraSetConrast、CameraSetGain等设置图像伽马、对比度、RGB数字增益等等。
+         CameraSetGamma、CameraSetContrast、CameraSetGain等设置图像伽马、对比度、RGB数字增益等等。
          CameraGetFriendlyName    CameraSetFriendlyName 获取/设置相机名称（该名称可写入相机硬件）
     */
 

others/src/uart/uart.cpp

@@ -4,6 +4,7 @@
 
 #include <uart/uart.h>
 #include <energy/param_struct_define.h>
+#include <log.h>
 
 using std::cout;
 using std::cerr;
@@ -16,7 +17,6 @@ GMAngle_t aim;
 
 
 Uart::Uart(){
-
     fd = open("/dev/ttyUSB0", O_RDWR);
     if(fd < 0)
     {
@@ -121,6 +121,9 @@ int Uart::set_opt(int fd, int nSpeed, int nBits, char nEvent, int nStop) {
     return 0;
 }
 
+FILE *send_info=fopen("send.info", "w");
+FILE *recv_info=fopen("recv.info", "w");
+
 void Uart::sendTarget(float x, float y, float z) {
     static short x_tmp, y_tmp, z_tmp;
 
@@ -146,6 +149,13 @@ void Uart::sendTarget(float x, float y, float z) {
     buff[6] = static_cast<char>((z_tmp >> 0) & 0xFF);
     buff[7] = 'e';
 
+    timeval ts;
+    gettimeofday(&ts, NULL);
+    fprintf(send_info, "%lf %f %f\n",
+            ts.tv_sec + ts.tv_usec / 1e6,
+            x, y
+    );
+
     write(fd, buff, 8);
 
 }
@@ -159,3 +169,28 @@ uint8_t Uart::receive() {
     return data;
 }
 
+void readall(int fd, void* buff, int size) {
+    int cnt = 0;
+    while ((cnt += read(fd, (char*)buff + cnt, size - cnt)) < size);
+}
+
+char readone(int fd){
+    char val;
+    while(read(fd, &val, 1) < 1);
+    return val;
+}
+
+
+
+bool Uart::debugUart() {
+    float val[3];
+    //while(readone(fd) != 's');
+    readall(fd, val, sizeof(val));
+    timeval ts;
+    gettimeofday(&ts, NULL);
+    fprintf(recv_info, "%lf %f %f %f\n",
+            ts.tv_sec + ts.tv_usec / 1e6,
+            val[0], val[1], val[2]
+    );
+}
+

tools/TrainCNN/backward.py

@@ -53,7 +53,7 @@ def save_para(folder, paras):
         save_bias(fp, paras[7])
 
 
-STEPS = 20000
+STEPS = 10000
 BATCH = 30
 LEARNING_RATE_BASE  = 0.01
 LEARNING_RATE_DECAY = 0.99
@@ -61,8 +61,6 @@ MOVING_AVERAGE_DECAY = 0.99
 
 
 def train(dataset, show_bar=False):
-    test_images, test_labels = dataset.all_test_sets()
-
     x = tf.placeholder(tf.float32, [None, generate.SRC_ROWS, generate.SRC_COLS, generate.SRC_CHANNELS])
     y_= tf.placeholder(tf.float32, [None, forward.OUTPUT_NODES])
     nodes, vars = forward.forward(x, 0.001)
@@ -104,7 +102,8 @@ def train(dataset, show_bar=False):
 
             if i % 100 == 0:
                 if i % 1000 == 0:
-                    acc = sess.run(accuracy, feed_dict={x: test_images, y_: test_labels})
+                    test_samples, test_labels = dataset.sample_train_sets(5000)
+                    acc = sess.run(accuracy, feed_dict={x: test_samples, y_: test_labels})
                 bar.set_postfix({"loss": loss_value, "acc": acc})
 
