ultralytics 8.3.169__py3-none-any.whl → 8.3.170__py3-none-any.whl

tests/test_exports.py

@@ -71,7 +71,7 @@ def test_export_openvino_matrix(task, dynamic, int8, half, batch, nms):
         # See https://github.com/ultralytics/ultralytics/actions/runs/8957949304/job/24601616830?pr=10423
         file = Path(file)
         file = file.rename(file.with_stem(f"{file.stem}-{uuid.uuid4()}"))
-    YOLO(file)([SOURCE] * batch, imgsz=64 if dynamic else 32)  # exported model inference
+    YOLO(file)([SOURCE] * batch, imgsz=64 if dynamic else 32, batch=batch)  # exported model inference
     shutil.rmtree(file, ignore_errors=True)  # retry in case of potential lingering multi-threaded file usage errors
 
 

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.169"
+__version__ = "8.3.170"
 
 import os
 

ultralytics/engine/predictor.py

@@ -394,7 +394,6 @@ class BasePredictor:
             dnn=self.args.dnn,
             data=self.args.data,
             fp16=self.args.half,
-            batch=self.args.batch,
             fuse=True,
             verbose=verbose,
         )

ultralytics/nn/autobackend.py

@@ -139,7 +139,6 @@ class AutoBackend(nn.Module):
         dnn: bool = False,
         data: Optional[Union[str, Path]] = None,
         fp16: bool = False,
-        batch: int = 1,
         fuse: bool = True,
         verbose: bool = True,
     ):
@@ -152,7 +151,6 @@ class AutoBackend(nn.Module):
             dnn (bool): Use OpenCV DNN module for ONNX inference.
             data (str | Path, optional): Path to the additional data.yaml file containing class names.
             fp16 (bool): Enable half-precision inference. Supported only on specific backends.
-            batch (int): Batch-size to assume for inference.
             fuse (bool): Fuse Conv2D + BatchNorm layers for optimization.
             verbose (bool): Enable verbose logging.
         """
@@ -311,16 +309,22 @@ class AutoBackend(nn.Module):
             if ov_model.get_parameters()[0].get_layout().empty:
                 ov_model.get_parameters()[0].set_layout(ov.Layout("NCHW"))
 
+            metadata = w.parent / "metadata.yaml"
+            if metadata.exists():
+                metadata = YAML.load(metadata)
+                batch = metadata["batch"]
+                dynamic = metadata.get("args", {}).get("dynamic", dynamic)
             # OpenVINO inference modes are 'LATENCY', 'THROUGHPUT' (not recommended), or 'CUMULATIVE_THROUGHPUT'
-            inference_mode = "CUMULATIVE_THROUGHPUT" if batch > 1 else "LATENCY"
-            LOGGER.info(f"Using OpenVINO {inference_mode} mode for batch={batch} inference...")
+            inference_mode = "CUMULATIVE_THROUGHPUT" if batch > 1 and dynamic else "LATENCY"
             ov_compiled_model = core.compile_model(
                 ov_model,
                 device_name=device_name,
                 config={"PERFORMANCE_HINT": inference_mode},
             )
+            LOGGER.info(
+                f"Using OpenVINO {inference_mode} mode for batch={batch} inference on {', '.join(ov_compiled_model.get_property('EXECUTION_DEVICES'))}..."
+            )
             input_name = ov_compiled_model.input().get_any_name()
-            metadata = w.parent / "metadata.yaml"
 
         # TensorRT
         elif engine:
@@ -397,7 +401,6 @@ class AutoBackend(nn.Module):
                 im = torch.from_numpy(np.empty(shape, dtype=dtype)).to(device)
                 bindings[name] = Binding(name, dtype, shape, im, int(im.data_ptr()))
             binding_addrs = OrderedDict((n, d.ptr) for n, d in bindings.items())
-            batch_size = bindings["images"].shape[0]  # if dynamic, this is instead max batch size
 
