dgenerate-ultralytics-headless 8.3.137__py3-none-any.whl → 8.3.224__py3-none-any.whl

tests/conftest.py

@@ -3,32 +3,18 @@
 import shutil
 from pathlib import Path
 
-from tests import TMP
-
 
 def pytest_addoption(parser):
-    """
-    Add custom command-line options to pytest.
-
-    Args:
-        parser (pytest.config.Parser): The pytest parser object for adding custom command-line options.
-
-    Returns:
-        (None)
-    """
+    """Add custom command-line options to pytest."""
     parser.addoption("--slow", action="store_true", default=False, help="Run slow tests")
 
 
 def pytest_collection_modifyitems(config, items):
-    """
-    Modify the list of test items to exclude tests marked as slow if the --slow option is not specified.
+    """Modify the list of test items to exclude tests marked as slow if the --slow option is not specified.
 
     Args:
-        config (pytest.config.Config): The pytest configuration object that provides access to command-line options.
+        config: The pytest configuration object that provides access to command-line options.
         items (list): The list of collected pytest item objects to be modified based on the presence of --slow option.
-
-    Returns:
-        (None): The function modifies the 'items' list in place.
     """
     if not config.getoption("--slow"):
         # Remove the item entirely from the list of test items if it's marked as 'slow'
@@ -36,48 +22,38 @@ def pytest_collection_modifyitems(config, items):
 
 
 def pytest_sessionstart(session):
-    """
-    Initialize session configurations for pytest.
+    """Initialize session configurations for pytest.
 
     This function is automatically called by pytest after the 'Session' object has been created but before performing
-    test collection. It sets the initial seeds and prepares the temporary directory for the test session.
+    test collection. It sets the initial seeds for the test session.
 
     Args:
-        session (pytest.Session): The pytest session object.
-
-    Returns:
-        (None)
+        session: The pytest session object.
     """
     from ultralytics.utils.torch_utils import init_seeds
 
     init_seeds()
-    shutil.rmtree(TMP, ignore_errors=True)  # delete any existing tests/tmp directory
-    TMP.mkdir(parents=True, exist_ok=True)  # create a new empty directory
 
 
 def pytest_terminal_summary(terminalreporter, exitstatus, config):
-    """
-    Cleanup operations after pytest session.
+    """Cleanup operations after pytest session.
 
-    This function is automatically called by pytest at the end of the entire test session. It removes certain files
-    and directories used during testing.
+    This function is automatically called by pytest at the end of the entire test session. It removes certain files and
+    directories used during testing.
 
     Args:
-        terminalreporter (pytest.terminal.TerminalReporter): The terminal reporter object used for terminal output.
+        terminalreporter: The terminal reporter object used for terminal output.
         exitstatus (int): The exit status of the test run.
-        config (pytest.config.Config): The pytest config object.
-
-    Returns:
-        (None)
+        config: The pytest config object.
     """
     from ultralytics.utils import WEIGHTS_DIR
 
     # Remove files
-    models = [path for x in ["*.onnx", "*.torchscript"] for path in WEIGHTS_DIR.rglob(x)]
-    for file in ["decelera_portrait_min.mov", "bus.jpg", "yolo11n.onnx", "yolo11n.torchscript"] + models:
+    models = [path for x in {"*.onnx", "*.torchscript"} for path in WEIGHTS_DIR.rglob(x)]
+    for file in ["decelera_portrait_min.mov", "bus.jpg", "yolo11n.onnx", "yolo11n.torchscript", *models]:
         Path(file).unlink(missing_ok=True)
 