 
@@ -151,8 +150,8 @@ def train(dataset, show_bar=False):
 
         vars_val = sess.run(vars)
         save_para("/home/xinyang/Desktop/AutoAim/tools/para", vars_val)
-        nodes_val = sess.run(nodes, feed_dict={x:test_images})
+        nodes_val = sess.run(nodes, feed_dict={x:test_samples})
-        return vars_val, nodes_val
+        return vars_val, nodes_val, test_samples
 
 
 if __name__ == "__main__":
@@ -160,3 +159,4 @@ if __name__ == "__main__":
     dataset = generate.DataSet("/home/xinyang/Desktop/DataSets/box")
     print("Finish!")
     train(dataset, show_bar=True)
+    input("Press any key to continue...")

tools/TrainCNN/generate.py

@@ -24,34 +24,40 @@ class DataSet:
         self.test_labels = []
         self.generate_data_sets(folder)
 
-    def file2nparray(self, name):
+    def generate_data_sets(self, folder):
-        try:
+        def id2label(id):
-            image = cv2.imread(name)
-            image = cv2.resize(image, (SRC_COLS, SRC_ROWS))
-            image = image.astype(np.float32)
-            return image / 255.0
-        except:
-            print(name)
-            sys.exit(-1)
-
-    def id2label(self, id):
             a = np.zeros([OUTPUT_NODES])
             a[id] = 1
             return a[:]
 
-    def generate_data_sets(self, folder):
+        def file2nparray(name):
+            try:
+                image = cv2.imread(name)
+                if image.shape[0] < 15:
+                    return None
+                elif image.shape[1] < 10:
+                    return None
+                image = cv2.resize(image, (SRC_COLS, SRC_ROWS))
+                image = image.astype(np.float32)
+                return image / 255.0, id2label(int(name.split("/")[-2]))
+            except TypeError:
+                print(name)
+                sys.exit(-1)
+
         sets = []
         for i in range(OUTPUT_NODES):
             dir = "%s/%d" % (folder, i)
             files = os.listdir(dir)
             for file in tqdm(files, postfix={"loading id": i}, dynamic_ncols=True):
                 if file[-3:] == "jpg":
+                    x = file2nparray("%s/%s" % (dir, file))
+                    if x is not None:
                         if random.random() > 0.2:
-                        self.train_samples.append(self.file2nparray("%s/%s" % (dir, file)))
+                            self.train_samples.append(x[0])
-                        self.train_labels.append(self.id2label(i))
+                            self.train_labels.append(x[1])
                         else:
-                        self.test_samples.append(self.file2nparray("%s/%s" % (dir, file)))
+                            self.test_samples.append(x[0])
-                        self.test_labels.append(self.id2label(i))
+                            self.test_labels.append(x[1])
         self.train_samples = np.array(self.train_samples)
         self.train_labels = np.array(self.train_labels)
         self.test_samples = np.array(self.test_samples)
@@ -67,6 +73,15 @@ class DataSet:
             labels.append(self.train_labels[id])
         return np.array(samples), np.array(labels)
 
+    def sample_test_sets(self, length):
+        samples = []
+        labels = []
+        for i in range(length):
+            id = random.randint(0, len(self.test_samples)-1)
+            samples.append(self.test_samples[id])
+            labels.append(self.test_labels[id])
+        return np.array(samples), np.array(labels)
+
     def all_train_sets(self):
         return self.train_samples[:], self.train_labels[:]
 

tools/para/conv1_b

@@ -1,7 +1,7 @@
 6
-0.6241298
+-0.37225634
-1.1128483
+-0.2478522
-0.92715627
+-0.47375765
-2.6803706
+0.009908229
--2.4037633
+0.69579834
-1.6914424
+-0.05971829

