ultralytics 8.2.37__py3-none-any.whl → 8.2.39__py3-none-any.whl

tests/test_python.py

@@ -577,3 +577,12 @@ def test_yolo_world():
         close_mosaic=1,
         trainer=WorldTrainerFromScratch,
     )
+
+
+def test_yolov10():
+    """A simple test for yolov10 for now."""
+    model = YOLO("yolov10n.yaml")
+    # train/val/predict
+    model.train(data="coco8.yaml", epochs=1, imgsz=32, close_mosaic=1, cache="disk")
+    model.val(data="coco8.yaml", imgsz=32)
+    model(SOURCE)

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.2.37"
+__version__ = "8.2.39"
 
 import os
 

ultralytics/cfg/models/v10/yolov10b.yaml

@@ -0,0 +1,42 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLOv10 object detection model. For Usage examples see https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  b: [0.67, 1.00, 512]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 3, C2f, [128, True]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 6, C2f, [256, True]]
+  - [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2fCIB, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv8.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, C2fCIB, [512, True]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10l.yaml

@@ -0,0 +1,42 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLOv10 object detection model. For Usage examples see https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  l: [1.00, 1.00, 512]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 3, C2f, [128, True]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 6, C2f, [256, True]]
+  - [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2fCIB, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv8.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, C2fCIB, [512, True]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10m.yaml

@@ -0,0 +1,42 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLOv10 object detection model. For Usage examples see https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  m: [0.67, 0.75, 768]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 3, C2f, [128, True]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 6, C2f, [256, True]]
+  - [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2fCIB, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv8.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, C2f, [512]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10n.yaml

@@ -0,0 +1,42 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLOv10 object detection model. For Usage examples see https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.33, 0.25, 1024]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 3, C2f, [128, True]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 6, C2f, [256, True]]
+  - [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2f, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv8.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, C2f, [512]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2f, [512]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10s.yaml

@@ -0,0 +1,42 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLOv10 object detection model. For Usage examples see https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  s: [0.33, 0.50, 1024]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 3, C2f, [128, True]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 6, C2f, [256, True]]
+  - [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2f, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2fCIB, [1024, True, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv8.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, C2f, [512]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2f, [512]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10x.yaml

@@ -0,0 +1,42 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLOv10 object detection model. For Usage examples see https://docs.ultralytics.com/tasks/detect
+
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  x: [1.00, 1.25, 512]
+
+backbone:
+  # [from, repeats, module, args]
+  - [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
+  - [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
+  - [-1, 3, C2f, [128, True]]
+  - [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
+  - [-1, 6, C2f, [256, True]]
+  - [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
+  - [-1, 6, C2fCIB, [512, True]]
+  - [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
+  - [-1, 3, C2fCIB, [1024, True]]
+  - [-1, 1, SPPF, [1024, 5]] # 9
+  - [-1, 1, PSA, [1024]] # 10
+
+# YOLOv8.0n head
+head:
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 6], 1, Concat, [1]] # cat backbone P4
+  - [-1, 3, C2fCIB, [512, True]] # 13
+
+  - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
+  - [[-1, 4], 1, Concat, [1]] # cat backbone P3
+  - [-1, 3, C2f, [256]] # 16 (P3/8-small)
+
+  - [-1, 1, Conv, [256, 3, 2]]
+  - [[-1, 13], 1, Concat, [1]] # cat head P4
+  - [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
+
+  - [-1, 1, SCDown, [512, 3, 2]]
+  - [[-1, 10], 1, Concat, [1]] # cat head P5
+  - [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
+
+  - [[16, 19, 22], 1, v10Detect, [nc]] # Detect(P3, P4, P5)

