ultralytics 8.3.108__py3-none-any.whl → 8.3.109__py3-none-any.whl

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.108"
+__version__ = "8.3.109"
 
 import os
 

ultralytics/engine/exporter.py

@@ -813,7 +813,7 @@ class Exporter:
         scale = 1 / 255
         classifier_config = None
         if self.model.task == "classify":
-            classifier_config = ct.ClassifierConfig(list(self.model.names.values())) if self.args.nms else None
+            classifier_config = ct.ClassifierConfig(list(self.model.names.values()))
             model = self.model
         elif self.model.task == "detect":
             model = IOSDetectModel(self.model, self.im) if self.args.nms else self.model

ultralytics/engine/trainer.py

@@ -457,8 +457,8 @@ class BaseTrainer:
                 self.scheduler.last_epoch = self.epoch  # do not move
                 self.stop |= epoch >= self.epochs  # stop if exceeded epochs
             self.run_callbacks("on_fit_epoch_end")
-            if self._get_memory(fraction=True) > 0.9:
-                self._clear_memory()  # clear if memory utilization > 90%
+            if self._get_memory(fraction=True) > 0.5:
+                self._clear_memory()  # clear if memory utilization > 50%
 
             # Early Stopping
             if RANK != -1:  # if DDP training

ultralytics/models/rtdetr/val.py

@@ -143,12 +143,10 @@ class RTDETRValidator(DetectionValidator):
         for i, bbox in enumerate(bboxes):  # (300, 4)
             bbox = ops.xywh2xyxy(bbox)
             score, cls = scores[i].max(-1)  # (300, )
-            # Do not need threshold for evaluation as only got 300 boxes here
-            # idx = score > self.args.conf
             pred = torch.cat([bbox, score[..., None], cls[..., None]], dim=-1)  # filter
             # Sort by confidence to correctly get internal metrics
             pred = pred[score.argsort(descending=True)]
-            outputs[i] = pred  # [idx]
+            outputs[i] = pred[score > self.args.conf]
 
         return outputs
 

ultralytics/utils/autobatch.py

@@ -86,8 +86,8 @@ def autobatch(model, imgsz=640, fraction=0.60, batch_size=DEFAULT_CFG.batch, max
             and (i == 0 or not results[i - 1] or y[2] > results[i - 1][2])  # first item or increasing memory
         ]
         fit_x, fit_y = zip(*xy) if xy else ([], [])
-        p = np.polyfit(np.log(fit_x), np.log(fit_y), deg=1)  # first-degree polynomial fit in log space
-        b = int(round(np.exp((np.log(f * fraction) - p[1]) / p[0])))  # y intercept (optimal batch size)
+        p = np.polyfit(fit_x, fit_y, deg=1)  # first-degree polynomial fit in log space
+        b = int((round(f * fraction) - p[1]) / p[0])  # y intercept (optimal batch size)
         if None in results:  # some sizes failed
             i = results.index(None)  # first fail index
             if b >= batch_sizes[i]:  # y intercept above failure point
@@ -96,7 +96,7 @@ def autobatch(model, imgsz=640, fraction=0.60, batch_size=DEFAULT_CFG.batch, max
             LOGGER.info(f"{prefix}WARNING ⚠️ batch={b} outside safe range, using default batch-size {batch_size}.")
             b = batch_size
 
-        fraction = (np.exp(np.polyval(p, np.log(b))) + r + a) / t  # predicted fraction
+        fraction = (np.polyval(p, b) + r + a) / t  # predicted fraction
         LOGGER.info(f"{prefix}Using batch-size {b} for {d} {t * fraction:.2f}G/{t:.2f}G ({fraction * 100:.0f}%) ✅")
         return b
     except Exception as e:

ultralytics/utils/checks.py

@@ -890,5 +890,6 @@ check_torchvision()  # check torch-torchvision compatibility
 
 # Define constants
 IS_PYTHON_MINIMUM_3_10 = check_python("3.10", hard=False)
+IS_PYTHON_3_11 = PYTHON_VERSION.startswith("3.11")
 IS_PYTHON_3_12 = PYTHON_VERSION.startswith("3.12")
 IS_PYTHON_3_13 = PYTHON_VERSION.startswith("3.13")