tools/para/conv1_w

@@ -2,453 +2,453 @@
 6
 5
 5
--1.8745673
+-0.7337494
--1.4418055
+-0.6937527
--0.68810487
+-0.67101884
--0.42730802
+-0.60440236
--0.019043377
+-0.73606586
--2.2401865
+-0.7478304
--1.5337001
+-0.8085305
--0.5666739
+-0.6904055
-0.1119876
+-0.7651195
-0.24716255
+-0.7084718
--2.2945662
+-0.9906155
--1.4734446
+-0.87745357
--0.298631
+-0.7000051
-0.19550888
+-0.8715864
-0.45057848
+-0.7446616
--2.4559898
+-0.8037889
--1.097164
+-0.618627
--0.035884537
+-0.6325674
-0.23402216
+-0.59341496
-0.3693794
+-0.62959474
--1.7285618
+-0.014231296
--0.8927671
+-0.08161524
-0.026205042
+-0.2579513
-0.19274746
+-0.4687266
-0.029146997
+-0.24779701
--1.3690577
+-0.22118886
--1.2756748
+-0.31540632
--0.32751036
+-0.21255392
-0.3233031
+0.01073099
-0.55376107
+-0.15033825
--1.4835969
+-0.32471213
--1.3036382
+-0.12707588
--0.75256515
+-0.17916436
--0.13608748
+-0.028622292
-0.2254278
+-0.05188435
--1.6409502
+-0.12553264
--1.4188147
+-0.0946007
--1.1627024
+-0.06460633
--0.62049645
+-0.041471746
--0.20085949
+0.015563008
--2.2059698
+-0.26039425
--1.7030506
+-0.079619355
--1.5584862
+-0.1205842
--1.2325822
+0.094940566
--0.6749467
+-0.1750217
--2.8320985
+-0.2796452
--2.3289032
+-0.19023262
--1.811129
+-0.055042416
--1.6702974
+-0.050695155
--1.0760157
+-0.044094857
--1.3135052
+-0.9086073
--0.90016854
+-0.35235822
--0.47004116
+0.30365855
--0.17118637
+1.000589
--0.2732028
+1.2184463
--1.3109291
+-0.7277262
--0.36519817
+-0.27227914
--0.10975292
+0.51391685
--0.06533194
+0.93604887
--0.559026
+1.1217358
--0.8616304
+-0.8503647
--0.06857806
+-0.1529237
-0.19276045
+0.7071794
--0.14059812
+1.0232986
--0.7283358
+0.9231354
--0.57705516
+-1.1999215
-0.20748538
+-0.26001996
-0.26281402
+0.31989247
--0.112977654
+0.49021512
--0.6980696
+0.4707462
--0.44812128
+-1.3921645
-0.40235195
+-0.7652607
-0.26663
+-0.32385713
--0.10336824
+-0.0044978694
--0.5741328
+0.12107601
--0.70127535
+-0.2628682
--1.1506568
+-0.040824424
--1.3301972
+-0.4928625
--1.4370873
+-1.1108128
--0.9951577
+-2.1292882
--0.3111034
+-0.43092158
--0.5350495
+0.039630573
--0.78488415
+-0.19942534
--1.3619742
+-1.1754087
--1.2252145
+-2.0381243
-0.10870424
+-0.45808747
--0.044690743
+0.019034432
--0.33280057
+-0.40220654
--1.180621
+-1.216894
--1.5130968
+-2.1285393
-0.32003295
+-0.6753537
-0.6245109
+-0.17457765
-0.3391734
+-0.19739395
--0.45662346
+-0.8989531
--1.2023503
+-1.7085532
-0.66186905
+-0.67778856
-0.6943321
+-0.2841309
-0.753682
+-0.20467272
--0.05385303
+-0.6957597
--0.69504744
+-1.3799949
--0.86241025
+-1.221984
-0.05611875
+-1.047475
-0.7984623
+-0.5553654
-1.4339544
+-0.5047841
-2.0078037
+-0.48746312
--0.6121641
+-0.82557076
-0.3216552
+-0.40178424
-0.7244501
+-0.14857721
-1.4381241
+-0.05297258
