Batch size > 1 for the 3D demo.

This commit lets to use differtent batch size for 3D CenterNet
and CenterTrack.

Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>

demo/demo/demo3D.cpp

@@ -1,7 +1,7 @@
 #include <iostream>
 #include <signal.h>
 #include <stdlib.h>     /* srand, rand */
-#include <unistd.h>
+//#include <unistd.h>
 #include <mutex>
 
 #include "CenternetDetection3D.h"
@@ -24,7 +24,12 @@ int main(int argc, char *argv[]) {
     std::string net = "dla34_cnet3d_fp32.rt";
     if(argc > 1)
         net = argv[1]; 
-    std::string input = "../demo/yolo_test.mp4";
+    #ifdef __linux__ 
+        std::string input = "../demo/yolo_test.mp4";
+    #elif _WIN32
+        std::string input = "..\\..\\..\\demo\\yolo_test.mp4";
+    #endif
+
     if(argc > 2)
         input = argv[2]; 
     char ntype = 'c';
@@ -33,9 +38,18 @@ int main(int argc, char *argv[]) {
     int n_classes = 3;
     if(argc > 4)
         n_classes = atoi(argv[4]); 
-    bool show = false;
+    int n_batch = 1;
     if(argc > 5)
-        show = atoi(argv[5]);
+        n_batch = atoi(argv[5]); 
+    bool show = true;
+    if(argc > 6)
+        show = atoi(argv[6]); 
+    float conf_thresh=0.3;
+    if(argc > 7)
+        conf_thresh = atof(argv[7]);     
+
+    if(n_batch < 1 || n_batch > 64)
+        FatalError("Batch dim not supported");
 
     if(!show)
 	SAVE_RESULT = true;
@@ -57,7 +71,7 @@ int main(int argc, char *argv[]) {
         FatalError("Network type not allowed (3rd parameter)\n");
     }
 
-    detNN->init(net, n_classes);
+    detNN->init(net, n_classes, n_batch, conf_thresh);
 
     gRun = true;
 
@@ -75,30 +89,40 @@ int main(int argc, char *argv[]) {
     }
 
     cv::Mat frame;
-    cv::Mat dnn_input;
     if(show)
-	cv::namedWindow("detection", cv::WINDOW_NORMAL);
+	    cv::namedWindow("detection", cv::WINDOW_NORMAL);
     
-    std::vector<tk::dnn::box> detected_bbox;
+    std::vector<cv::Mat> batch_frame;
+    std::vector<cv::Mat> batch_dnn_input;
 
     while(gRun) {
-        cap >> frame; 
-        if(!frame.data) {
-            break;
-        }  
- 
-        // this will be resized to the net format
-        dnn_input = frame.clone();
+        batch_dnn_input.clear();
+        batch_frame.clear();
         
+        for(int bi=0; bi< n_batch; ++bi){
+            cap >> frame; 
+            if(!frame.data) 
+                break;
+            
+            batch_frame.push_back(frame);
+
+            // this will be resized to the net format
+            batch_dnn_input.push_back(frame.clone());
+        } 
+        if(!frame.data) 
+            break;  
+ 
         //inference
-        detNN->update(dnn_input);
-        frame = detNN->draw(frame);
-	
-	if(show) {
-	    cv::imshow("detection", frame);
-            cv::waitKey(1);
-	}
-        if(SAVE_RESULT)
+        detNN->update(batch_dnn_input, n_batch);
+        detNN->draw(batch_frame);
+
+        if(show){
+            for(int bi=0; bi< n_batch; ++bi){
+                cv::imshow("detection", batch_frame[bi]);
+                cv::waitKey(1);
+            }
+        }
+        if(n_batch == 1 && SAVE_RESULT)
             resultVideo << frame;
     }
 
@@ -124,7 +148,6 @@ int main(int argc, char *argv[]) {
     std::cout<<"Avg: "<<mean<<" ms\n"<<COL_END;   
     
     
-
     return 0;
 }