ultralytics 8.3.67__py3-none-any.whl → 8.3.68__py3-none-any.whl

tests/test_exports.py

@@ -44,18 +44,25 @@ def test_export_openvino():
 @pytest.mark.skipif(not TORCH_1_13, reason="OpenVINO requires torch>=1.13")
 @pytest.mark.parametrize(
     "task, dynamic, int8, half, batch, nms",
-    [  # generate all combinations but exclude those where both int8 and half are True
+    [  # generate all combinations except for exclusion cases
         (task, dynamic, int8, half, batch, nms)
         for task, dynamic, int8, half, batch, nms in product(
             TASKS, [True, False], [True, False], [True, False], [1, 2], [True, False]
         )
-        if not (int8 and half)  # exclude cases where both int8 and half are True
+        if not ((int8 and half) or (task == "classify" and nms))
     ],
 )
 def test_export_openvino_matrix(task, dynamic, int8, half, batch, nms):
     """Test YOLO model exports to OpenVINO under various configuration matrix conditions."""
     file = YOLO(TASK2MODEL[task]).export(
-        format="openvino", imgsz=32, dynamic=dynamic, int8=int8, half=half, batch=batch, data=TASK2DATA[task], nms=nms
+        format="openvino",
+        imgsz=32,
+        dynamic=dynamic,
+        int8=int8,
+        half=half,
+        batch=batch,
+        data=TASK2DATA[task],
+        nms=nms,
     )
     if WINDOWS:
         # Use unique filenames due to Windows file permissions bug possibly due to latent threaded use
@@ -69,7 +76,13 @@ def test_export_openvino_matrix(task, dynamic, int8, half, batch, nms):
 @pytest.mark.slow
 @pytest.mark.parametrize(
     "task, dynamic, int8, half, batch, simplify, nms",
-    product(TASKS, [True, False], [False], [False], [1, 2], [True, False], [True, False]),
+    [  # generate all combinations except for exclusion cases
+        (task, dynamic, int8, half, batch, simplify, nms)
+        for task, dynamic, int8, half, batch, simplify, nms in product(
+            TASKS, [True, False], [False], [False], [1, 2], [True, False], [True, False]
+        )
+        if not ((int8 and half) or (task == "classify" and nms) or (task == "obb" and nms and not TORCH_1_13))
+    ],
 )
 def test_export_onnx_matrix(task, dynamic, int8, half, batch, simplify, nms):
     """Test YOLO exports to ONNX format with various configurations and parameters."""
@@ -82,14 +95,19 @@ def test_export_onnx_matrix(task, dynamic, int8, half, batch, simplify, nms):
 
 @pytest.mark.slow
 @pytest.mark.parametrize(
-    "task, dynamic, int8, half, batch, nms", product(TASKS, [False], [False], [False], [1, 2], [True, False])
+    "task, dynamic, int8, half, batch, nms",
+    [  # generate all combinations except for exclusion cases
+        (task, dynamic, int8, half, batch, nms)
+        for task, dynamic, int8, half, batch, nms in product(TASKS, [False], [False], [False], [1, 2], [True, False])
+        if not (task == "classify" and nms)
+    ],
 )
 def test_export_torchscript_matrix(task, dynamic, int8, half, batch, nms):
     """Tests YOLO model exports to TorchScript format under varied configurations."""
     file = YOLO(TASK2MODEL[task]).export(
         format="torchscript", imgsz=32, dynamic=dynamic, int8=int8, half=half, batch=batch, nms=nms
     )
-    YOLO(file)([SOURCE] * 3, imgsz=64 if dynamic else 32)  # exported model inference at batch=3
+    YOLO(file)([SOURCE] * batch, imgsz=64 if dynamic else 32)  # exported model inference
     Path(file).unlink()  # cleanup
 