-1.9696213
+-0.536673
--0.29659018
+-0.5235084
-0.13415621
+0.052303962
-0.61756736
+-0.023993408
-1.0113128
+-0.31840283
-1.3834459
+-0.9369167
-0.12413465
+-0.5166214
-0.3135587
+-0.1376763
-0.32853445
+0.0063631153
-0.7981063
+-0.12015801
-0.83142936
+-1.2773997
--0.004516094
+-0.72208375
-0.32636595
+-0.24810186
-0.55108666
+-0.26033
-0.6248727
+-0.46964744
-0.60938156
+-1.557477
--0.38326544
+-0.0126399975
--1.2629062
+-0.2124332
--0.385575
+0.07490671
-0.11398253
+-0.08790178
-0.40000448
+-0.11780411
--1.0602297
+0.042807758
--1.1948771
+0.008334734
--0.6945023
+0.060645778
--0.4127804
+-0.14671083
-0.029964926
+-0.16901183
--1.4086407
+-0.22304396
--1.3599807
+-0.0769471
--1.3076004
+-0.009709285
--1.1330422
+-0.14782685
--0.38810351
+-0.095943585
--2.1059783
+0.020692833
--1.8239182
+-0.14911899
--1.7029382
+-0.15973799
--1.4902409
+-0.03142608
--0.91088384
+0.104167305
--3.230572
+-0.20708825
--2.4590926
+-0.05318397
--1.9471443
+-0.07113983
--1.860621
+-0.13408132
--1.3370123
+-0.11653387
--0.5690341
+-0.7500504
--0.33530146
+-0.7248431
-0.31661218
+-0.61835104
-0.8375982
+-0.45383522
-1.1338086
+-0.16763654
--1.3648574
+-0.61524427
--0.8348736
+-0.7349246
-0.36666754
+-0.8378667
-1.1275568
+-0.5694857
-1.1844105
+-0.45536998
--1.8321881
+-0.76552916
--0.78104144
+-0.851986
-0.59508055
+-0.85871804
-1.2501543
+-0.7100276
-1.2034286
+-0.49703908
--1.6087818
+-0.64794004
--0.6121007
+-0.50571287
-0.693586
+-0.6866874
-1.2163337
+-0.40854928
-1.1292332
+-0.5622537
--0.6255259
+0.07620155
-0.0911698
+-0.0787729
-0.78314143
+-0.19114618
-0.9095932
+-0.16987182
-0.5689121
+-0.17041641
--3.2688649
+-0.27857593
--1.2751737
+-0.121658556
-0.7530108
+-0.085185595
-1.5721122
+-0.08372851
-2.11933
+-0.14375111
--2.9633296
+-0.37070906
--1.3632398
+-0.14901304
-0.11986004
+-0.054120127
-1.1412225
+0.038107906
-1.8641368
+-0.07748371
--1.9467463
+-0.20931405
--0.9146176
+-0.1937567
--0.10545669
+0.14340971
-0.49356145
+-0.053399563
-1.3669914
+-0.083370306
--1.7783622
+-0.21443273
--0.99905616
+-0.080105215
--0.28957212
+-0.10266688
-0.13239379
+0.10945406
-0.9921155
+-0.18393016
--2.1976538
+-0.16443613
--1.0333587
+0.017121822
--0.3801185
+0.04672509
-0.021550074
+0.09892883
-0.5849712
+-0.11781335
--0.7216267
+-1.161838
--0.36925313
+-0.8175547
--0.5770921
+-0.44016403
--0.89754397
+0.090491325
--0.9315221
+0.8639599
--0.17996566
+-0.49316305
-0.5721206
+0.25248703
-0.46629494
+0.3574456
--0.11679081
+0.791709
--0.8407021
+1.0159097
-0.14923953
+0.108047605
-1.1722741
+0.72324693
-1.0859729
+1.0133348
--0.08064234
+1.2196273
--1.1707838
+0.8379106
-0.527985
+0.12326059
-1.556374
+0.6342552
-1.3262485
+0.91193444
-0.052869447
+0.69442016
--1.0933924
+0.5248603
-0.8913072