     # Remove directories
-    models = [path for x in ["*.mlpackage", "*_openvino_model"] for path in WEIGHTS_DIR.rglob(x)]
-    for directory in [WEIGHTS_DIR / "path with spaces", TMP.parents[1] / ".pytest_cache", TMP] + models:
+    models = [path for x in {"*.mlpackage", "*_openvino_model"} for path in WEIGHTS_DIR.rglob(x)]
+    for directory in [WEIGHTS_DIR / "path with spaces", *models]:
         shutil.rmtree(directory, ignore_errors=True)

tests/test_cli.py

@@ -1,18 +1,14 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
 import subprocess
+from pathlib import Path
 
 import pytest
 from PIL import Image
 
-from tests import CUDA_DEVICE_COUNT, CUDA_IS_AVAILABLE
-from ultralytics.cfg import TASK2DATA, TASK2MODEL, TASKS
+from tests import CUDA_DEVICE_COUNT, CUDA_IS_AVAILABLE, MODELS, TASK_MODEL_DATA
 from ultralytics.utils import ARM64, ASSETS, LINUX, WEIGHTS_DIR, checks
-from ultralytics.utils.torch_utils import TORCH_1_9
-
-# Constants
-TASK_MODEL_DATA = [(task, WEIGHTS_DIR / TASK2MODEL[task], TASK2DATA[task]) for task in TASKS]
-MODELS = [WEIGHTS_DIR / TASK2MODEL[task] for task in TASKS]
+from ultralytics.utils.torch_utils import TORCH_1_11, TORCH_2_9, WINDOWS
 
 
 def run(cmd: str) -> None:
@@ -38,13 +34,13 @@ def test_train(task: str, model: str, data: str) -> None:
 @pytest.mark.parametrize("task,model,data", TASK_MODEL_DATA)
 def test_val(task: str, model: str, data: str) -> None:
     """Test YOLO validation process for specified task, model, and data using a shell command."""
-    run(f"yolo val {task} model={model} data={data} imgsz=32 save_txt save_json")
+    run(f"yolo val {task} model={model} data={data} imgsz=32 save_txt save_json visualize")
 
 
 @pytest.mark.parametrize("task,model,data", TASK_MODEL_DATA)
 def test_predict(task: str, model: str, data: str) -> None:
     """Test YOLO prediction on provided sample assets for specified task and model."""
-    run(f"yolo predict model={model} source={ASSETS} imgsz=32 save save_crop save_txt")
+    run(f"yolo {task} predict model={model} source={ASSETS} imgsz=32 save save_crop save_txt visualize")
 
 
 @pytest.mark.parametrize("model", MODELS)
@@ -53,15 +49,12 @@ def test_export(model: str) -> None:
     run(f"yolo export model={model} format=torchscript imgsz=32")
 
 
-def test_rtdetr(task: str = "detect", model: str = "yolov8n-rtdetr.yaml", data: str = "coco8.yaml") -> None:
+@pytest.mark.skipif(not TORCH_1_11, reason="RTDETR requires torch>=1.11")
+def test_rtdetr(task: str = "detect", model: Path = WEIGHTS_DIR / "rtdetr-l.pt", data: str = "coco8.yaml") -> None:
     """Test the RTDETR functionality within Ultralytics for detection tasks using specified model and data."""
-    # Warning: must use imgsz=640 (note also add coma, spaces, fraction=0.25 args to test single-image training)
-    run(f"yolo train {task} model={model} data={data} --imgsz= 160 epochs =1, cache = disk fraction=0.25")  # spaces
+    # Add comma, spaces, fraction=0.25 args to test single-image training
     run(f"yolo predict {task} model={model} source={ASSETS / 'bus.jpg'} imgsz=160 save save_crop save_txt")
-    if TORCH_1_9:
-        weights = WEIGHTS_DIR / "rtdetr-l.pt"
-        run(f"yolo predict {task} model={weights} source={ASSETS / 'bus.jpg'} imgsz=160 save save_crop save_txt")
-        run(f"yolo train {task} model={weights} epochs=1 imgsz=160 cache=disk data=coco8.yaml")
+    run(f"yolo train {task} model={model} data={data} --imgsz= 160 epochs =1, cache = disk fraction=0.25")
 
 
 @pytest.mark.skipif(checks.IS_PYTHON_3_12, reason="MobileSAM with CLIP is not supported in Python 3.12")
@@ -89,7 +82,7 @@ def test_fastsam(
         everything_results = sam_model(s, device="cpu", retina_masks=True, imgsz=320, conf=0.4, iou=0.9)
 