 
@@ -99,10 +117,10 @@ def test_export_torchscript_matrix(task, dynamic, int8, half, batch, nms):
 @pytest.mark.skipif(checks.IS_PYTHON_3_12, reason="CoreML not supported in Python 3.12")
 @pytest.mark.parametrize(
     "task, dynamic, int8, half, batch",
-    [  # generate all combinations but exclude those where both int8 and half are True
+    [  # generate all combinations except for exclusion cases
         (task, dynamic, int8, half, batch)
         for task, dynamic, int8, half, batch in product(TASKS, [False], [True, False], [True, False], [1])
-        if not (int8 and half)  # exclude cases where both int8 and half are True
+        if not (int8 and half)
     ],
 )
 def test_export_coreml_matrix(task, dynamic, int8, half, batch):
@@ -124,12 +142,12 @@ def test_export_coreml_matrix(task, dynamic, int8, half, batch):
 @pytest.mark.skipif(not LINUX, reason="Test disabled as TF suffers from install conflicts on Windows and macOS")
 @pytest.mark.parametrize(
     "task, dynamic, int8, half, batch, nms",
-    [  # generate all combinations but exclude those where both int8 and half are True
+    [  # generate all combinations except for exclusion cases
         (task, dynamic, int8, half, batch, nms)
         for task, dynamic, int8, half, batch, nms in product(
             TASKS, [False], [True, False], [True, False], [1], [True, False]
         )
-        if not (int8 and half)  # exclude cases where both int8 and half are True
+        if not ((int8 and half) or (task == "classify" and nms))
     ],
 )
 def test_export_tflite_matrix(task, dynamic, int8, half, batch, nms):

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.67"
+__version__ = "8.3.68"
 
 import os
 

ultralytics/engine/exporter.py

@@ -75,7 +75,7 @@ from ultralytics.data.dataset import YOLODataset
 from ultralytics.data.utils import check_cls_dataset, check_det_dataset
 from ultralytics.nn.autobackend import check_class_names, default_class_names
 from ultralytics.nn.modules import C2f, Classify, Detect, RTDETRDecoder
-from ultralytics.nn.tasks import DetectionModel, SegmentationModel, WorldModel
+from ultralytics.nn.tasks import ClassificationModel, DetectionModel, SegmentationModel, WorldModel
 from ultralytics.utils import (
     ARM64,
     DEFAULT_CFG,
@@ -282,6 +282,7 @@ class Exporter:
         if self.args.int8 and tflite:
             assert not getattr(model, "end2end", False), "TFLite INT8 export not supported for end2end models."
         if self.args.nms:
+            assert not isinstance(model, ClassificationModel), "'nms=True' is not valid for classification models."
             if getattr(model, "end2end", False):
                 LOGGER.warning("WARNING ⚠️ 'nms=True' is not available for end2end models. Forcing 'nms=False'.")
                 self.args.nms = False
@@ -507,6 +508,7 @@ class Exporter:
         output_names = ["output0", "output1"] if isinstance(self.model, SegmentationModel) else ["output0"]
         dynamic = self.args.dynamic
         if dynamic:
+            self.model.cpu()  # dynamic=True only compatible with cpu
             dynamic = {"images": {0: "batch", 2: "height", 3: "width"}}  # shape(1,3,640,640)
             if isinstance(self.model, SegmentationModel):
                 dynamic["output0"] = {0: "batch", 2: "anchors"}  # shape(1, 116, 8400)
@@ -518,13 +520,14 @@ class Exporter:
         if self.args.nms and self.model.task == "obb":
             self.args.opset = opset_version  # for NMSModel
             # OBB error https://github.com/pytorch/pytorch/issues/110859#issuecomment-1757841865
-            torch.onnx.register_custom_op_symbolic("aten::lift_fresh", lambda g, x: x, opset_version)
+            try:
+                torch.onnx.register_custom_op_symbolic("aten::lift_fresh", lambda g, x: x, opset_version)
+            except RuntimeError:  # it will fail if it's already registered
+                pass
             check_requirements("onnxslim>=0.1.46")  # Older versions has bug with OBB
 