         # CoreML
         elif coreml:
@@ -695,8 +698,8 @@ class AutoBackend(nn.Module):
                     # Start async inference with userdata=i to specify the position in results list
                     async_queue.start_async(inputs={self.input_name: im[i : i + 1]}, userdata=i)  # keep image as BCHW
                 async_queue.wait_all()  # wait for all inference requests to complete
-                y = np.concatenate([list(r.values())[0] for r in results])
-
+                y = [list(r.values()) for r in results]
+                y = [np.concatenate(x) for x in zip(*y)]
             else:  # inference_mode = "LATENCY", optimized for fastest first result at batch-size 1
                 y = list(self.ov_compiled_model(im).values())
 

ultralytics/utils/patches.py

@@ -39,7 +39,7 @@ def imread(filename: str, flags: int = cv2.IMREAD_COLOR) -> Optional[np.ndarray]
         return None
     else:
         im = cv2.imdecode(file_bytes, flags)
-        return im[..., None] if im.ndim == 2 else im  # Always ensure 3 dimensions
+        return im[..., None] if im is not None and im.ndim == 2 else im  # Always ensure 3 dimensions
 
 
 def imwrite(filename: str, img: np.ndarray, params: Optional[List[int]] = None) -> bool:

{ultralytics-8.3.169.dist-info → ultralytics-8.3.170.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.169
+Version: 8.3.170
 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-8.3.169.dist-info → ultralytics-8.3.170.dist-info}/RECORD