         # Remove small regions
-        new_masks, _ = Predictor.remove_small_regions(everything_results[0].masks.data, min_area=20)
+        _new_masks, _ = Predictor.remove_small_regions(everything_results[0].masks.data, min_area=20)
 
         # Run inference with bboxes and points and texts prompt at the same time
         sam_model(source, bboxes=[439, 437, 524, 709], points=[[200, 200]], labels=[1], texts="a photo of a dog")
@@ -136,3 +129,10 @@ def test_train_gpu(task: str, model: str, data: str) -> None:
 def test_solutions(solution: str) -> None:
     """Test yolo solutions command-line modes."""
     run(f"yolo solutions {solution} verbose=False")
+
+
+@pytest.mark.skipif(not checks.IS_PYTHON_MINIMUM_3_10 or not TORCH_2_9, reason="Requires Python>=3.10 and Torch>=2.9.0")
+@pytest.mark.skipif(WINDOWS, reason="Skipping test on Windows")
+def test_export_executorch() -> None:
+    """Test exporting a YOLO model to ExecuTorch format via CLI."""
+    run("yolo export model=yolo11n.pt format=executorch imgsz=32")

tests/test_cuda.py

@@ -22,8 +22,12 @@ if CUDA_IS_AVAILABLE:
     else:
         gpu_info = GPUInfo()
         gpu_info.print_status()
-        idle_gpus = gpu_info.select_idle_gpu(count=2, min_memory_mb=2048)
-        if idle_gpus:
+        autodevice_fraction = __import__("os").environ.get("YOLO_AUTODEVICE_FRACTION_FREE", 0.3)
+        if idle_gpus := gpu_info.select_idle_gpu(
+            count=2,
+            min_memory_fraction=autodevice_fraction,
+            min_util_fraction=autodevice_fraction,
+        ):
             DEVICES = idle_gpus
 
 
@@ -41,7 +45,6 @@ def test_amp():
 
 
 @pytest.mark.slow
-@pytest.mark.skipif(IS_JETSON, reason="Temporary disable ONNX for Jetson")
 @pytest.mark.skipif(not DEVICES, reason="No CUDA devices available")
 @pytest.mark.parametrize(
     "task, dynamic, int8, half, batch, simplify, nms",
@@ -50,7 +53,9 @@ def test_amp():
         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))
+        if not (
+            (int8 and half) or (task == "classify" and nms) or (task == "obb" and nms and (not TORCH_1_13 or IS_JETSON))
+        )
     ],
 )
 def test_export_onnx_matrix(task, dynamic, int8, half, batch, simplify, nms):
@@ -65,13 +70,13 @@ def test_export_onnx_matrix(task, dynamic, int8, half, batch, simplify, nms):
         simplify=simplify,
         nms=nms,
         device=DEVICES[0],
+        # opset=20 if nms else None,  # fix ONNX Runtime errors with NMS
     )
     YOLO(file)([SOURCE] * batch, imgsz=64 if dynamic else 32, device=DEVICES[0])  # exported model inference
     Path(file).unlink()  # cleanup
 
 
 @pytest.mark.slow
-@pytest.mark.skipif(True, reason="CUDA export tests disabled pending additional Ultralytics GPU server availability")
 @pytest.mark.skipif(not DEVICES, reason="No CUDA devices available")
 @pytest.mark.parametrize(
     "task, dynamic, int8, half, batch",
@@ -99,7 +104,7 @@ def test_export_engine_matrix(task, dynamic, int8, half, batch):
     )
     YOLO(file)([SOURCE] * batch, imgsz=64 if dynamic else 32, device=DEVICES[0])  # exported model inference
     Path(file).unlink()  # cleanup
-    Path(file).with_suffix(".cache").unlink() if int8 else None  # cleanup INT8 cache
+    Path(file).with_suffix(".cache").unlink(missing_ok=True) if int8 else None  # cleanup INT8 cache
 
