dgenerate-ultralytics-headless 8.4.3__py3-none-any.whl → 8.4.4__py3-none-any.whl

{dgenerate_ultralytics_headless-8.4.3.dist-info → dgenerate_ultralytics_headless-8.4.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dgenerate-ultralytics-headless
-Version: 8.4.3
+Version: 8.4.4
 Summary: Automatically built Ultralytics package with python-opencv-headless dependency instead of python-opencv
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>
@@ -120,7 +120,7 @@ The workflow runs automatically every day at midnight UTC to check for new Ultra
 
 <div align="center">
   <p>
-    <a href="https://www.ultralytics.com/events/yolovision?utm_source=github&utm_medium=org&utm_campaign=yv25_event" target="_blank">
+    <a href="https://platform.ultralytics.com/ultralytics/yolo26" target="_blank">
       <img width="100%" src="https://raw.githubusercontent.com/ultralytics/assets/main/yolov8/banner-yolov8.png" alt="Ultralytics YOLO banner"></a>
   </p>
 
@@ -147,8 +147,8 @@ Find detailed documentation in the [Ultralytics Docs](https://docs.ultralytics.c
 
 Request an Enterprise License for commercial use at [Ultralytics Licensing](https://www.ultralytics.com/license).
 
-<a href="https://docs.ultralytics.com/models/yolo11/" target="_blank">
-  <img width="100%" src="https://raw.githubusercontent.com/ultralytics/assets/refs/heads/main/yolo/performance-comparison.png" alt="YOLO11 performance plots">
+<a href="https://platform.ultralytics.com/ultralytics/yolo26" target="_blank">
+  <img width="100%" src="https://raw.githubusercontent.com/ultralytics/assets/refs/heads/main/yolo/performance-comparison.png" alt="YOLO26 performance plots">
 </a>
 
 <div align="center">
@@ -341,8 +341,8 @@ Our key integrations with leading AI platforms extend the functionality of Ultra
 <br>
 
 <div align="center">
-  <a href="https://www.ultralytics.com/hub">
-    <img src="https://github.com/ultralytics/assets/raw/main/partners/logo-ultralytics-hub.png" width="10%" alt="Ultralytics HUB logo"></a>
+  <a href="https://platform.ultralytics.com/ultralytics/yolo26">
+    <img src="https://github.com/ultralytics/assets/raw/main/partners/logo-ultralytics-hub.png" width="10%" alt="Ultralytics Platform logo"></a>
   <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="15%" height="0" alt="space">
   <a href="https://docs.ultralytics.com/integrations/weights-biases/">
     <img src="https://github.com/ultralytics/assets/raw/main/partners/logo-wb.png" width="10%" alt="Weights & Biases logo"></a>
@@ -354,9 +354,9 @@ Our key integrations with leading AI platforms extend the functionality of Ultra
     <img src="https://github.com/ultralytics/assets/raw/main/partners/logo-neuralmagic.png" width="10%" alt="Neural Magic logo"></a>
 </div>
 
-|                                                       Ultralytics HUB 🌟                                                        |                                                          Weights & Biases                                                           |                                                                              Comet                                                                              |                                                        Neural Magic                                                         |
-| :-----------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------: |
-| Streamline YOLO workflows: Label, train, and deploy effortlessly with [Ultralytics HUB](https://hub.ultralytics.com/). Try now! | Track experiments, hyperparameters, and results with [Weights & Biases](https://docs.ultralytics.com/integrations/weights-biases/). | Free forever, [Comet ML](https://docs.ultralytics.com/integrations/comet/) lets you save YOLO models, resume training, and interactively visualize predictions. | Run YOLO inference up to 6x faster with [Neural Magic DeepSparse](https://docs.ultralytics.com/integrations/neural-magic/). |
+|                                                                   Ultralytics Platform 🌟                                                                   |                                                          Weights & Biases                                                           |                                                                              Comet                                                                              |                                                        Neural Magic                                                         |
+| :---------------------------------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------: |
+| Streamline YOLO workflows: Label, train, and deploy effortlessly with [Ultralytics Platform](https://platform.ultralytics.com/ultralytics/yolo26). Try now! | Track experiments, hyperparameters, and results with [Weights & Biases](https://docs.ultralytics.com/integrations/weights-biases/). | Free forever, [Comet ML](https://docs.ultralytics.com/integrations/comet/) lets you save YOLO models, resume training, and interactively visualize predictions. | Run YOLO inference up to 6x faster with [Neural Magic DeepSparse](https://docs.ultralytics.com/integrations/neural-magic/). |
 