         torch.onnx.export(
-            NMSModel(self.model.cpu() if dynamic else self.model, self.args)
-            if self.args.nms
-            else self.model,  # dynamic=True only compatible with cpu
+            NMSModel(self.model, self.args) if self.args.nms else self.model,
             self.im.cpu() if dynamic else self.im,
             f,
             verbose=False,
@@ -1556,6 +1559,7 @@ class NMSModel(torch.nn.Module):
         extra_shape = pred.shape[-1] - (4 + self.model.nc)  # extras from Segment, OBB, Pose
         boxes, scores, extras = pred.split([4, self.model.nc, extra_shape], dim=2)
         scores, classes = scores.max(dim=-1)
+        self.args.max_det = min(pred.shape[1], self.args.max_det)  # in case num_anchors < max_det
         # (N, max_det, 4 coords + 1 class score + 1 class label + extra_shape).
         out = torch.zeros(
             boxes.shape[0],
@@ -1570,7 +1574,7 @@ class NMSModel(torch.nn.Module):
                 # TFLite GatherND error if mask is empty
                 score *= mask
                 # Explicit length otherwise reshape error, hardcoded to `self.args.max_det * 5`
-                mask = score.topk(self.args.max_det * 5).indices
+                mask = score.topk(min(self.args.max_det * 5, score.shape[0])).indices
             box, score, cls, extra = box[mask], score[mask], cls[mask], extra[mask]
             if not self.obb:
                 box = xywh2xyxy(box)
@@ -1593,14 +1597,25 @@ class NMSModel(torch.nn.Module):
                 offbox = nmsbox[:, :end] + cls_offset * multiplier
                 nmsbox = torch.cat((offbox, nmsbox[:, end:]), dim=-1)
             nms_fn = (
-                partial(nms_rotated, use_triu=not (self.is_tf or (self.args.opset or 14) < 14)) if self.obb else nms
+                partial(
+                    nms_rotated,
+                    use_triu=not (
+                        self.is_tf
+                        or (self.args.opset or 14) < 14
+                        or (self.args.format == "openvino" and self.args.int8)  # OpenVINO int8 error with triu
+                    ),
+                )
+                if self.obb
+                else nms
             )
             keep = nms_fn(
                 torch.cat([nmsbox, extra], dim=-1) if self.obb else nmsbox,
                 score,
                 self.args.iou,
             )[: self.args.max_det]
-            dets = torch.cat([box[keep], score[keep].view(-1, 1), cls[keep].view(-1, 1), extra[keep]], dim=-1)
+            dets = torch.cat(
+                [box[keep], score[keep].view(-1, 1), cls[keep].view(-1, 1).to(out.dtype), extra[keep]], dim=-1
+            )
             # Zero-pad to max_det size to avoid reshape error
             pad = (0, 0, 0, self.args.max_det - dets.shape[0])
             out[i] = torch.nn.functional.pad(dets, pad)

ultralytics/utils/benchmarks.py

@@ -134,7 +134,7 @@ def benchmark(
 
             # Export
             if format == "-":
-                filename = model.ckpt_path or model.cfg
+                filename = model.pt_path or model.ckpt_path or model.model_name
                 exported_model = model  # PyTorch format
             else:
                 filename = model.export(imgsz=imgsz, format=format, half=half, int8=int8, device=device, verbose=False)
@@ -169,7 +169,7 @@ def benchmark(
     check_yolo(device=device)  # print system info
     df = pd.DataFrame(y, columns=["Format", "Status❔", "Size (MB)", key, "Inference time (ms/im)", "FPS"])
 
-    name = Path(model.ckpt_path).name
+    name = model.model_name
     s = f"\nBenchmarks complete for {name} on {data} at imgsz={imgsz} ({time.time() - t0:.2f}s)\n{df}\n"
     LOGGER.info(s)
     with open("benchmarks.log", "a", errors="ignore", encoding="utf-8") as f:

{ultralytics-8.3.67.dist-info → ultralytics-8.3.68.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ultralytics
-Version: 8.3.67
+Version: 8.3.68
 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-8.3.67.dist-info → ultralytics-8.3.68.dist-info}/RECORD