{ultralytics-8.3.108.dist-info → ultralytics-8.3.109.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.108
+Version: 8.3.109
 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-8.3.108.dist-info → ultralytics-8.3.109.dist-info}/RECORD

@@ -1,4 +1,4 @@
-ultralytics/__init__.py,sha256=ihzQQ3TdLAuJ4ZYoKETGLRD-wxI8Bh9DRKvuM_sU12k,730
+ultralytics/__init__.py,sha256=tTjnpkRXWYl2pbPaYIAqZyl6F8jys30t6Xa7IwdCIp8,730
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
 ultralytics/cfg/__init__.py,sha256=HZdpo0m_8NynZLmTie2dDx-OEZH7WoM8YtALjB7lKgM,39838
@@ -102,11 +102,11 @@ ultralytics/data/loaders.py,sha256=_Gyp_BfGTZwsFdn4UnolXxdU_sAYZLIrv0L2TRI9R5g,2
 ultralytics/data/split_dota.py,sha256=p8eVGht9tABSVbf9vwvxA_AQYEva3IGHePKlMeNrn64,11872
 ultralytics/data/utils.py,sha256=aRPwIoLrCML_Kcd0dI9B6c5Ct4dvhdF36rDHtuf7Ww4,33217
 ultralytics/engine/__init__.py,sha256=lm6MckFYCPTbqIoX7w0s_daxdjNeBeKW6DXppv1-QUM,70
-ultralytics/engine/exporter.py,sha256=eGP2x38VreRmtBzGt0iNRiow_lNxZuQbhGQ7v5YQxrU,73952
+ultralytics/engine/exporter.py,sha256=Nz2ytl_wSLjtW1mc2hSv5QiWt5CMcJarJu8sijcyDd0,73925
 ultralytics/engine/model.py,sha256=YgQKYZrPENSTvLENspg-bXI9FinzzWARfb0U-C9vH-M,52916
 ultralytics/engine/predictor.py,sha256=hXDF7d03rtVzoEQBW1tMN665-TALIyM1q7kXARJlmKM,21630
 ultralytics/engine/results.py,sha256=H3pFJhUjYKvVyOUqqZjfIn8vnCpl81aYNOnregMrBoQ,79716
-ultralytics/engine/trainer.py,sha256=KAeiNoH5NIRhQPIfr5AhVwDerk9dy0-QJu-FlxtG4xA,38904
+ultralytics/engine/trainer.py,sha256=CdCkH0ky8cqqVQHZQf4rQ_f5wKz98sYwY6Z83uLDrwY,38904
 ultralytics/engine/tuner.py,sha256=CW6Ys4NV6SVScXA5GQO5DeSIJWys9e_mqUg26b6NYu4,12598
 ultralytics/engine/validator.py,sha256=Xijg74RHn43ANjQJaBJ4zZkWd0MMPUH2TzfmydAMbzk,16974
 ultralytics/hub/__init__.py,sha256=wDtAUKdfqob95tfFHgDJFXcsNSDSdoIQkJTm-CfIUTI,6616
@@ -128,7 +128,7 @@ ultralytics/models/rtdetr/__init__.py,sha256=_jEHmOjI_QP_nT3XJXLgYHQ6bXG4EL8Gnvn
 ultralytics/models/rtdetr/model.py,sha256=zx9UKpReYCRL7Is2DXIX9ZcJE25KE_fPZ-NYx5vF6E4,2119
 ultralytics/models/rtdetr/predict.py,sha256=5VNvyULxegg_NfGo7ugfIKHrtKhpaspJZdagU1haQmo,3942
 ultralytics/models/rtdetr/train.py,sha256=YONMv5RjLuO29Ab_tuHtgrlBfsicCGQeAvYDVeL02bs,4144
-ultralytics/models/rtdetr/val.py,sha256=xo6B02EgLKqMf9nAwpRVwslIg_UUzivE3UFoALc8ohE,7407
+ultralytics/models/rtdetr/val.py,sha256=MfX3drVsGOqbK0au-ZroDNfeYXmFCSembfElFmuFGuI,7301
 ultralytics/models/sam/__init__.py,sha256=iR7B06rAEni21eptg8n4rLOP0Z_qV9y9PL-L93n4_7s,266