ultralytics/cfg/models/v8/yolov8-p6.yaml

@@ -5,11 +5,11 @@
 nc: 80 # number of classes
 scales: # model compound scaling constants, i.e. 'model=yolov8n-p6.yaml' will call yolov8-p6.yaml with scale 'n'
   # [depth, width, max_channels]
-  n: [0.33, 0.25, 1024]
-  s: [0.33, 0.50, 1024]
-  m: [0.67, 0.75, 768]
-  l: [1.00, 1.00, 512]
-  x: [1.00, 1.25, 512]
+  n: [0.33, 0.25, 1024] # YOLOv8n-p6 summary (fused): 220 layers, 4976656 parameters, 42560 gradients, 8.7 GFLOPs
+  s: [0.33, 0.50, 1024] # YOLOv8s-p6 summary (fused): 220 layers, 17897168 parameters, 57920 gradients, 28.5 GFLOPs
+  m: [0.67, 0.75, 768] # YOLOv8m-p6 summary (fused): 285 layers, 44862352 parameters, 78400 gradients, 83.1 GFLOPs
+  l: [1.00, 1.00, 512] # YOLOv8l-p6 summary (fused): 350 layers, 62351440 parameters, 98880 gradients, 167.3 GFLOPs
+  x: [1.00, 1.25, 512] # YOLOv8x-p6 summary (fused): 350 layers, 97382352 parameters, 123456 gradients, 261.1 GFLOPs
 
 # YOLOv8.0x6 backbone
 backbone:

ultralytics/data/augment.py

@@ -1223,16 +1223,13 @@ def classify_transforms(
     else:
         # Resize the shortest edge to matching target dim for non-square target
         tfl = [T.Resize(scale_size)]
-    tfl += [T.CenterCrop(size)]
-
-    tfl += [
-        T.ToTensor(),
-        T.Normalize(
-            mean=torch.tensor(mean),
-            std=torch.tensor(std),
-        ),
-    ]
-
+    tfl.extend(
+        [
+            T.CenterCrop(size),
+            T.ToTensor(),
+            T.Normalize(mean=torch.tensor(mean), std=torch.tensor(std)),
+        ]
+    )
     return T.Compose(tfl)
 
 
@@ -1284,9 +1281,9 @@ def classify_augmentations(
     ratio = tuple(ratio or (3.0 / 4.0, 4.0 / 3.0))  # default imagenet ratio range
     primary_tfl = [T.RandomResizedCrop(size, scale=scale, ratio=ratio, interpolation=interpolation)]
     if hflip > 0.0:
-        primary_tfl += [T.RandomHorizontalFlip(p=hflip)]
+        primary_tfl.append(T.RandomHorizontalFlip(p=hflip))
     if vflip > 0.0:
-        primary_tfl += [T.RandomVerticalFlip(p=vflip)]
+        primary_tfl.append(T.RandomVerticalFlip(p=vflip))
 
     secondary_tfl = []
     disable_color_jitter = False
@@ -1298,19 +1295,19 @@ def classify_augmentations(
 
         if auto_augment == "randaugment":
             if TORCHVISION_0_11:
-                secondary_tfl += [T.RandAugment(interpolation=interpolation)]
+                secondary_tfl.append(T.RandAugment(interpolation=interpolation))
             else:
                 LOGGER.warning('"auto_augment=randaugment" requires torchvision >= 0.11.0. Disabling it.')
 
         elif auto_augment == "augmix":
             if TORCHVISION_0_13:
-                secondary_tfl += [T.AugMix(interpolation=interpolation)]
+                secondary_tfl.append(T.AugMix(interpolation=interpolation))
             else:
                 LOGGER.warning('"auto_augment=augmix" requires torchvision >= 0.13.0. Disabling it.')
 
         elif auto_augment == "autoaugment":
             if TORCHVISION_0_10:
-                secondary_tfl += [T.AutoAugment(interpolation=interpolation)]
+                secondary_tfl.append(T.AutoAugment(interpolation=interpolation))
             else:
                 LOGGER.warning('"auto_augment=autoaugment" requires torchvision >= 0.10.0. Disabling it.')
 
@@ -1321,7 +1318,7 @@ def classify_augmentations(
             )
 
     if not disable_color_jitter:
-        secondary_tfl += [T.ColorJitter(brightness=hsv_v, contrast=hsv_v, saturation=hsv_s, hue=hsv_h)]
+        secondary_tfl.append(T.ColorJitter(brightness=hsv_v, contrast=hsv_v, saturation=hsv_s, hue=hsv_h))
 
     final_tfl = [
         T.ToTensor(),

ultralytics/data/converter.py

@@ -329,8 +329,7 @@ def convert_coco(
 
         if lvis:
             with open((Path(save_dir) / json_file.name.replace("lvis_v1_", "").replace(".json", ".txt")), "a") as f:
-                for l in image_txt:
-                    f.write(f"{l}\n")
+                f.writelines(f"{line}\n" for line in image_txt)
 
     LOGGER.info(f"{'LVIS' if lvis else 'COCO'} data converted successfully.\nResults saved to {save_dir.resolve()}")
 
