Save webcam results, add --nosave option (#2598)

This updates the default detect.py behavior to automatically save all inference images/videos/webcams unless the new argument --nosave is used (python detect.py --nosave) or unless a list of streaming sources is passed (python detect.py --source streams.txt)

detect.py

@@ -17,6 +17,7 @@ from utils.torch_utils import select_device, load_classifier, time_synchronized
 
 def detect(save_img=False):
     source, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
+    save_img = not opt.nosave and not source.endswith('.txt')  # save inference images
     webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
         ('rtsp://', 'rtmp://', 'http://'))
 
@@ -49,7 +50,6 @@ def detect(save_img=False):
         cudnn.benchmark = True  # set True to speed up constant image size inference
         dataset = LoadStreams(source, img_size=imgsz, stride=stride)
     else:
-        save_img = True
         dataset = LoadImages(source, img_size=imgsz, stride=stride)
 
     # Get names and colors
@@ -124,17 +124,19 @@ def detect(save_img=False):
             if save_img:
                 if dataset.mode == 'image':
                     cv2.imwrite(save_path, im0)
-                else:  # 'video'
+                else:  # 'video' or 'stream'
                     if vid_path != save_path:  # new video
                         vid_path = save_path
                         if isinstance(vid_writer, cv2.VideoWriter):
                             vid_writer.release()  # release previous video writer
-
-                        fourcc = 'mp4v'  # output video codec
-                        fps = vid_cap.get(cv2.CAP_PROP_FPS)
-                        w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-                        h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-                        vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (w, h))
+                        if vid_cap:  # video
+                            fps = vid_cap.get(cv2.CAP_PROP_FPS)
+                            w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+                            h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                        else:  # stream
+                            fps, w, h = 30, im0.shape[1], im0.shape[0]
+                            save_path += '.mp4'
+                        vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
                     vid_writer.write(im0)
 
     if save_txt or save_img:
@@ -155,6 +157,7 @@ if __name__ == '__main__':
     parser.add_argument('--view-img', action='store_true', help='display results')
     parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
     parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
+    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
     parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
     parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
     parser.add_argument('--augment', action='store_true', help='augmented inference')