 
 @pytest.mark.skipif(not DEVICES, reason="No CUDA devices available")
@@ -108,12 +113,16 @@ def test_train():
     import os
 
     device = tuple(DEVICES) if len(DEVICES) > 1 else DEVICES[0]
-    results = YOLO(MODEL).train(data="coco8.yaml", imgsz=64, epochs=1, device=device)  # requires imgsz>=64
     # NVIDIA Jetson only has one GPU and therefore skipping checks
     if not IS_JETSON:
+        results = YOLO(MODEL).train(
+            data="coco8.yaml", imgsz=64, epochs=1, device=device, batch=15
+        )  # requires imgsz>=64
         visible = eval(os.environ["CUDA_VISIBLE_DEVICES"])
         assert visible == device, f"Passed GPUs '{device}', but used GPUs '{visible}'"
-        assert results is (None if len(DEVICES) > 1 else not None)  # DDP returns None, single-GPU returns metrics
+        assert (
+            (results is None) if len(DEVICES) > 1 else (results is not None)
+        )  # DDP returns None, single-GPU returns metrics
 
 
 @pytest.mark.slow

tests/test_engine.py

@@ -3,6 +3,8 @@
 import sys
 from unittest import mock
 
+import torch
+
 from tests import MODEL
 from ultralytics import YOLO
 from ultralytics.cfg import get_cfg
@@ -11,13 +13,13 @@ from ultralytics.models.yolo import classify, detect, segment
 from ultralytics.utils import ASSETS, DEFAULT_CFG, WEIGHTS_DIR
 
 
-def test_func(*args):  # noqa
+def test_func(*args):
     """Test function callback for evaluating YOLO model performance metrics."""
     print("callback test passed")
 
 
 def test_export():
-    """Tests the model exporting function by adding a callback and asserting its execution."""
+    """Test model exporting functionality by adding a callback and verifying its execution."""
     exporter = Exporter()
     exporter.add_callback("on_export_start", test_func)
     assert test_func in exporter.callbacks["on_export_start"], "callback test failed"
@@ -48,11 +50,12 @@ def test_detect():
     pred = detect.DetectionPredictor(overrides={"imgsz": [64, 64]})
     pred.add_callback("on_predict_start", test_func)
     assert test_func in pred.callbacks["on_predict_start"], "callback test failed"
-    # Confirm there is no issue with sys.argv being empty.
+    # Confirm there is no issue with sys.argv being empty
     with mock.patch.object(sys, "argv", []):
         result = pred(source=ASSETS, model=MODEL)
         assert len(result), "predictor test failed"
 
+    # Test resume functionality
     overrides["resume"] = trainer.last
     trainer = detect.DetectionTrainer(overrides=overrides)
     try:
@@ -61,16 +64,23 @@ def test_detect():
         print(f"Expected exception caught: {e}")
         return
 
-    Exception("Resume test failed!")
+    raise Exception("Resume test failed!")
 
 
 def test_segment():
-    """Tests image segmentation training, validation, and prediction pipelines using YOLO models."""
-    overrides = {"data": "coco8-seg.yaml", "model": "yolo11n-seg.yaml", "imgsz": 32, "epochs": 1, "save": False}
+    """Test image segmentation training, validation, and prediction pipelines using YOLO models."""
+    overrides = {
+        "data": "coco8-seg.yaml",
+        "model": "yolo11n-seg.yaml",
+        "imgsz": 32,
+        "epochs": 1,
+        "save": False,
+        "mask_ratio": 1,
+        "overlap_mask": False,
+    }
     cfg = get_cfg(DEFAULT_CFG)
     cfg.data = "coco8-seg.yaml"
     cfg.imgsz = 32
-    # YOLO(CFG_SEG).train(**overrides)  # works
 
     # Trainer
     trainer = segment.SegmentationTrainer(overrides=overrides)
@@ -91,7 +101,7 @@ def test_segment():
     result = pred(source=ASSETS, model=WEIGHTS_DIR / "yolo11n-seg.pt")
     assert len(result), "predictor test failed"
 