@@ -534,25 +533,25 @@ def yolo_bbox2segment(im_dir, save_dir=None, sam_model="sam_b.pt"):
 
     LOGGER.info("Detection labels detected, generating segment labels by SAM model!")
     sam_model = SAM(sam_model)
-    for l in tqdm(dataset.labels, total=len(dataset.labels), desc="Generating segment labels"):
-        h, w = l["shape"]
-        boxes = l["bboxes"]
+    for label in tqdm(dataset.labels, total=len(dataset.labels), desc="Generating segment labels"):
+        h, w = label["shape"]
+        boxes = label["bboxes"]
         if len(boxes) == 0:  # skip empty labels
             continue
         boxes[:, [0, 2]] *= w
         boxes[:, [1, 3]] *= h
-        im = cv2.imread(l["im_file"])
+        im = cv2.imread(label["im_file"])
         sam_results = sam_model(im, bboxes=xywh2xyxy(boxes), verbose=False, save=False)
-        l["segments"] = sam_results[0].masks.xyn
+        label["segments"] = sam_results[0].masks.xyn
 
     save_dir = Path(save_dir) if save_dir else Path(im_dir).parent / "labels-segment"
     save_dir.mkdir(parents=True, exist_ok=True)
-    for l in dataset.labels:
+    for label in dataset.labels:
         texts = []
-        lb_name = Path(l["im_file"]).with_suffix(".txt").name
+        lb_name = Path(label["im_file"]).with_suffix(".txt").name
         txt_file = save_dir / lb_name
-        cls = l["cls"]
-        for i, s in enumerate(l["segments"]):
+        cls = label["cls"]
+        for i, s in enumerate(label["segments"]):
             line = (int(cls[i]), *s.reshape(-1))
             texts.append(("%g " * len(line)).rstrip() % line)
         if texts:

ultralytics/data/split_dota.py

@@ -26,8 +26,8 @@ def bbox_iof(polygon1, bbox2, eps=1e-6):
         bbox2 (np.ndarray): Bounding boxes, (n ,4).
     """
     polygon1 = polygon1.reshape(-1, 4, 2)
-    lt_point = np.min(polygon1, axis=-2)
-    rb_point = np.max(polygon1, axis=-2)
+    lt_point = np.min(polygon1, axis=-2)  # left-top
+    rb_point = np.max(polygon1, axis=-2)  # right-bottom
     bbox1 = np.concatenate([lt_point, rb_point], axis=-1)
 
     lt = np.maximum(bbox1[:, None, :2], bbox2[..., :2])
@@ -35,8 +35,8 @@ def bbox_iof(polygon1, bbox2, eps=1e-6):
     wh = np.clip(rb - lt, 0, np.inf)
     h_overlaps = wh[..., 0] * wh[..., 1]
 
-    l, t, r, b = (bbox2[..., i] for i in range(4))
-    polygon2 = np.stack([l, t, r, t, r, b, l, b], axis=-1).reshape(-1, 4, 2)
+    left, top, right, bottom = (bbox2[..., i] for i in range(4))
+    polygon2 = np.stack([left, top, right, top, right, bottom, left, bottom], axis=-1).reshape(-1, 4, 2)
 
     sg_polys1 = [Polygon(p) for p in polygon1]
     sg_polys2 = [Polygon(p) for p in polygon2]

ultralytics/engine/exporter.py

@@ -388,7 +388,7 @@ class Exporter:
         """YOLOv8 ONNX export."""
         requirements = ["onnx>=1.12.0"]
         if self.args.simplify:
-            requirements += ["onnxslim==0.1.28", "onnxruntime" + ("-gpu" if torch.cuda.is_available() else "")]
+            requirements += ["onnxslim>=0.1.31", "onnxruntime" + ("-gpu" if torch.cuda.is_available() else "")]
         check_requirements(requirements)
         import onnx  # noqa
 
@@ -827,7 +827,7 @@ class Exporter:
                 "onnx>=1.12.0",
                 "onnx2tf>1.17.5,<=1.22.3",
                 "sng4onnx>=1.0.1",
-                "onnxslim==0.1.28",
+                "onnxslim>=0.1.31",
                 "onnx_graphsurgeon>=0.3.26",
                 "tflite_support<=0.4.3" if IS_JETSON else "tflite_support",  # fix ImportError 'GLIBCXX_3.4.29'
                 "flatbuffers>=23.5.26,<100",  # update old 'flatbuffers' included inside tensorflow package
@@ -920,6 +920,7 @@ class Exporter:
     @try_export
     def export_tflite(self, keras_model, nms, agnostic_nms, prefix=colorstr("TensorFlow Lite:")):
         """YOLOv8 TensorFlow Lite export."""
+        # BUG https://github.com/ultralytics/ultralytics/issues/13436
         import tensorflow as tf  # noqa
 