+0.06752323
-1.8925939
+0.22544046
-1.1744183
+0.21614142
--0.16056827
+-0.033874128
--0.96226853
+-0.35373747
--2.0482447
+1.2651725
--2.1394062
+1.0176816
--2.3160622
+0.63459647
--1.5373954
+-0.68232757
--1.0280651
+-2.055359
--1.0137186
+1.2116768
--1.1347228
+1.0648314
--1.2650911
+0.79537696
--1.3904438
+-0.44271514
--1.4724954
+-2.0117953
--0.6152145
+1.2231245
--0.38191465
+1.1929921
--0.6525277
+0.5311513
--1.2026839
+-0.62809414
--1.574993
+-2.1078017
--0.14897716
+0.8818138
-0.40652698
+1.0870899
-0.22212738
+0.7286623
--0.7051095
+-0.21488012
--1.6179065
+-1.6681597
-0.12883945
+0.7761452
-0.92052716
+1.039942
-0.71651196
+0.7954326
--0.1521632
+0.22737303
--1.3601139
+-1.0519534
--1.3278087
+-1.4585321
-0.091166034
+-1.2353656
-0.70035547
+-1.00755
-0.85970676
+-0.40541697
-1.4728521
+-0.241744
--0.4685758
+-0.2468871
-0.67533374
+-0.124388404
-1.2041222
+0.034186
-0.91583323
+0.15726992
-1.3638756
+-0.2593506
--0.21221842
+0.21214157
-0.46413553
+0.60234964
-0.6931065
+0.48045504
-0.5078553
+0.08620858
-1.0690873
+-0.45957863
--0.2822384
+0.79536515
--0.18992352
+1.0071297
--0.30851105
+0.6323838
--0.48985106
+-0.05272095
--0.112165235
+-1.2025502
--0.6343776
+0.8740463
--0.97740346
+0.9715014
--1.2637299
+0.6848851
--1.1870348
+-0.20320709
--0.65784734
+-1.7574068
--2.275478
+-0.04044696
--1.5841419
+-0.08917504
-0.59182155
+-0.070345305
-1.7027438
+-0.23287608
-2.2658849
+-0.10763591
--2.0428355
+0.10209269
--0.9335362
+-0.049792744
-0.25750664
+-0.07547748
-1.0987146
+0.10696673
-1.5473177
+-0.16306788
--0.8157582
+0.088507146
--0.23004234
+0.02865851
-0.3001771
+-0.13394779
-0.6583938
+-0.10253158
-1.0895797
+-0.036603633
--0.093778014
+-0.20971416
-0.08269198
+-0.051816575
-0.17656319
+0.18494779
-0.3352879
+-0.020245025
-1.0185977
+-0.07630297
--0.6558476
+-0.12080981
-0.4106111
+-0.12838727
-0.3651244
+0.07689702
-0.3434926
+-0.1401755
-0.78885883
+-0.047443036
-0.9312759
+-0.4872008
-0.45665312
+-0.755767
-0.87845147
+-0.90513796
-1.4286675
+-0.6640466
-1.9387178
+-0.509753
-0.0055226237
+-0.4808521
--0.11264928
+-0.5807188
-0.69314396
+-0.6151164
-1.5066721
+-0.5550288
-1.5526584
+-0.4243716
--0.15990084
+-0.40014786
-0.10977341
+-0.25531605
-0.7288155
+-0.26900706
-1.5179793
+-0.35961694
-1.5454628
+-0.31855944
-0.42554915
+-0.06904432
-0.6133954
+0.08449408
-1.1112447
+-0.04440668
-1.4276886
+0.05930122
-1.3272578
+0.0011873574
-1.5569048
+0.7064937
-1.5756388
+0.49867254
-1.9869299
+0.6776411
-1.8189707
+0.8048061
-1.3973557
+0.5733196
--4.249913
+-0.19441545
--1.9120424
+-0.005778725
--0.0061387075
+-0.0071499897
-0.80639493
+0.08352753
-1.4316615
+-0.13246052
--3.410931
+-0.033308238
--1.7743304
+0.065881364
--0.18588163
+-0.1476445
-0.5619047
