ultralytics 8.2.46 Results, DFL and AIGym fixes (#14074)

Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: AAOMM <52826299+Chayanonjackal@users.noreply.github.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: Muhammad Rizwan Munawar <muhammadrizwanmunawar123@gmail.com>
Co-authored-by: zzzer <48149018+zhixuwei@users.noreply.github.com>
Co-authored-by: Abirami Vina <abirami.vina@gmail.com>

docs/en/guides/workouts-monitoring.md

@@ -55,16 +55,14 @@ Monitoring workouts through pose estimation with [Ultralytics YOLOv8](https://gi
             kpts_to_check=[6, 8, 10],
         )
 
-        frame_count = 0
         while cap.isOpened():
             success, im0 = cap.read()
             if not success:
                 print("Video frame is empty or video processing has been successfully completed.")
                 break
-            frame_count += 1
             results = model.track(im0, verbose=False)  # Tracking recommended
             # results = model.predict(im0)  # Prediction also supported
-            im0 = gym_object.start_counting(im0, results, frame_count)
+            im0 = gym_object.start_counting(im0, results)
 
         cv2.destroyAllWindows()
         ```
@@ -90,16 +88,14 @@ Monitoring workouts through pose estimation with [Ultralytics YOLOv8](https://gi
             kpts_to_check=[6, 8, 10],
         )
 
-        frame_count = 0
         while cap.isOpened():
             success, im0 = cap.read()
             if not success:
                 print("Video frame is empty or video processing has been successfully completed.")
                 break
-            frame_count += 1
             results = model.track(im0, verbose=False)  # Tracking recommended
             # results = model.predict(im0)  # Prediction also supported
-            im0 = gym_object.start_counting(im0, results, frame_count)
+            im0 = gym_object.start_counting(im0, results)
             video_writer.write(im0)
 
         cv2.destroyAllWindows()

docs/mkdocs_github_authors.yaml

@@ -11,6 +11,7 @@
 47978446+sergiuwaxmann@users.noreply.github.com: sergiuwaxmann
 48149018+zhixuwei@users.noreply.github.com: zhixuwei
 49699333+dependabot[bot]@users.noreply.github.com: dependabot
+52826299+Chayanonjackal@users.noreply.github.com: Chayanonjackal
 61612323+Laughing-q@users.noreply.github.com: Laughing-q
 62214284+Burhan-Q@users.noreply.github.com: Burhan-Q
 68285002+Kayzwer@users.noreply.github.com: Kayzwer

ultralytics/cfg/default.yaml

@@ -11,7 +11,7 @@ epochs: 100 # (int) number of epochs to train for
 time: # (float, optional) number of hours to train for, overrides epochs if supplied
 patience: 100 # (int) epochs to wait for no observable improvement for early stopping of training
 batch: 16 # (int) number of images per batch (-1 for AutoBatch)
-imgsz: 640 # (int | list) input images size as int for train and val modes, or list[w,h] for predict and export modes
+imgsz: 640 # (int | list) input images size as int for train and val modes, or list[h,w] for predict and export modes
 save: True # (bool) save train checkpoints and predict results
 save_period: -1 # (int) Save checkpoint every x epochs (disabled if < 1)
 cache: False # (bool) True/ram, disk or False. Use cache for data loading

ultralytics/cfg/models/v10/yolov10b.yaml

@@ -3,7 +3,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
   # [depth, width, max_channels]
   b: [0.67, 1.00, 512]
 
@@ -21,7 +21,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv8.0n head
+# YOLOv10.0n head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

ultralytics/cfg/models/v10/yolov10l.yaml

@@ -3,7 +3,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
   # [depth, width, max_channels]
   l: [1.00, 1.00, 512]
 
@@ -21,7 +21,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv8.0n head
+# YOLOv10.0n head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

ultralytics/cfg/models/v10/yolov10m.yaml

@@ -3,7 +3,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
   # [depth, width, max_channels]
   m: [0.67, 0.75, 768]
 
@@ -21,7 +21,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv8.0n head
+# YOLOv10.0n head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

ultralytics/cfg/models/v10/yolov10n.yaml

@@ -3,7 +3,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024]
 
@@ -21,7 +21,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv8.0n head
+# YOLOv10.0n head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

ultralytics/cfg/models/v10/yolov10s.yaml

@@ -3,7 +3,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
   # [depth, width, max_channels]
   s: [0.33, 0.50, 1024]
 
@@ -21,7 +21,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv8.0n head
+# YOLOv10.0n head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

ultralytics/cfg/models/v10/yolov10x.yaml

@@ -3,7 +3,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
   # [depth, width, max_channels]
   x: [1.00, 1.25, 512]
 
@@ -21,7 +21,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv8.0n head
+# YOLOv10.0n head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

ultralytics/solutions/ai_gym.py

@@ -53,24 +53,29 @@ class AIGym:
 
         # Check if environment supports imshow
         self.env_check = check_imshow(warn=True)
+        self.count = list()
+        self.angle = list()
+        self.stage = list()
 
-    def start_counting(self, im0, results, frame_count):
+    def start_counting(self, im0, results):
         """
         Function used to count the gym steps.
 
         Args:
             im0 (ndarray): Current frame from the video stream.
             results (list): Pose estimation data.
-            frame_count (int): Current frame count.
         """
 
         self.im0 = im0
 
-        # Initialize count, angle, and stage lists on the first frame
+        if not len(results[0]):
-        if frame_count == 1:
+            return self.im0
-            self.count = [0] * len(results[0])
+
-            self.angle = [0] * len(results[0])
+        if len(results[0]) > len(self.count):
-            self.stage = ["-" for _ in results[0]]
+            new_human = len(results[0]) - len(self.count)
+            self.count += [0] * new_human
+            self.angle += [0] * new_human
+            self.stage += ["-"] * new_human
 
         self.keypoints = results[0].keypoints.data
         self.annotator = Annotator(im0, line_width=self.tf)