 ## 🤝 Contribute
 

{dgenerate_ultralytics_headless-8.4.3.dist-info → dgenerate_ultralytics_headless-8.4.4.dist-info}/RECORD

@@ -1,4 +1,4 @@
-dgenerate_ultralytics_headless-8.4.3.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+dgenerate_ultralytics_headless-8.4.4.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
 tests/__init__.py,sha256=hfUXxYLJB3846OCzWV94ZKEZsi8vq9Pqrdd2mMgjjck,804
 tests/conftest.py,sha256=rlKyDuOC_3ptXrWS8Q19bNEGOupUmYXHj3nB6o1GBGY,2318
 tests/test_cli.py,sha256=GhIFHi-_WIJpDgoGNRi0DnjbfwP1wHbklBMnkCM-P_4,5464
@@ -8,11 +8,11 @@ tests/test_exports.py,sha256=Toy4u-4bsoyAbzNhc9kbMuKqvMKywZxNj5jlFNTzFWs,14670
 tests/test_integrations.py,sha256=FjvTGjXm3bvYHK3_obgObhC5SzHCTzw4aOJV9Hh08jQ,6220
 tests/test_python.py,sha256=np6on3Sa0NNi5pquvilekjKxxedAJMpLOQEthGaIalQ,29284
 tests/test_solutions.py,sha256=1tRlM72YciE42Nk9v83gsXOD5RSx9GSWVsKGhH7-HxE,14122
-ultralytics/__init__.py,sha256=cei9ajuLEweE4RyDoGwvanjvIJe8Z347vRJatW87-JI,1300
+ultralytics/__init__.py,sha256=sJYUdz1Qx-pwzIz34CD4B1PgspkWiGojpY2uQ6D5lE0,1300
 ultralytics/py.typed,sha256=la67KBlbjXN-_-DfGNcdOcjYumVpKG_Tkw-8n5dnGB4,8
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
-ultralytics/cfg/__init__.py,sha256=w-ZCBR5lbL2ef0UhQfK7IvySIOhtPcJTJF0-3tAXObw,40300
+ultralytics/cfg/__init__.py,sha256=_LkOX0ZG8AlWr_NG2KW7E8SQ7DqVeD_vSiYUd2EKXA4,40288
 ultralytics/cfg/default.yaml,sha256=E__q2msvK9XCQngf0YFLpueCer_1tRcMJM0p3ahBdbA,9015
 ultralytics/cfg/datasets/Argoverse.yaml,sha256=QGpdh3Hj5dFrvbsaE_8rAVj9BO4XpKTB7uhXaTTnE-o,3364
 ultralytics/cfg/datasets/DOTAv1.5.yaml,sha256=KE7VC-ZMDSei1pLPm-pdk_ZAMRU_gLwGgtIQNbwp6dA,1212
@@ -133,11 +133,11 @@ ultralytics/data/scripts/get_coco.sh,sha256=UuJpJeo3qQpTHVINeOpmP0NYmg8PhEFE3A8J
 ultralytics/data/scripts/get_coco128.sh,sha256=qmRQl_hOKrsdHrTrnyQuFIH01oDz3lfaz138OgGfLt8,650
 ultralytics/data/scripts/get_imagenet.sh,sha256=hr42H16bM47iT27rgS7MpEo-GeOZAYUQXgr0B2cwn48,1705
 ultralytics/engine/__init__.py,sha256=lm6MckFYCPTbqIoX7w0s_daxdjNeBeKW6DXppv1-QUM,70
-ultralytics/engine/exporter.py,sha256=RCViSGpUjFyUEW6GxhbKfURBW5vCOgCcXtLJKKI8ceM,73429
+ultralytics/engine/exporter.py,sha256=n_DtRhD0jT9sTFb8oQ_TYdQYTQJbsQzwqdISwR-mQY4,73330
 ultralytics/engine/model.py,sha256=euDHUy7J5vVBvS_d-KbGZd_0BP5bF6Y3cTQ7VXtwZ4k,53210
 ultralytics/engine/predictor.py,sha256=tXrHSTHJ-rDQ3lrPW9P5_ei_ewTwbY2sji6MExybJ28,22838
 ultralytics/engine/results.py,sha256=uvD7WqaePkuYbcf-iFqh3DIy5_ZSyHeDiKIzY5VjePM,68181
-ultralytics/engine/trainer.py,sha256=8kAqel2aF2_GZ9Bi-lyf7ykWW_vkGD6dx8z5bPU6zlM,47219