+-0.17577946
-1.2757853
+-0.20313627
--2.25766
+-0.026538868
--1.1736825
+0.10845672
--0.47299188
+0.12951013
-0.38950402
+-0.054592907
-1.098909
+-0.054286536
--2.850165
+0.0909873
--1.7250451
+0.07470816
--0.7260333
+2.0157931e-05
--0.055943523
+-0.075895675
-0.9642611
+-0.0631687
--4.005538
+0.1139621
--2.295592
+0.13023847
--1.041572
+0.07489004
--0.24684854
+0.1949782
-0.6455168
+0.02820571
-1.1459881
+0.40668908
-1.4573389
+-0.000711774
-1.4954526
+-0.744561
-1.2473075
+-0.5027803
-1.0846232
+0.20088871
-1.2540116
+0.96308225
-1.9666128
+0.92510736
-1.9739157
+0.5134376
-1.2105061
+0.25474888
-0.7538055
+0.4503637
-1.2492738
+1.6561543
-2.14189
+1.8223486
-1.7544507
+1.2207514
-0.96942043
+0.7662908
-0.31504372
+0.38526574
-1.7381212
+1.4918652
-2.490894
+1.6164081
-1.6445026
+1.0311278
-0.26533163
+0.3336429
--0.3193328
+-0.15712811
-2.0120225
+1.4385474
-2.0718558
+1.0327717
-0.8759794
+0.056643657
-0.04767526
+-0.74796945
--0.41645908
+-0.96597683
-1.2511733
+1.1695682
-0.5724159
+1.2116307
-0.37694663
+0.67098075
-1.2807285
+0.061276477
-1.8684267
+-1.1508046
-1.8152616
+1.1278331
-1.280423
+1.0747397
-1.101077
+0.81522405
-1.197118
+-0.024527794
-1.5331124
+-0.95285547
-1.7447906
+0.8995342
-1.6138377
+1.0385815
-1.4156343
+0.71533716
-1.0536009
+-0.045309864
-0.8561865
+-1.1234874
-1.9363236
+0.619687
-2.2086453
+0.90204847
-1.6627563
+0.6468797
-1.021228
+0.33503526
-0.60839254
+-0.66591007
-2.1018016
+0.50283337
-2.1533952
+0.6998083
-1.9573407
+0.7065805
-1.29546
+0.5727497
-0.57359654
+0.04260265
--0.29376534
+-0.4851468
-0.9012422
+-0.20692436
-1.1789744
+0.19345768
-0.710556
+1.0645467
-0.8737443
+1.5191267
-0.095544085
+0.8372995
-1.045074
+0.7781821
-0.9252817
+1.028298
-0.471885
+1.4177388
-0.6031909
+1.4664948
--0.2500516
+1.3292006
-0.14211257
+1.3957899
--0.27518043
+1.5092078
--1.0673013
+1.3398026
--0.845284
+0.997704
--0.7930444
+1.5843834
--1.1906688
+1.6184856
--2.2155006
+1.5397934
--2.8370302
+1.256475
--2.2175434
+0.34014988
--0.9103819
+1.5893154
--2.3526044
+1.544945
--3.3939815
+1.0299425
--3.9634273
+0.6678114
--2.9982874
+-0.1956785
--3.0668538
+-0.10900813
--1.9301875
+-0.11298105
-0.46062958
+-0.016902497
-1.1481701
+-0.1565643
-1.6189759
+-0.054204118
--2.693133
+-0.034246
--1.3168526
+-0.2205075
-0.39946663
+-0.058389995
-0.777253
+0.044116203
-1.2958935
+-0.14663707
--1.7610679
+-0.026256435
--0.87182975
+-0.10222199
-0.015992796
+-0.25303757
-0.35228586
+-0.12922764
-0.825145
+-0.09234042
--2.3087604
+-0.16156028
--1.4618046
+0.119986236
--0.49614725
+-0.010263173
--0.12511182
+-0.04062929
-0.5606166
+-0.024711546
--3.9921951
+0.024872124
--2.422155
+-0.037144
--0.9274944
+-0.10166565
--0.43651518
+0.0026121684
-0.110710315
+-0.20799841

