Support .txt files as a line-by-line media list rather than streams (#10059)

* Update streams.txt default

Signed-off-by: Colin Wong <cwongmath@gmail.com>

* Change streams list extension to .streams

* Read txt as media per line

* Missed one

* Missed another one

* Update dataloaders.py

* Update detect.py

* Update dataloaders.py

* Update detect.py

* Update predict.py

* Update predict.py

* Update README.md

Signed-off-by: Colin Wong <cwongmath@gmail.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

README.md

@@ -182,14 +182,16 @@ results.print()  # or .show(), .save(), .crop(), .pandas(), etc.
 the latest YOLOv5 [release](https://github.com/ultralytics/yolov5/releases) and saving results to `runs/detect`.
 
 ```bash
-python detect.py --source 0  # webcam
+python detect.py --weights yolov5s.pt --source 0                               # webcam
-                          img.jpg  # image
+                                               img.jpg                         # image
-                          vid.mp4  # video
+                                               vid.mp4                         # video
-                          screen  # screenshot
+                                               screen                          # screenshot
-                          path/  # directory
+                                               path/                           # directory
-                          'path/*.jpg'  # glob
+                                               list.txt                        # list of images
-                          'https://youtu.be/Zgi9g1ksQHc'  # YouTube
+                                               list.streams                    # list of streams
-                          'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
+                                               'path/*.jpg'                    # glob
+                                               'https://youtu.be/Zgi9g1ksQHc'  # YouTube
+                                               'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
 ```
 
 </details>

classify/predict.py

@@ -8,6 +8,8 @@ Usage - sources:
                                                                    vid.mp4                         # video
                                                                    screen                          # screenshot
                                                                    path/                           # directory
+                                                                   list.txt                        # list of images
+                                                                   list.streams                    # list of streams
                                                                    'path/*.jpg'                    # glob
                                                                    'https://youtu.be/Zgi9g1ksQHc'  # YouTube
                                                                    'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
@@ -74,7 +76,7 @@ def run(
     save_img = not nosave and not source.endswith('.txt')  # save inference images
     is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
     is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
-    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
+    webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file)
     screenshot = source.lower().startswith('screen')
     if is_url and is_file:
         source = check_file(source)  # download

detect.py

@@ -8,6 +8,8 @@ Usage - sources:
                                                      vid.mp4                         # video
                                                      screen                          # screenshot
                                                      path/                           # directory
+                                                     list.txt                        # list of images
+                                                     list.streams                    # list of streams
                                                      'path/*.jpg'                    # glob
                                                      'https://youtu.be/Zgi9g1ksQHc'  # YouTube
                                                      'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
@@ -82,7 +84,7 @@ def run(
     save_img = not nosave and not source.endswith('.txt')  # save inference images
     is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
     is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
-    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
+    webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file)
     screenshot = source.lower().startswith('screen')
     if is_url and is_file:
         source = check_file(source)  # download

segment/predict.py

@@ -8,6 +8,8 @@ Usage - sources:
                                                                   vid.mp4                         # video
                                                                   screen                          # screenshot
                                                                   path/                           # directory
+                                                                  list.txt                        # list of images
+                                                                  list.streams                    # list of streams
                                                                   'path/*.jpg'                    # glob
                                                                   'https://youtu.be/Zgi9g1ksQHc'  # YouTube
                                                                   'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
@@ -85,7 +87,7 @@ def run(
     save_img = not nosave and not source.endswith('.txt')  # save inference images
     is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
     is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
-    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
+    webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file)
     screenshot = source.lower().startswith('screen')
     if is_url and is_file:
         source = check_file(source)  # download

utils/dataloaders.py

@@ -238,6 +238,8 @@ class LoadScreenshots:
 class LoadImages:
     # YOLOv5 image/video dataloader, i.e. `python detect.py --source image.jpg/vid.mp4`
     def __init__(self, path, img_size=640, stride=32, auto=True, transforms=None, vid_stride=1):
+        if isinstance(path, str) and Path(path).suffix == ".txt":  # *.txt file with img/vid/dir on each line
+            path = Path(path).read_text().rsplit()
         files = []
         for p in sorted(path) if isinstance(path, (list, tuple)) else [path]:
             p = str(Path(p).resolve())
@@ -338,7 +340,7 @@ class LoadImages:
 
 class LoadStreams:
     # YOLOv5 streamloader, i.e. `python detect.py --source 'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP streams`
-    def __init__(self, sources='streams.txt', img_size=640, stride=32, auto=True, transforms=None, vid_stride=1):
+    def __init__(self, sources='file.streams', img_size=640, stride=32, auto=True, transforms=None, vid_stride=1):
         torch.backends.cudnn.benchmark = True  # faster for fixed-size inference
         self.mode = 'stream'
         self.img_size = img_size