-    # Test resume
+    # Test resume functionality
     overrides["resume"] = trainer.last
     trainer = segment.SegmentationTrainer(overrides=overrides)
     try:
@@ -100,7 +110,7 @@ def test_segment():
         print(f"Expected exception caught: {e}")
         return
 
-    Exception("Resume test failed!")
+    raise Exception("Resume test failed!")
 
 
 def test_classify():
@@ -109,7 +119,6 @@ def test_classify():
     cfg = get_cfg(DEFAULT_CFG)
     cfg.data = "imagenet10"
     cfg.imgsz = 32
-    # YOLO(CFG_SEG).train(**overrides)  # works
 
     # Trainer
     trainer = classify.ClassificationTrainer(overrides=overrides)
@@ -129,3 +138,20 @@ def test_classify():
     assert test_func in pred.callbacks["on_predict_start"], "callback test failed"
     result = pred(source=ASSETS, model=trainer.best)
     assert len(result), "predictor test failed"
+
+
+def test_nan_recovery():
+    """Test NaN loss detection and recovery during training."""
+    nan_injected = [False]
+
+    def inject_nan(trainer):
+        """Inject NaN into loss during batch processing to test recovery mechanism."""
+        if trainer.epoch == 1 and trainer.tloss is not None and not nan_injected[0]:
+            trainer.tloss *= torch.tensor(float("nan"))
+            nan_injected[0] = True
+
+    overrides = {"data": "coco8.yaml", "model": "yolo11n.yaml", "imgsz": 32, "epochs": 3}
+    trainer = detect.DetectionTrainer(overrides=overrides)
+    trainer.add_callback("on_train_batch_end", inject_nan)
+    trainer.train()
+    assert nan_injected[0], "NaN injection failed"

tests/test_exports.py

@@ -12,19 +12,12 @@ import pytest
 from tests import MODEL, SOURCE
 from ultralytics import YOLO
 from ultralytics.cfg import TASK2DATA, TASK2MODEL, TASKS
-from ultralytics.utils import (
-    ARM64,
-    IS_RASPBERRYPI,
-    LINUX,
-    MACOS,
-    WINDOWS,
-    checks,
-)
-from ultralytics.utils.torch_utils import TORCH_1_9, TORCH_1_13
+from ultralytics.utils import ARM64, IS_RASPBERRYPI, LINUX, MACOS, WINDOWS, checks
+from ultralytics.utils.torch_utils import TORCH_1_11, TORCH_1_13, TORCH_2_1, TORCH_2_9
 
 
 def test_export_torchscript():
-    """Test YOLO model exporting to TorchScript format for compatibility and correctness."""
+    """Test YOLO model export to TorchScript format for compatibility and correctness."""
     file = YOLO(MODEL).export(format="torchscript", optimize=False, imgsz=32)
     YOLO(file)(SOURCE, imgsz=32)  # exported model inference
 
@@ -35,15 +28,15 @@ def test_export_onnx():
     YOLO(file)(SOURCE, imgsz=32)  # exported model inference
 
 
-@pytest.mark.skipif(not TORCH_1_13, reason="OpenVINO requires torch>=1.13")
+@pytest.mark.skipif(not TORCH_2_1, reason="OpenVINO requires torch>=2.1")
 def test_export_openvino():
-    """Test YOLO exports to OpenVINO format for model inference compatibility."""
+    """Test YOLO export to OpenVINO format for model inference compatibility."""
     file = YOLO(MODEL).export(format="openvino", imgsz=32)
     YOLO(file)(SOURCE, imgsz=32)  # exported model inference
 