+ultralytics/engine/trainer.py,sha256=lvYPaEkaGXuGnH8j19aMIB2BML3b0LhEqt-HyZ_I6nU,47219
 ultralytics/engine/tuner.py,sha256=F4fyQaC5_GT74TULRO0VhzTv2S_a54cZDc3FjFoqaHE,21840
 ultralytics/engine/validator.py,sha256=DiKsygbNJdRdwXoKoYOJA6bP_T7vMW3Syj_Qc_l7xTM,17761
 ultralytics/hub/__init__.py,sha256=Z0K_E00jzQh90b18q3IDChwVmTvyIYp6C00sCV-n2F8,6709
@@ -208,9 +208,9 @@ ultralytics/models/yolo/pose/predict.py,sha256=6EW9palcAoWX-gu5ROQvO6AxBSm719934
 ultralytics/models/yolo/pose/train.py,sha256=IlmsFlb0TsWZVy6PL3Trr_aXfwwGMBKAHyxnP7VPp_g,4747
 ultralytics/models/yolo/pose/val.py,sha256=0luDccEPb_lUMjzaBb5VMsh9RdXVAbxb3Br57VKWNdc,12004
 ultralytics/models/yolo/segment/__init__.py,sha256=3IThhZ1wlkY9FvmWm9cE-5-ZyE6F1FgzAtQ6jOOFzzw,275
-ultralytics/models/yolo/segment/predict.py,sha256=9CAAjkghFYdGaXYUOcpGZilhwNSnYL2U1Qu_Qc6UtFY,5430
+ultralytics/models/yolo/segment/predict.py,sha256=zLhmSTVEnaUumIX9SbjZH09kr2VrNdYWEss7FvseVuY,5428
 ultralytics/models/yolo/segment/train.py,sha256=nS3qrT7Y3swCwjGZzeDQ2EunC9ilMsOiWs6LaTUCAE4,3021
-ultralytics/models/yolo/segment/val.py,sha256=EDcwcfwgc9eUKgUL9NIlh_rGhlqcNEAWcRT7KtQj6AQ,13286
+ultralytics/models/yolo/segment/val.py,sha256=AvPS4rhV2PFpi0yixUfJhdczXctmZQSKgTjh7qVH0To,13204
 ultralytics/models/yolo/world/__init__.py,sha256=nlh8I6t8hMGz_vZg8QSlsUW1R-2eKvn9CGUoPPQEGhA,131
 ultralytics/models/yolo/world/train.py,sha256=80kswko6Zu7peXPBhXcfrTo5HO3Rg8C_cu4vPBQlk7M,7906
 ultralytics/models/yolo/world/train_world.py,sha256=5Jj4gzEwDJtz37bEahL6Lf4xp-c1xiYjGKeg_w7Esns,8723
@@ -220,7 +220,7 @@ ultralytics/models/yolo/yoloe/train.py,sha256=99iSHQs--5VU_s82Q4w-fAJmyT5-y0TykT
 ultralytics/models/yolo/yoloe/train_seg.py,sha256=rV2Jnbuh6vvBMaupaZK_aRXBMevO0XhN2VUR43ZwlIY,5285
 ultralytics/models/yolo/yoloe/val.py,sha256=utUFWeFKRFWZrPr1y3A8ztbTwdoWMYqzlwBN7CQ0tCA,9418
 ultralytics/nn/__init__.py,sha256=538LZPUKKvc3JCMgiQ4VLGqRN2ZAaVLFcQbeNNHFkEA,545
-ultralytics/nn/autobackend.py,sha256=ib-4b7nxFpnU7EHZytKrMt4p8la94ZV02_FF8-ifh1c,45057
+ultralytics/nn/autobackend.py,sha256=MLS68iMNv6U0HyBK8nGjcyLOyImYIGEjP4398KqOkV0,45068
 ultralytics/nn/tasks.py,sha256=PmlYScI7qTRCmYRR90Mw1QnqeRzvY0ojAMrgStBr11g,72010
 ultralytics/nn/text_model.py,sha256=c--WzxjFEDb7p95u3YGcSsJLjj91zFNqXshij8Evrwg,15291
 ultralytics/nn/modules/__init__.py,sha256=9KyQBxpomp5uJJ1PvMGuOFs2pR3NpqZcFHJlM6Q56c0,3322
@@ -265,7 +265,7 @@ ultralytics/trackers/utils/matching.py,sha256=x6uZOIx0O9oVmAcfY6tYMTJQE2cDTUlRR6
 ultralytics/utils/__init__.py,sha256=XLEK_pvptzNWhJaO8x0MWghREIyEDei0LOGnUnmU1Kg,55145
 ultralytics/utils/autobatch.py,sha256=jiE4m_--H9UkXFDm_FqzcZk_hSTCGpS72XdVEKgZwAo,5114
