ultralytics 8.3.129__tar.gz → 8.3.130__tar.gz

{ultralytics-8.3.129/ultralytics.egg-info → ultralytics-8.3.130}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.129
+Version: 8.3.130
 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-8.3.129 → ultralytics-8.3.130}/tests/test_cuda.py

@@ -12,6 +12,7 @@ from ultralytics.cfg import TASK2DATA, TASK2MODEL, TASKS
 from ultralytics.utils import ASSETS, WEIGHTS_DIR
 from ultralytics.utils.autodevice import GPUInfo
 from ultralytics.utils.checks import check_amp
+from ultralytics.utils.torch_utils import TORCH_1_13
 
 # Try to find idle devices if CUDA is available
 DEVICES = []
@@ -36,6 +37,40 @@ def test_amp():
     assert check_amp(model)
 
 
+@pytest.mark.slow
+@pytest.mark.skipif(not DEVICES, reason="No CUDA devices available")
+@pytest.mark.parametrize(
+    "task, dynamic, int8, half, batch, simplify, nms",
+    [  # 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)
+            or (simplify and dynamic)  # onnxslim is slow when dynamic=True
+        )
+    ],
+)
+def test_export_onnx_matrix(task, dynamic, int8, half, batch, simplify, nms):
+    """Test YOLO exports 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,
+        device=DEVICES[0],
+    )
+    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")
@@ -60,7 +95,7 @@ def test_export_engine_matrix(task, dynamic, int8, half, batch):
         batch=batch,
         data=TASK2DATA[task],
         workspace=1,  # reduce workspace GB for less resource utilization during testing
-        simplify=True,  # use 'onnxslim'
+        simplify=True,
         device=DEVICES[0],
     )
     YOLO(file)([SOURCE] * batch, imgsz=64 if dynamic else 32, device=DEVICES[0])  # exported model inference

{ultralytics-8.3.129 → ultralytics-8.3.130}/tests/test_exports.py

@@ -83,7 +83,12 @@ 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 (task == "obb" and nms and not TORCH_1_13)
+            or (simplify and dynamic)  # onnxslim is slow when dynamic=True
+        )
     ],
 )
 def test_export_onnx_matrix(task, dynamic, int8, half, batch, simplify, nms):

{ultralytics-8.3.129 → ultralytics-8.3.130}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.129"
+__version__ = "8.3.130"
 
 import os
 

{ultralytics-8.3.129 → ultralytics-8.3.130}/ultralytics/data/split.py

@@ -1,3 +1,5 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
 import random
 import shutil
 from pathlib import Path

{ultralytics-8.3.129 → ultralytics-8.3.130}/ultralytics/nn/autobackend.py

@@ -159,9 +159,9 @@ class AutoBackend(nn.Module):
 
         # In-memory PyTorch model
         if nn_module:
-            model = weights.to(device)
             if fuse:
-                model = model.fuse(verbose=verbose)
+                weights = weights.fuse(verbose=verbose)  # fuse before move to gpu
+            model = weights.to(device)
             if hasattr(model, "kpt_shape"):
                 kpt_shape = model.kpt_shape  # pose-only
             stride = max(int(model.stride.max()), 32)  # model stride

{ultralytics-8.3.129 → ultralytics-8.3.130/ultralytics.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.129
+Version: 8.3.130
 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>