 
 @pytest.mark.slow
-@pytest.mark.skipif(not TORCH_1_13, reason="OpenVINO requires torch>=1.13")
+@pytest.mark.skipif(not TORCH_2_1, reason="OpenVINO requires torch>=2.1")
 @pytest.mark.parametrize(
     "task, dynamic, int8, half, batch, nms",
     [  # generate all combinations except for exclusion cases
@@ -55,7 +48,7 @@ def test_export_openvino():
     ],
 )
 def test_export_openvino_matrix(task, dynamic, int8, half, batch, nms):
-    """Test YOLO model exports to OpenVINO under various configuration matrix conditions."""
+    """Test YOLO model export to OpenVINO under various configuration matrix conditions."""
     file = YOLO(TASK2MODEL[task]).export(
         format="openvino",
         imgsz=32,
@@ -71,7 +64,7 @@ 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
 
 
@@ -83,11 +76,11 @@ def test_export_openvino_matrix(task, dynamic, int8, half, batch, 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))
+        if not ((int8 and half) or (task == "classify" and nms) or (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."""
+    """Test YOLO export to ONNX format with various configurations and parameters."""
     file = YOLO(TASK2MODEL[task]).export(
         format="onnx", imgsz=32, dynamic=dynamic, int8=int8, half=half, batch=batch, simplify=simplify, nms=nms
     )
@@ -100,12 +93,14 @@ def test_export_onnx_matrix(task, dynamic, int8, half, batch, simplify, nms):
     "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])
+        for task, dynamic, int8, half, batch, nms in product(
+            TASKS, [False, True], [False], [False, True], [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."""
+    """Test YOLO model export 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
     )
@@ -115,18 +110,23 @@ def test_export_torchscript_matrix(task, dynamic, int8, half, batch, nms):
 
 @pytest.mark.slow
 @pytest.mark.skipif(not MACOS, reason="CoreML inference only supported on macOS")
-@pytest.mark.skipif(not TORCH_1_9, reason="CoreML>=7.2 not supported with PyTorch<=1.8")
+@pytest.mark.skipif(not TORCH_1_11, reason="CoreML export requires torch>=1.11")
 @pytest.mark.skipif(checks.IS_PYTHON_3_13, reason="CoreML not supported in Python 3.13")
 @pytest.mark.parametrize(
-    "task, dynamic, int8, half, batch",
+    "task, dynamic, int8, half, nms, batch",
     [  # 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])
+        (task, dynamic, int8, half, nms, batch)
+        for task, dynamic, int8, half, nms, batch in product(
+            TASKS, [True, False], [True, False], [True, False], [True, False], [1]
+        )
         if not (int8 and half)
+        and not (task != "detect" and nms)
+        and not (dynamic and nms)
+        and not (task == "classify" and dynamic)
     ],
 )
-def test_export_coreml_matrix(task, dynamic, int8, half, batch):
-    """Test YOLO exports to CoreML format with various parameter configurations."""
+def test_export_coreml_matrix(task, dynamic, int8, half, nms, batch):
+    """Test YOLO export to CoreML format with various parameter configurations."""
     file = YOLO(TASK2MODEL[task]).export(
         format="coreml",
         imgsz=32,
@@ -134,8 +134,9 @@ def test_export_coreml_matrix(task, dynamic, int8, half, batch):
         int8=int8,
         half=half,
         batch=batch,
+        nms=nms,
     )
-    YOLO(file)([SOURCE] * batch, imgsz=32)  # exported model inference at batch=3
+    YOLO(file)([SOURCE] * batch, imgsz=32)  # exported model inference
     shutil.rmtree(file)  # cleanup
 
 
@@ -152,24 +153,24 @@ def test_export_coreml_matrix(task, dynamic, int8, half, batch):
         for task, dynamic, int8, half, batch, nms in product(
             TASKS, [False], [True, False], [True, False], [1], [True, False]
         )
-        if not ((int8 and half) or (task == "classify" and nms) or (ARM64 and nms))
+        if not ((int8 and half) or (task == "classify" and nms) or (ARM64 and nms) or (nms and not TORCH_1_13))
     ],
 )
 def test_export_tflite_matrix(task, dynamic, int8, half, batch, nms):
-    """Test YOLO exports to TFLite format considering various export configurations."""
+    """Test YOLO export to TFLite format considering various export configurations."""
     file = YOLO(TASK2MODEL[task]).export(
         format="tflite", imgsz=32, dynamic=dynamic, int8=int8, half=half, batch=batch, nms=nms
     )
-    YOLO(file)([SOURCE] * batch, imgsz=32)  # exported model inference at batch=3
+    YOLO(file)([SOURCE] * batch, imgsz=32)  # exported model inference
     Path(file).unlink()  # cleanup
 