 ultralytics/utils/autodevice.py,sha256=rXlPuo-iX-vZ4BabmMGEGh9Uxpau4R7Zlt1KCo9Xfyc,8892
-ultralytics/utils/benchmarks.py,sha256=x0kLvVCRSRx0nEI_suiKM5R-RXLfxhs6pRiA6qwofcg,32293
+ultralytics/utils/benchmarks.py,sha256=f4RykrjO1oEBxrTbH6qM_9vMxYKXO9F0ruFcM4xKF7A,32293
 ultralytics/utils/checks.py,sha256=NWc0J-Nk4qHSVEXFDWfJkI7IjTNHFXajKjsSodDroBk,39411
 ultralytics/utils/cpu.py,sha256=OksKOlX93AsbSsFuoYvLXRXgpkOibrZSwQyW6lipt4Q,3493
 ultralytics/utils/dist.py,sha256=hOuY1-unhQAY-uWiZw3LWw36d1mqJuYK75NdlwB4oKE,4131
@@ -297,14 +297,14 @@ ultralytics/utils/callbacks/mlflow.py,sha256=wCXjQgdufp9LYujqMzLZOmIOur6kvrApHNe
 ultralytics/utils/callbacks/neptune.py,sha256=_vt3cMwDHCR-LyT3KtRikGpj6AG11oQ-skUUUUdZ74o,4391
 ultralytics/utils/callbacks/platform.py,sha256=Ufws7Kp_MHh3jrz-Sx5q1KKQ-l1hoDnLi1_thZJsHPQ,16091
 ultralytics/utils/callbacks/raytune.py,sha256=Y0dFyNZVRuFovSh7nkgUIHTQL3xIXOACElgHuYbg_5I,1278
-ultralytics/utils/callbacks/tensorboard.py,sha256=PTJYvD2gqRUN8xw5VoTjvKnu2adukLfvhMlDgTnTiFU,4952
+ultralytics/utils/callbacks/tensorboard.py,sha256=K7b6KtC7rimfzqFu-NDZ_55Tbd7eC6TckqQdTNPuQ6U,5039
 ultralytics/utils/callbacks/wb.py,sha256=ghmL3gigOa-z_F54-TzMraKw9MAaYX-Wk4H8dLoRvX8,7705
 ultralytics/utils/export/__init__.py,sha256=Cfh-PwVfTF_lwPp-Ss4wiX4z8Sm1XRPklsqdFfmTZ30,333
 ultralytics/utils/export/engine.py,sha256=QoXPqnmQn6W5TOUAygOtCG63R9ExDG4-Df6X6W-_Mzo,10470
-ultralytics/utils/export/imx.py,sha256=Sj3xKLV6APulltaitauSs3oas_ndbtiHkP-KRI-bxoY,13553
+ultralytics/utils/export/imx.py,sha256=VnMDO7c8ezBs91UDoLg9rR0oY8Uc7FujKpbdGxrzV18,13744
 ultralytics/utils/export/tensorflow.py,sha256=xHEcEM3_VeYctyqkJCpgkqcNie1M8xLqcFKr6uANEEQ,9951
-dgenerate_ultralytics_headless-8.4.3.dist-info/METADATA,sha256=x1NlWX5fBn4slcR5Aigeg2RqLZ7McxcqDvg4aMRrUJc,40052
-dgenerate_ultralytics_headless-8.4.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dgenerate_ultralytics_headless-8.4.3.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
-dgenerate_ultralytics_headless-8.4.3.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
-dgenerate_ultralytics_headless-8.4.3.dist-info/RECORD,,
+dgenerate_ultralytics_headless-8.4.4.dist-info/METADATA,sha256=wK7cNiOfQHx28uF-HEPMHSoxLT0azRn5P4dNsYFWyq4,40118
+dgenerate_ultralytics_headless-8.4.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dgenerate_ultralytics_headless-8.4.4.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
+dgenerate_ultralytics_headless-8.4.4.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
+dgenerate_ultralytics_headless-8.4.4.dist-info/RECORD,,