@@ -3,11 +3,11 @@ tests/conftest.py,sha256=LXtQJcFNWPGuzauTGkiXgsvVC3llJKfg22WcmhRzuQc,2593
 tests/test_cli.py,sha256=EMf5gTAopOnIz8VvzaM-Qb044o7D0flnUHYQ-2ffOM4,5670
 tests/test_cuda.py,sha256=-nQsfF3lGfqLm6cIeu_BCiXqLj7HzpL7R1GzPEc6z2I,8128
 tests/test_engine.py,sha256=Jpt2KVrltrEgh2-3Ykouz-2Z_2fza0eymL5ectRXadM,4922
-tests/test_exports.py,sha256=HmMKOTCia9ZDC0VYc_EPmvBTM5LM5eeI1NF_pKjLpd8,9677
+tests/test_exports.py,sha256=hGUS29WDX9KvFS2PuX2c8NlHSmw3O5UFs0iBVoOqH5k,9690
 tests/test_integrations.py,sha256=kl_AKmE_Qs1GB0_91iVwbzNxofm_hFTt0zzU6JF-pg4,6323
 tests/test_python.py,sha256=-qvdeg-hEcKU5mWSDEU24iFZ-i8FAwQRznSXpkp6WQ4,27928
 tests/test_solutions.py,sha256=tuf6n_fsI8KvSdJrnc-cqP2qYdiYqCWuVrx0z9dOz3Q,13213
-ultralytics/__init__.py,sha256=4cDmvA4EGkWesc5wuiEUkFyDQsQLpWUYq2_7JUrJc38,730
+ultralytics/__init__.py,sha256=KR0C3cGcq9H13HpaXEpZX1N1dJzQJ4H61fjTm_ef418,730
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
 ultralytics/cfg/__init__.py,sha256=VIpPHImhjb0XLJquGZrG_LBGZchtOtBSXR7HYTYV2GU,39602
@@ -121,7 +121,7 @@ ultralytics/data/scripts/get_imagenet.sh,sha256=hr42H16bM47iT27rgS7MpEo-GeOZAYUQ
 ultralytics/engine/__init__.py,sha256=lm6MckFYCPTbqIoX7w0s_daxdjNeBeKW6DXppv1-QUM,70
 ultralytics/engine/exporter.py,sha256=mKAUcyX3C8lDFhkEu3T3kzkbODFEbH1_Wn1W2hMjw4Y,74878
 ultralytics/engine/model.py,sha256=877u2n0ISz2COOYtEMUqQe0E-HHB4Atb2DuH1XCE98k,53530
-ultralytics/engine/predictor.py,sha256=xxl1kdAzKrN8Y_5MQ5f92uFPeeRq1mYOl6hNlzpPjy8,22520
+ultralytics/engine/predictor.py,sha256=iXnUB-tvBHtVpKbB-5EKs1wSREBIerdUxWx39MaFYuk,22485
 ultralytics/engine/results.py,sha256=QcHcbPVlLBiy_APwABr-T5K65HR8Bl1rRzxawjjP76E,71873
 ultralytics/engine/trainer.py,sha256=28FeqASvQRxCaK96SXDM-BfPJjqy5KNiWhf8v6GXTug,39785
 ultralytics/engine/tuner.py,sha256=sfQ8_yzgLNcGlKyz9b2vAzyggGZXiQzdZ5tKstyqjHM,12825
@@ -194,7 +194,7 @@ ultralytics/models/yolo/yoloe/train.py,sha256=XYpQYSnSD8vi_9VSj_S5oIsNUEqm3e66vP
 ultralytics/models/yolo/yoloe/train_seg.py,sha256=aCV7M8oQOvODFnU4piZdJh3tIrBJYAzZfRVRx1vRgxo,4956
 ultralytics/models/yolo/yoloe/val.py,sha256=yebPkxwKKt__cY05Zbh1YXg4_BKzzpcDc3Cv3FJ5SAA,9769
 ultralytics/nn/__init__.py,sha256=rjociYD9lo_K-d-1s6TbdWklPLjTcEHk7OIlRDJstIE,615
-ultralytics/nn/autobackend.py,sha256=_65yU6AIpmz1vV24oSNNMPIBmywPTQQdWF0pwHDHxiU,41628
+ultralytics/nn/autobackend.py,sha256=wnIhA0tsgCn7berelnRvBRVLSV9Kz6ZPiryHavTkQNw,41789
 ultralytics/nn/tasks.py,sha256=jRUjYn1xz_LEa_zx6Upb0UpXvy0Bca1o5HEc7FCRgwM,72653
 ultralytics/nn/text_model.py,sha256=cYwD-0el4VeToDBP4iPFOQGqyEQatJOBHrVyONL3K_s,15282
 ultralytics/nn/modules/__init__.py,sha256=2nY0X69Z5DD5SWt6v3CUTZa5gXSzC9TQr3VTVqhyGho,3158
@@ -248,7 +248,7 @@ ultralytics/utils/instance.py,sha256=dC83rHvQXciAED3rOiScFs3BOX9OI06Ey1mj9sjUKvs
 ultralytics/utils/loss.py,sha256=fbOWc3Iu0QOJiWbi-mXWA9-1otTYlehtmUsI7os7ydM,39799
 ultralytics/utils/metrics.py,sha256=NX22CnIPqs7i_UAcf2D0-KQNNOoRu39OjLtjcbnWTN8,66296
 ultralytics/utils/ops.py,sha256=8d60fbpntrexK3gPoLUS6mWAYGrtrQaQCOYyRJsCjuI,34521
-ultralytics/utils/patches.py,sha256=tBAsNo_RyoFLL9OAzVuJmuoDLUJIPuTMByBYyblGG1A,6517
+ultralytics/utils/patches.py,sha256=PPWiKzwGbCvuawLzDKVR8tWOQAlZbJBi8g_-A6eTCYA,6536
 ultralytics/utils/plotting.py,sha256=IEugKlTITLxArZjbSr7i_cTaHHAqNwVVk08Ak7I_ZdM,47169
 ultralytics/utils/tal.py,sha256=aXawOnhn8ni65tJWIW-PYqWr_TRvltbHBjrTo7o6lDQ,20924
 ultralytics/utils/torch_utils.py,sha256=D76Pvmw5OKh-vd4aJkOMO0dSLbM5WzGr7Hmds54hPEk,39233
@@ -265,9 +265,9 @@ ultralytics/utils/callbacks/neptune.py,sha256=j8pecmlcsM8FGzLKWoBw5xUsi5t8E5HuxY
 ultralytics/utils/callbacks/raytune.py,sha256=S6Bq16oQDQ8BQgnZzA0zJHGN_BBr8iAM_WtGoLiEcwg,1283
 ultralytics/utils/callbacks/tensorboard.py,sha256=MDPBW7aDes-66OE6YqKXXvqA_EocjzEMHWGM-8z9vUQ,5281
 ultralytics/utils/callbacks/wb.py,sha256=Tm_-aRr2CN32MJkY9tylpMBJkb007-MSRNSQ7rDJ5QU,7521
-ultralytics-8.3.169.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
-ultralytics-8.3.169.dist-info/METADATA,sha256=sph15jWqUk8QTPjuJ7pEa1e45rfOlLPS_6D0gbVx4-o,37576
-ultralytics-8.3.169.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-ultralytics-8.3.169.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
-ultralytics-8.3.169.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
-ultralytics-8.3.169.dist-info/RECORD,,
+ultralytics-8.3.170.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+ultralytics-8.3.170.dist-info/METADATA,sha256=DPqQcsMjDKxYsAP5P9NFgqN5-jNmvQEGr-JNlPkXSj8,37576
+ultralytics-8.3.170.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+ultralytics-8.3.170.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
+ultralytics-8.3.170.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
+ultralytics-8.3.170.dist-info/RECORD,,