tools/para/conv2_b

@@ -1,11 +1,11 @@
 10
-2.4876857
+-1.3008373
--0.2729608
+-0.09357162
--2.472103
+-1.0318826
-1.4380744
+-0.18906969
-0.13707557
+-0.31774887
--0.38399124
+-1.4002659
--0.10049698
+-0.36336994
--0.44721037
+3.8660808
--0.24111606
+1.2288735
--0.05031827
+0.97610044

tools/para/fc1_b

@@ -1,17 +1,17 @@
 16
-6.674671
+-0.10046868
--0.4621555
+-0.048594907
--0.35395312
+-0.18817224
--6.140842
+-0.17443945
--0.6383096
+-0.475507
--0.0026992396
+-0.014380081
--0.105528705
+-0.08149044
--0.12171911
+-2.158695
--0.039757866
+-4.6233006
--4.064281
+-0.6036441
--0.36199543
+5.3300047
--0.06976157
+-0.009695345
--0.042993866
+-0.008206175
-0.0015301058
+-0.068684034
--0.06826296
+-0.023278365
--0.0050806464
+3.647335

tools/para/fc2_b

@@ -1,5 +1,6 @@
-4
+5
-6.171619
+5.166837
--1.5262855
+-1.2788563
--4.09489
+-1.4764651
--2.3815227
+-1.0171041
+-4.429165

tools/para/fc2_w

@@ -1,66 +1,82 @@
 16
-4
+5
-0.70240104
+3.3546818e-34
--0.058500186
+-5.0533795e-34
--0.23156737
+-2.9876767e-35
--0.33127818
+-5.747061e-34
--3.6112761e-34
+-1.2654221e-33
--3.3890292e-34
+3.1982972e-34
-9.363116e-34
+9.094423e-35
-4.0197816e-34
+7.818431e-34
--0.2575022
+6.1448995e-34
-0.69736814
+1.2132283e-33
--0.2684227
+-8.594385e-34
--0.08991088
+4.8569645e-34
--0.3760809
+1.8429814e-34
--0.065089576
+1.1041889e-33
-0.45981047
+2.012101e-34
-0.008204719
+0.00033738822
--4.8556375e-34
+-6.27447e-05
-4.816393e-34
+3.181418e-09
-3.872484e-34
+5.5260244e-08
-5.096778e-34
+-4.1039914e-09
-1.7445673e-19
+-0.29261625
-1.2270845e-33
+-0.09727536
--2.260416e-25
+0.59134495
-1.0369542e-20
+0.18011163
-4.00948e-34
+-0.16496071
--5.999333e-34
+-4.434109e-34
-3.7143163e-34
+-2.3553354e-35
--4.228372e-34
+1.0642948e-33
--1.0954501e-34
+4.470902e-34
--2.7085206e-34
+-7.44183e-35
-8.016929e-34
+7.1034632e-34
-9.2079354e-35
+6.991907e-34
--3.945864e-34
+-1.5644636e-35
-1.98814e-34
+1.4569e-34
-2.3972646e-34
+-4.247144e-34
-3.942207e-34
+-0.10007951
--0.14058167
+0.6292724
--0.07198931
+-0.11631892
--0.38025984
+-0.2893417
-0.5981627
+-0.060249113
-4.3956684e-34
+-0.10115793
-3.1032594e-34
+-0.05707638
-3.4351758e-34
+-0.021602122
-5.5414507e-34
+-0.18273582
--1.248324e-34
+0.4733028
-8.8546844e-35
+-0.32697493
-6.8084945e-34
+0.0043840045
--1.1866068e-34
+-0.42484373
--3.865728e-34
+0.6746338
-1.8786859e-34
+0.061171096
-3.3450276e-34
+0.76072145
--2.8077459e-34
+-0.24171914
-0.0013890187
+-0.18183002
-0.026067872
+-0.06504542
-0.0082543865
+-0.23874648
--0.02225164
+1.1150656e-34
-2.0089658e-34
+5.1261775e-34
--6.1273506e-34
+-4.443484e-34
--6.228039e-34
+-3.415351e-35
--5.0242814e-34
+-5.0846646e-34
--4.3343494e-34
+6.830828e-13
-3.0939117e-34
+1.3946587e-21
-1.2827092e-34
+5.382798e-34
--4.305108e-34
+6.7468184e-11
+-3.8273462e-34
+-8.327467e-34
+5.3624216e-35
+-1.1396765e-33
+-9.036933e-34
+-6.1432046e-34
+1.0177867e-33
+8.3691855e-34
+-2.4372232e-34
+-1.14444385e-33
+3.8171564e-34
+0.121070996
+-0.054560866
+-0.062351264
+0.012382605
+0.22265062