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.4.3"
+__version__ = "8.4.4"
 
 import importlib
 import os

ultralytics/cfg/__init__.py

@@ -412,7 +412,7 @@ def get_save_dir(args: SimpleNamespace, name: str | None = None) -> Path:
         nested = args.project and len(Path(args.project).parts) > 1  # e.g. "user/project" or "org\repo"
         project = runs / args.project if nested else args.project or runs
         name = name or args.name or f"{args.mode}"
-        save_dir = increment_path(Path(project) / name, exist_ok=args.exist_ok if RANK in {-1, 0} else True, mkdir=True)
+        save_dir = increment_path(Path(project) / name, exist_ok=args.exist_ok if RANK in {-1, 0} else True)
 
     return Path(save_dir).resolve()  # resolve to display full path in console
 

ultralytics/engine/exporter.py

@@ -614,12 +614,11 @@ class Exporter:
                 f"work. Use export 'imgsz={max(self.imgsz)}' if val is required."
             )
             imgsz = self.imgsz[0] if square else str(self.imgsz)[1:-1].replace(" ", "")
-            predict_data = f"data={data}" if model.task == "segment" and pb else ""
             q = "int8" if self.args.int8 else "half" if self.args.half else ""  # quantization
             LOGGER.info(
                 f"\nExport complete ({time.time() - t:.1f}s)"
                 f"\nResults saved to {colorstr('bold', file.parent.resolve())}"
-                f"\nPredict:         yolo predict task={model.task} model={f} imgsz={imgsz} {q} {predict_data}"
+                f"\nPredict:         yolo predict task={model.task} model={f} imgsz={imgsz} {q}"
                 f"\nValidate:        yolo val task={model.task} model={f} imgsz={imgsz} data={data} {q} {s}"
                 f"\nVisualize:       https://netron.app"
             )

ultralytics/engine/trainer.py

@@ -984,7 +984,7 @@ class BaseTrainer:
         g[2] = {"params": g[2], **optim_args, "param_group": "bias"}
         g[0] = {"params": g[0], **optim_args, "weight_decay": decay, "param_group": "weight"}
         g[1] = {"params": g[1], **optim_args, "weight_decay": 0.0, "param_group": "bn"}
-        muon, sgd = (0.5, 0.5) if iterations > 10000 else (0.1, 1.0)  # scale factor for MuSGD
+        muon, sgd = (0.1, 1.0) if iterations > 10000 else (0.5, 0.5)  # scale factor for MuSGD
         if use_muon:
             g[3] = {"params": g[3], **optim_args, "weight_decay": decay, "use_muon": True, "param_group": "muon"}
             import re

ultralytics/models/yolo/segment/predict.py

@@ -60,7 +60,7 @@ class SegmentationPredictor(DetectionPredictor):
             >>> results = predictor.postprocess(preds, img, orig_img)
         """
         # Extract protos - tuple if PyTorch model or array if exported
-        protos = preds[0][-1] if isinstance(preds[0], tuple) else preds[-1]
+        protos = preds[0][1] if isinstance(preds[0], tuple) else preds[1]
         return super().postprocess(preds[0], img, orig_imgs, protos=protos)
 
     def construct_results(self, preds, img, orig_imgs, protos):

ultralytics/models/yolo/segment/val.py

@@ -99,9 +99,7 @@ class SegmentationValidator(DetectionValidator):
         Returns:
             list[dict[str, torch.Tensor]]: Processed detection predictions with masks.
         """
-        proto = (
-            preds[0][-1] if isinstance(preds[0], tuple) else preds[-1]
-        )  # second output is len 3 if pt, but only 1 if exported
+        proto = preds[0][1] if isinstance(preds[0], tuple) else preds[1]
         preds = super().postprocess(preds[0])
         imgsz = [4 * x for x in proto.shape[2:]]  # get image size from proto
         for i, pred in enumerate(preds):

ultralytics/nn/autobackend.py

@@ -887,7 +887,7 @@ class AutoBackend(nn.Module):
                                 x[:, 6::3] *= h
                     y.append(x)
             # TF segment fixes: export is reversed vs ONNX export and protos are transposed
-            if len(y) == 2:  # segment with (det, proto) output order reversed
+            if self.task == "segment":  # segment with (det, proto) output order reversed
                 if len(y[1].shape) != 4:
                     y = list(reversed(y))  # should be y = (1, 116, 8400), (1, 160, 160, 32)
                 if y[1].shape[-1] == 6:  # end-to-end model

ultralytics/utils/benchmarks.py

@@ -160,6 +160,8 @@ def benchmark(
                 assert cpu, "inference not supported on CPU"
             if "cuda" in device.type:
                 assert gpu, "inference not supported on GPU"
+            if format == "ncnn":
+                assert not is_end2end, "End-to-end torch.topk operation is not supported for NCNN prediction yet"
 