@@ -3,11 +3,11 @@ tests/conftest.py,sha256=DE4-5JqWhsQPyDhU5hHqRevz971yPBQORs3LitLc6Fo,3010
 tests/test_cli.py,sha256=b9pPCu6x_MejPw-G7TI3wxSZnaMmutcXW7aCzMzz4ig,5076
 tests/test_cuda.py,sha256=inPe0f_L0GutDxYLbe49BPEmjMevaS9XXCWX1Lfjo2g,5971
 tests/test_engine.py,sha256=aGqZ8P7QO5C_nOa1b4FOyk92Ysdk5WiP-ST310Vyxys,4962
-tests/test_exports.py,sha256=Y4enSgWxhxSyq7uu-vlFeWqgCbeh-QF-nxnaNEsEpCw,8838
+tests/test_exports.py,sha256=T_z_NUS9URQXv83k5XNLHTuksJ8srtzbZnWuiiQWM98,9260
 tests/test_integrations.py,sha256=p3DMnnPMKsV0Qm82JVJUIY1UZ67xRgF9E8AaL76TEHE,6154
 tests/test_python.py,sha256=tW-EFJC2rjl_DvAa8khXGWYdypseQjrLjGHhe2p9r9A,23238
 tests/test_solutions.py,sha256=aY0G3vNzXGCENG9FD76MfUp7jgzeESPsUvbvQYBUvH0,4205
-ultralytics/__init__.py,sha256=-pbOPM7jE9MCRGiQugGcikq7OUWsYt2YkjiRmMDsY6E,709
+ultralytics/__init__.py,sha256=n5q3ToHB7gVfXmfVkZ0WhUK4hNEtU2DDIumDdhLV43E,709
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
 ultralytics/cfg/__init__.py,sha256=qP44HnFP4QcC5FQz29A-EGTuwdtxXAzPvw_IvCVmiqA,39771
@@ -102,7 +102,7 @@ ultralytics/data/loaders.py,sha256=JOwXbz-dxgG2bx0_cQHp-olz5FleoCX8EzrUvZ77vvg,2
 ultralytics/data/split_dota.py,sha256=YI-i2MqdiBt06W67TJnBXQHJrqTnkJDJ3zzoL0UZVro,10733
 ultralytics/data/utils.py,sha256=K8xyA1xHLpaeluUbqOl5fy6AWZ6nDciCBZJofjxzOuw,33841
 ultralytics/engine/__init__.py,sha256=lm6MckFYCPTbqIoX7w0s_daxdjNeBeKW6DXppv1-QUM,70
-ultralytics/engine/exporter.py,sha256=n8f28FkSJC6KSu2TiFyVDC7MEbRTZlO2henB2KdmZro,75968
+ultralytics/engine/exporter.py,sha256=aXUX8GZUw1CBaXYSI7OFwx1tsnl6VkgQQXb_iKi-cs8,76632
 ultralytics/engine/model.py,sha256=IHeaCwXlbxs6f2gVF5hEQVUiY-3F9Oz1wJNSTPZ-tZ0,53110
 ultralytics/engine/predictor.py,sha256=jiYDAjupOlRUpPvw9tu7or9PjXtLm-YCRiawANtWxj0,17881
 ultralytics/engine/results.py,sha256=0u-8GbhLoWBidfoWJ__CIV-_OKxoIRXk2j2OlaWMfd4,75327
@@ -206,7 +206,7 @@ ultralytics/trackers/utils/kalman_filter.py,sha256=OBvemZXptgn9v1sgBLvFomCqOWwjI
 ultralytics/trackers/utils/matching.py,sha256=64PKHGoETwXhuZ9udE217hbjJHygLOPaYA66J2qMSno,7130
 ultralytics/utils/__init__.py,sha256=Ahn7Vn60HIquaBZwLWfWH4bKnm0JcpJXYxnOnY-RH-s,50010
 ultralytics/utils/autobatch.py,sha256=zc81HlAMArPASEbExty0E_zpITF8PVwin7w-xBFFZ5w,5048
-ultralytics/utils/benchmarks.py,sha256=o9T7xfwhMsrOP0ce3F654L1an3fIoBKxUKz1CHNXerw,25979
+ultralytics/utils/benchmarks.py,sha256=48NaNwlHy_ZZOm3QwUxAM1qdVtff2xjw18tpx07H7uQ,25993
 ultralytics/utils/checks.py,sha256=P543iMxEbXi0WWGrY67GaA7jIsas63K4uCSZpqmVx8M,31017
 ultralytics/utils/dist.py,sha256=fuiJQEnyyL-SighlI3hUlZPaaSreUl4Q39snF6OhQtI,2386
 ultralytics/utils/downloads.py,sha256=aUESyJOE2d7mJwbGECHWLR3RF8HVQPSwNH0cfmLGgdI,21999
@@ -233,9 +233,9 @@ ultralytics/utils/callbacks/neptune.py,sha256=waZ_bRu0-qBKujTLuqonC2gx2DkgBuVnfq
 ultralytics/utils/callbacks/raytune.py,sha256=TbuZlDb721aIkh-nMozZcP2g_ttUh2cG5LUaXmept6g,728
 ultralytics/utils/callbacks/tensorboard.py,sha256=JHOEVlNQ5dYJPd4Z-EvqbXowuK5uA0p8wPgyyaIUQs0,4194
 ultralytics/utils/callbacks/wb.py,sha256=ayhT2y62AcSOacnawshATU0rWrlSFQ77mrGgBdRl3W4,7086
-ultralytics-8.3.67.dist-info/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
-ultralytics-8.3.67.dist-info/METADATA,sha256=ObYbsIICOizFYrlFM-E9UxGiF1TZ7n-HTwalyVWnMd8,35202
-ultralytics-8.3.67.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-ultralytics-8.3.67.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
-ultralytics-8.3.67.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
-ultralytics-8.3.67.dist-info/RECORD,,
+ultralytics-8.3.68.dist-info/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+ultralytics-8.3.68.dist-info/METADATA,sha256=WO4rbpms65Um7GOdhwAt7w7z6fUBBtiikVAvvH0q5lU,35202
+ultralytics-8.3.68.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+ultralytics-8.3.68.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
+ultralytics-8.3.68.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
+ultralytics-8.3.68.dist-info/RECORD,,