         LOGGER.info(f"\n{prefix} starting export with tensorflow {tf.__version__}...")

ultralytics/engine/model.py

@@ -142,7 +142,6 @@ class Model(nn.Module):
         # Check if Triton Server model
         elif self.is_triton_model(model):
             self.model_name = self.model = model
-            self.task = task
             return
 
         # Load or create new YOLO model

ultralytics/models/sam/modules/tiny_encoder.py

@@ -384,8 +384,8 @@ class TinyViTBlock(nn.Module):
         convolution.
         """
         h, w = self.input_resolution
-        b, l, c = x.shape
-        assert l == h * w, "input feature has wrong size"
+        b, hw, c = x.shape  # batch, height*width, channels
+        assert hw == h * w, "input feature has wrong size"
         res_x = x
         if h == self.window_size and w == self.window_size:
             x = self.attn(x)
@@ -394,13 +394,13 @@ class TinyViTBlock(nn.Module):
             pad_b = (self.window_size - h % self.window_size) % self.window_size
             pad_r = (self.window_size - w % self.window_size) % self.window_size
             padding = pad_b > 0 or pad_r > 0
-
             if padding:
                 x = F.pad(x, (0, 0, 0, pad_r, 0, pad_b))
 
             pH, pW = h + pad_b, w + pad_r
             nH = pH // self.window_size
             nW = pW // self.window_size
+
             # Window partition
             x = (
                 x.view(b, nH, self.window_size, nW, self.window_size, c)
@@ -408,19 +408,18 @@ class TinyViTBlock(nn.Module):
                 .reshape(b * nH * nW, self.window_size * self.window_size, c)
             )
             x = self.attn(x)
+
             # Window reverse
             x = x.view(b, nH, nW, self.window_size, self.window_size, c).transpose(2, 3).reshape(b, pH, pW, c)
-
             if padding:
                 x = x[:, :h, :w].contiguous()
 
-            x = x.view(b, l, c)
+            x = x.view(b, hw, c)
 
         x = res_x + self.drop_path(x)
-
         x = x.transpose(1, 2).reshape(b, c, h, w)
         x = self.local_conv(x)
-        x = x.view(b, c, l).transpose(1, 2)
+        x = x.view(b, c, hw).transpose(1, 2)
 
         return x + self.drop_path(self.mlp(x))
 

ultralytics/nn/modules/__init__.py

@@ -22,18 +22,22 @@ from .block import (
     C2,
     C3,
     C3TR,
+    CIB,
     DFL,
     ELAN1,
+    PSA,
     SPP,
     SPPELAN,
     SPPF,
     AConv,
     ADown,
+    Attention,
     BNContrastiveHead,
     Bottleneck,
     BottleneckCSP,
     C2f,
     C2fAttn,
+    C2fCIB,
     C3Ghost,
     C3x,
     CBFuse,
@@ -46,7 +50,9 @@ from .block import (
     Proto,
     RepC3,
     RepNCSPELAN4,
+    RepVGGDW,
     ResNetLayer,
+    SCDown,
 )
 from .conv import (
     CBAM,
@@ -63,7 +69,7 @@ from .conv import (
     RepConv,
     SpatialAttention,
 )
-from .head import OBB, Classify, Detect, Pose, RTDETRDecoder, Segment, WorldDetect
+from .head import OBB, Classify, Detect, Pose, RTDETRDecoder, Segment, WorldDetect, v10Detect
 from .transformer import (
     AIFI,
     MLP,
@@ -127,6 +133,7 @@ __all__ = (
     "ResNetLayer",
     "OBB",
     "WorldDetect",
+    "v10Detect",
     "ImagePoolingAttn",
     "ContrastiveHead",
     "BNContrastiveHead",
@@ -137,4 +144,10 @@ __all__ = (
     "CBLinear",
     "AConv",
     "ELAN1",
+    "RepVGGDW",
+    "CIB",
+    "C2fCIB",
+    "Attention",
+    "PSA",
+    "SCDown",
 )