             # Export
             if format == "-":
@@ -178,8 +180,6 @@ def benchmark(
             assert model.task != "pose" or format != "executorch", "ExecuTorch Pose inference is not supported"
             assert format not in {"edgetpu", "tfjs"}, "inference not supported"
             assert format != "coreml" or platform.system() == "Darwin", "inference only supported on macOS>=10.13"
-            if format == "ncnn":
-                assert not is_end2end, "End-to-end torch.topk operation is not supported for NCNN prediction yet"
             exported_model.predict(ASSETS / "bus.jpg", imgsz=imgsz, device=device, half=half, verbose=False)
 
             # Validate

ultralytics/utils/callbacks/tensorboard.py

@@ -1,6 +1,7 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 from ultralytics.utils import LOGGER, SETTINGS, TESTS_RUNNING, colorstr, torch_utils
+from ultralytics.utils.torch_utils import smart_inference_mode
 
 try:
     assert not TESTS_RUNNING  # do not log pytest
@@ -38,6 +39,7 @@ def _log_scalars(scalars: dict, step: int = 0) -> None:
             WRITER.add_scalar(k, v, step)
 
 
+@smart_inference_mode()
 def _log_tensorboard_graph(trainer) -> None:
     """Log model graph to TensorBoard.
 

ultralytics/utils/export/imx.py

@@ -23,25 +23,37 @@ MCT_CONFIG = {
         "detect": {
             "layer_names": ["sub", "mul_2", "add_14", "cat_19"],
             "weights_memory": 2585350.2439,
-            "n_layers": 238,
+            "n_layers": {238, 239},
         },
         "pose": {
             "layer_names": ["sub", "mul_2", "add_14", "cat_21", "cat_22", "mul_4", "add_15"],
             "weights_memory": 2437771.67,
-            "n_layers": 257,
+            "n_layers": {257, 258},
+        },
+        "classify": {"layer_names": [], "weights_memory": np.inf, "n_layers": {112}},
+        "segment": {
+            "layer_names": ["sub", "mul_2", "add_14", "cat_21"],
+            "weights_memory": 2466604.8,
+            "n_layers": {265, 266},
         },
-        "classify": {"layer_names": [], "weights_memory": np.inf, "n_layers": 112},
-        "segment": {"layer_names": ["sub", "mul_2", "add_14", "cat_21"], "weights_memory": 2466604.8, "n_layers": 265},
     },
     "YOLOv8": {
-        "detect": {"layer_names": ["sub", "mul", "add_6", "cat_15"], "weights_memory": 2550540.8, "n_layers": 168},
+        "detect": {
+            "layer_names": ["sub", "mul", "add_6", "cat_15"],
+            "weights_memory": 2550540.8,
+            "n_layers": {168, 169},
+        },
         "pose": {
             "layer_names": ["add_7", "mul_2", "cat_17", "mul", "sub", "add_6", "cat_18"],
             "weights_memory": 2482451.85,
-            "n_layers": 187,
+            "n_layers": {187, 188},
+        },
+        "classify": {"layer_names": [], "weights_memory": np.inf, "n_layers": {73}},
+        "segment": {
+            "layer_names": ["sub", "mul", "add_6", "cat_17"],
+            "weights_memory": 2580060.0,
+            "n_layers": {195, 196},
         },
-        "classify": {"layer_names": [], "weights_memory": np.inf, "n_layers": 73},
-        "segment": {"layer_names": ["sub", "mul", "add_6", "cat_17"], "weights_memory": 2580060.0, "n_layers": 195},
     },
 }
 
@@ -251,7 +263,7 @@ def torch2imx(
     mct_config = MCT_CONFIG["YOLO11" if "C2PSA" in model.__str__() else "YOLOv8"][model.task]
 
     # Check if the model has the expected number of layers
-    if len(list(model.modules())) != mct_config["n_layers"]:
+    if len(list(model.modules())) not in mct_config["n_layers"]:
         raise ValueError("IMX export only supported for YOLOv8n and YOLO11n models.")
 
     for layer_name in mct_config["layer_names"]: