ultralytics 8.3.16__tar.gz → 8.3.17__tar.gz

{ultralytics-8.3.16/ultralytics.egg-info → ultralytics-8.3.17}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.3.16
+Version: 8.3.17
 Summary: Ultralytics YOLO 🚀 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>

{ultralytics-8.3.16 → ultralytics-8.3.17}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.3.16"
+__version__ = "8.3.17"
 
 import os
 

{ultralytics-8.3.16 → ultralytics-8.3.17}/ultralytics/cfg/__init__.py

@@ -438,34 +438,60 @@ def check_dict_alignment(base: Dict, custom: Dict, e=None):
 
 def merge_equals_args(args: List[str]) -> List[str]:
     """
-    Merges arguments around isolated '=' in a list of strings, handling three cases:
-    1. ['arg', '=', 'val'] becomes ['arg=val'],
-    2. ['arg=', 'val'] becomes ['arg=val'],
-    3. ['arg', '=val'] becomes ['arg=val'].
+    Merges arguments around isolated '=' in a list of strings and joins fragments with brackets.
+
+    This function handles the following cases:
+    1. ['arg', '=', 'val'] becomes ['arg=val']
+    2. ['arg=', 'val'] becomes ['arg=val']
+    3. ['arg', '=val'] becomes ['arg=val']
+    4. Joins fragments with brackets, e.g., ['imgsz=[3,', '640,', '640]'] becomes ['imgsz=[3,640,640]']
 
     Args:
-        args (List[str]): A list of strings where each element represents an argument.
+        args (List[str]): A list of strings where each element represents an argument or fragment.
 
     Returns:
-        (List[str]): A list of strings where the arguments around isolated '=' are merged.
+        List[str]: A list of strings where the arguments around isolated '=' are merged and fragments with brackets are joined.
 
     Examples:
-        >>> args = ["arg1", "=", "value", "arg2=", "value2", "arg3", "=value3"]
-        >>> merge_equals_args(args)
-        ['arg1=value', 'arg2=value2', 'arg3=value3']
+        >>> args = ["arg1", "=", "value", "arg2=", "value2", "arg3", "=value3", "imgsz=[3,", "640,", "640]"]
+        >>> merge_and_join_args(args)
+        ['arg1=value', 'arg2=value2', 'arg3=value3', 'imgsz=[3,640,640]']
     """
     new_args = []
-    for i, arg in enumerate(args):
+    current = ""
+    depth = 0
+
+    i = 0
+    while i < len(args):
+        arg = args[i]
+
+        # Handle equals sign merging
         if arg == "=" and 0 < i < len(args) - 1:  # merge ['arg', '=', 'val']
             new_args[-1] += f"={args[i + 1]}"
-            del args[i + 1]
+            i += 2
+            continue
         elif arg.endswith("=") and i < len(args) - 1 and "=" not in args[i + 1]:  # merge ['arg=', 'val']
             new_args.append(f"{arg}{args[i + 1]}")
-            del args[i + 1]
+            i += 2
+            continue
         elif arg.startswith("=") and i > 0:  # merge ['arg', '=val']
             new_args[-1] += arg
-        else:
-            new_args.append(arg)
+            i += 1
+            continue
+
+        # Handle bracket joining
+        depth += arg.count("[") - arg.count("]")
+        current += arg
+        if depth == 0:
+            new_args.append(current)
+            current = ""
+
+        i += 1
+
+    # Append any remaining current string
+    if current:
+        new_args.append(current)
+
     return new_args
 
 

{ultralytics-8.3.16 → ultralytics-8.3.17}/ultralytics/nn/modules/head.py

@@ -28,6 +28,7 @@ class Detect(nn.Module):
     shape = None
     anchors = torch.empty(0)  # init
     strides = torch.empty(0)  # init
+    legacy = False  # backward compatibility for v3/v5/v8/v9 models
 
     def __init__(self, nc=80, ch=()):
         """Initializes the YOLO detection layer with specified number of classes and channels."""
@@ -41,13 +42,17 @@ class Detect(nn.Module):
         self.cv2 = nn.ModuleList(
             nn.Sequential(Conv(x, c2, 3), Conv(c2, c2, 3), nn.Conv2d(c2, 4 * self.reg_max, 1)) for x in ch
         )
-        self.cv3 = nn.ModuleList(
-            nn.Sequential(
-                nn.Sequential(DWConv(x, x, 3), Conv(x, c3, 1)),
-                nn.Sequential(DWConv(c3, c3, 3), Conv(c3, c3, 1)),
-                nn.Conv2d(c3, self.nc, 1),
+        self.cv3 = (
+            nn.ModuleList(nn.Sequential(Conv(x, c3, 3), Conv(c3, c3, 3), nn.Conv2d(c3, self.nc, 1)) for x in ch)
+            if self.legacy
+            else nn.ModuleList(
+                nn.Sequential(
+                    nn.Sequential(DWConv(x, x, 3), Conv(x, c3, 1)),
+                    nn.Sequential(DWConv(c3, c3, 3), Conv(c3, c3, 1)),
+                    nn.Conv2d(c3, self.nc, 1),
+                )
+                for x in ch
             )
-            for x in ch
         )
         self.dfl = DFL(self.reg_max) if self.reg_max > 1 else nn.Identity()
 

{ultralytics-8.3.16 → ultralytics-8.3.17}/ultralytics/nn/tasks.py

@@ -936,6 +936,7 @@ def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
     import ast
 
     # Args
+    legacy = True  # backward compatibility for v3/v5/v8/v9 models
     max_channels = float("inf")
     nc, act, scales = (d.get(x) for x in ("nc", "activation", "scales"))
     depth, width, kpt_shape = (d.get(x, 1.0) for x in ("depth_multiple", "width_multiple", "kpt_shape"))
@@ -1027,8 +1028,10 @@ def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
             }:
                 args.insert(2, n)  # number of repeats
                 n = 1
-            if m is C3k2 and scale in "mlx":  # for M/L/X sizes
-                args[3] = True
+            if m is C3k2:  # for M/L/X sizes
+                legacy = False
+                if scale in "mlx":
+                    args[3] = True
         elif m is AIFI:
             args = [ch[f], *args]
         elif m in {HGStem, HGBlock}:
@@ -1047,6 +1050,8 @@ def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
             args.append([ch[x] for x in f])
             if m is Segment:
                 args[2] = make_divisible(min(args[2], max_channels) * width, 8)
+            if m in {Detect, Segment, Pose, OBB}:
+                m.legacy = legacy
         elif m is RTDETRDecoder:  # special case, channels arg must be passed in index 1
             args.insert(1, [ch[x] for x in f])
         elif m is CBLinear:

{ultralytics-8.3.16 → ultralytics-8.3.17/ultralytics.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.3.16
+Version: 8.3.17
 Summary: Ultralytics YOLO 🚀 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>