 
-@pytest.mark.skipif(not TORCH_1_9, reason="CoreML>=7.2 not supported with PyTorch<=1.8")
+@pytest.mark.skipif(not TORCH_1_11, reason="CoreML export requires torch>=1.11")
 @pytest.mark.skipif(WINDOWS, reason="CoreML not supported on Windows")  # RuntimeError: BlobWriter not loaded
 @pytest.mark.skipif(LINUX and ARM64, reason="CoreML not supported on aarch64 Linux")
 @pytest.mark.skipif(checks.IS_PYTHON_3_13, reason="CoreML not supported in Python 3.13")
 def test_export_coreml():
-    """Test YOLO exports to CoreML format and check for errors."""
+    """Test YOLO export to CoreML format and check for errors."""
     # Capture stdout and stderr
     stdout, stderr = io.StringIO(), io.StringIO()
     with redirect_stdout(stdout), redirect_stderr(stderr):
@@ -187,7 +188,7 @@ def test_export_coreml():
 @pytest.mark.skipif(not checks.IS_PYTHON_MINIMUM_3_10, reason="TFLite export requires Python>=3.10")
 @pytest.mark.skipif(not LINUX, reason="Test disabled as TF suffers from install conflicts on Windows and macOS")
 def test_export_tflite():
-    """Test YOLO exports to TFLite format under specific OS and Python version conditions."""
+    """Test YOLO export to TFLite format under specific OS and Python version conditions."""
     model = YOLO(MODEL)
     file = model.export(format="tflite", imgsz=32)
     YOLO(file)(SOURCE, imgsz=32)
@@ -196,7 +197,7 @@ def test_export_tflite():
 @pytest.mark.skipif(True, reason="Test disabled")
 @pytest.mark.skipif(not LINUX, reason="TF suffers from install conflicts on Windows and macOS")
 def test_export_pb():
-    """Test YOLO exports to TensorFlow's Protobuf (*.pb) format."""
+    """Test YOLO export to TensorFlow's Protobuf (*.pb) format."""
     model = YOLO(MODEL)
     file = model.export(format="pb", imgsz=32)
     YOLO(file)(SOURCE, imgsz=32)
@@ -204,28 +205,88 @@ def test_export_pb():
 
 @pytest.mark.skipif(True, reason="Test disabled as Paddle protobuf and ONNX protobuf requirements conflict.")
 def test_export_paddle():
-    """Test YOLO exports to Paddle format, noting protobuf conflicts with ONNX."""
+    """Test YOLO export to Paddle format, noting protobuf conflicts with ONNX."""
     YOLO(MODEL).export(format="paddle", imgsz=32)
 
 
 @pytest.mark.slow
 def test_export_mnn():
-    """Test YOLO exports to MNN format (WARNING: MNN test must precede NCNN test or CI error on Windows)."""
+    """Test YOLO export to MNN format (WARNING: MNN test must precede NCNN test or CI error on Windows)."""
     file = YOLO(MODEL).export(format="mnn", imgsz=32)
     YOLO(file)(SOURCE, imgsz=32)  # exported model inference
 
 
+@pytest.mark.slow
+@pytest.mark.parametrize(
+    "task, int8, half, batch",
+    [  # generate all combinations except for exclusion cases
+        (task, int8, half, batch)
+        for task, int8, half, batch in product(TASKS, [True, False], [True, False], [1, 2])
+        if not (int8 and half)
+    ],
+)
+def test_export_mnn_matrix(task, int8, half, batch):
+    """Test YOLO export to MNN format considering various export configurations."""
+    file = YOLO(TASK2MODEL[task]).export(format="mnn", imgsz=32, int8=int8, half=half, batch=batch)
+    YOLO(file)([SOURCE] * batch, imgsz=32)  # exported model inference
+    Path(file).unlink()  # cleanup
+
+
 @pytest.mark.slow
 def test_export_ncnn():
-    """Test YOLO exports to NCNN format."""
+    """Test YOLO export to NCNN format."""
     file = YOLO(MODEL).export(format="ncnn", imgsz=32)
     YOLO(file)(SOURCE, imgsz=32)  # exported model inference
 