 ultralytics/models/sam/amg.py,sha256=r_duG0DCeCyTYfhcVh-ti10FPMl4VGL4SKc8yvbQpNU,11050
 ultralytics/models/sam/build.py,sha256=Vhml3zBGDcRO-efauNdM0ZlKTV10ADAj_aT823lPJv8,12515
@@ -215,9 +215,9 @@ ultralytics/trackers/utils/gmc.py,sha256=NnLxtgZIKdO5-C_J0xqeob1iRXgpubyJOgbIEeJ
 ultralytics/trackers/utils/kalman_filter.py,sha256=A0CqOnnaKH6kr0XwuHzyHmIU6aJAjJYxF9jVlNBKZHo,21326
 ultralytics/trackers/utils/matching.py,sha256=7eIufSdeN7cXuFMjvcfvz0Ldq84m4YKZl5IGxBR8IIo,7169
 ultralytics/utils/__init__.py,sha256=-OY2ZAJdN7XLPSG1dpnWWv63ZqmhzAxrio2dMGXuyEg,50254
-ultralytics/utils/autobatch.py,sha256=KnvmNSAO_6H3ZLJ4fOFMTFbOaMlbp025LiJqrdKIz8c,4998
+ultralytics/utils/autobatch.py,sha256=0QSSYfzZIcHbbE5udrhRofJiJru20YaO7I1D8nhJHhc,4950
 ultralytics/utils/benchmarks.py,sha256=7xJ7I0XqLXE-51_OCETKdfMKpk1zUkMTq0kCbdMsMks,30359
-ultralytics/utils/checks.py,sha256=d30cJY1G3wBWWTlq3C3yGVmDhAUtfXa9U3nuTO4sXQo,32677
+ultralytics/utils/checks.py,sha256=J2ebkGG1QBbYIrBjwlfECiJtDJzqFkAg_Nn9pdRsW_c,32728
 ultralytics/utils/dist.py,sha256=M8svPWdrRDcSmqIBGrqIaV8yi98Z3HUhXwsauDjVlkM,4090
 ultralytics/utils/downloads.py,sha256=4P1JIc04tTd_oz3-AHlhRSGaVtnSQPg_gYlh__U27-4,22169
 ultralytics/utils/errors.py,sha256=vY9h2evFSrHnZdHJVVrmm8Zzw4qVDLyo9DeYW5g0dFk,1573
@@ -244,9 +244,9 @@ ultralytics/utils/callbacks/neptune.py,sha256=XXnnKQ-MoLIexl8y2Vb0i-cCLyePE0n5BU
 ultralytics/utils/callbacks/raytune.py,sha256=A8amUGpux7dYES-L1iSeMoMXBySGWCD1aUqT7vcG-pU,1284
 ultralytics/utils/callbacks/tensorboard.py,sha256=7eUX21_Ym7i6iN4euZzrqglphyl5xak1yl_-wfFshbg,5502
 ultralytics/utils/callbacks/wb.py,sha256=iDRFXI4IIDm8R5OI89DMTmjs8aHLo1HRCLkOFKdaMG4,7507
-ultralytics-8.3.108.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
-ultralytics-8.3.108.dist-info/METADATA,sha256=MD-pW1ZQjH1xiuXRiomX1tSk9JOZPo6mcWrP-x0Osio,37354
-ultralytics-8.3.108.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-ultralytics-8.3.108.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
-ultralytics-8.3.108.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
-ultralytics-8.3.108.dist-info/RECORD,,
+ultralytics-8.3.109.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+ultralytics-8.3.109.dist-info/METADATA,sha256=IFJeOd0oWz3zDZ9deDgTtFGWE-mRt2nSoQPnoj0QZ7E,37354
+ultralytics-8.3.109.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+ultralytics-8.3.109.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
+ultralytics-8.3.109.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
+ultralytics-8.3.109.dist-info/RECORD,,