 
+@pytest.mark.slow
+@pytest.mark.parametrize("task, half, batch", list(product(TASKS, [True, False], [1])))
+def test_export_ncnn_matrix(task, half, batch):
+    """Test YOLO export to NCNN format considering various export configurations."""
+    file = YOLO(TASK2MODEL[task]).export(format="ncnn", imgsz=32, half=half, batch=batch)
+    YOLO(file)([SOURCE] * batch, imgsz=32)  # exported model inference
+    shutil.rmtree(file, ignore_errors=True)  # retry in case of potential lingering multi-threaded file usage errors
+
+
 @pytest.mark.skipif(True, reason="Test disabled as keras and tensorflow version conflicts with TFlite export.")
 @pytest.mark.skipif(not LINUX or MACOS, reason="Skipping test on Windows and Macos")
 def test_export_imx():
-    """Test YOLO exports to IMX format."""
+    """Test YOLO export to IMX format."""
     model = YOLO("yolov8n.pt")
     file = model.export(format="imx", imgsz=32)
     YOLO(file)(SOURCE, imgsz=32)
+
+
+@pytest.mark.skipif(not checks.IS_PYTHON_MINIMUM_3_10 or not TORCH_2_9, reason="Requires Python>=3.10 and Torch>=2.9.0")
+@pytest.mark.skipif(WINDOWS, reason="Skipping test on Windows")
+def test_export_executorch():
+    """Test YOLO model export to ExecuTorch format."""
+    file = YOLO(MODEL).export(format="executorch", imgsz=32)
+    assert Path(file).exists(), f"ExecuTorch export failed, directory not found: {file}"
+    # Check that .pte file exists in the exported directory
+    pte_file = Path(file) / Path(MODEL).with_suffix(".pte").name
+    assert pte_file.exists(), f"ExecuTorch .pte file not found: {pte_file}"
+    # Check that metadata.yaml exists
+    metadata_file = Path(file) / "metadata.yaml"
+    assert metadata_file.exists(), f"ExecuTorch metadata.yaml not found: {metadata_file}"
+    # Note: Inference testing skipped as ExecuTorch requires special runtime setup
+    shutil.rmtree(file, ignore_errors=True)  # cleanup
+
+
+@pytest.mark.slow
+@pytest.mark.skipif(not checks.IS_PYTHON_MINIMUM_3_10 or not TORCH_2_9, reason="Requires Python>=3.10 and Torch>=2.9.0")
+@pytest.mark.skipif(WINDOWS, reason="Skipping test on Windows")
+@pytest.mark.parametrize("task", TASKS)
+def test_export_executorch_matrix(task):
+    """Test YOLO export to ExecuTorch format for various task types."""
+    file = YOLO(TASK2MODEL[task]).export(format="executorch", imgsz=32)
+    assert Path(file).exists(), f"ExecuTorch export failed for task '{task}', directory not found: {file}"
+    # Check that .pte file exists in the exported directory
+    model_name = Path(TASK2MODEL[task]).with_suffix(".pte").name
+    pte_file = Path(file) / model_name
+    assert pte_file.exists(), f"ExecuTorch .pte file not found for task '{task}': {pte_file}"
+    # Check that metadata.yaml exists
+    metadata_file = Path(file) / "metadata.yaml"
+    assert metadata_file.exists(), f"ExecuTorch metadata.yaml not found for task '{task}': {metadata_file}"
+    # Note: Inference testing skipped as ExecuTorch requires special runtime setup
+    shutil.rmtree(file, ignore_errors=True)  # cleanup