easydetect 0.2.3__tar.gz → 0.3.0__tar.gz

{easydetect-0.2.3 → easydetect-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: easydetect
-Version: 0.2.3
+Version: 0.3.0
 Summary: Easy real-time object detection you can ship: D-FINE with PyTorch training, OpenVINO inference on CPU/GPU/NPU, and a browser app to label and train. Apache-2.0 throughout.
 Project-URL: Homepage, https://github.com/themakerrobot/easydetect
 Project-URL: Source, https://github.com/themakerrobot/easydetect

{easydetect-0.2.3 → easydetect-0.3.0}/easydetect/__init__.py

@@ -24,7 +24,7 @@ needs numpy/opencv/openvino/pyyaml; training adds
 
 from __future__ import annotations
 
-__version__ = "0.2.3"
+__version__ = "0.3.0"
 
 from .errors import DownloadError, EasyDetectError, ModelNotFoundError
 from .metrics import BoxMetrics, DetMetrics

{easydetect-0.2.3 → easydetect-0.3.0}/easydetect/cli.py

@@ -28,7 +28,7 @@ Modes:
 
 Common keys:
   model=dfine-n|s|m|l|x|best.pt|model.xml   source=bus.jpg|dir|video.mp4|0|url
-  data=data.yaml  epochs=100  imgsz=640  batch=8  conf=0.25  iou=0.7|none  device=0|cpu|AUTO
+  data=data.yaml  epochs=100  imgsz=640  batch=8  conf=0.5  iou=0.7|none  device=0|cpu|AUTO
   contain=0.8  project=runs  name=predict  save=true  show=false  format=openvino  half=true
 
 Examples:

{easydetect-0.2.3 → easydetect-0.3.0}/easydetect/model.py

@@ -114,7 +114,7 @@ class Detector:
     def predict(
         self,
         source: Any = None,
-        conf: float = 0.25,
+        conf: float = 0.5,
         imgsz: int | None = None,
         device: str | None = None,
         max_det: int = 300,
@@ -134,12 +134,14 @@ class Detector:
         """Run detection on any supported source.
 
         Returns a ``list[Results]``, or a generator when ``stream=True`` (the
-        only sane option for a long video or a live camera). ``iou`` drops a
-        box covering a higher-scoring one by more than that IoU — the same
-        object found twice, sometimes under two classes; ``None`` keeps all.
-        ``contain=0.8`` also merges a box with 80% of its area inside another
-        of its class — the visible pieces of a half hidden object reported
-        beside the whole of it — into one box. Off by default.
+        only sane option for a long video or a live camera). ``conf=0.5``
+        is where D-FINE's boxes are mostly right (70% on COCO, against 32% at
+        YOLO's usual 0.25). ``iou`` drops a box covering a higher-scoring one
+        by more than that IoU — the same object found twice, sometimes under
+        two classes; ``None`` keeps all. ``contain=0.8`` also merges a box
+        with 80% of its area inside another of its class — the visible pieces
+        of a half hidden object beside the whole of it — into one box; off by
+        default, as on COCO it removes more real objects than it fixes.
         """
         if source is None:
             raise ValueError("predict() needs a source (image, folder, video, url, camera index)")
@@ -171,7 +173,7 @@ class Detector:
     def track(
         self,
         source: Any = None,
-        conf: float = 0.25,
+        conf: float = 0.5,
         iou: float | None = 0.7,
         contain: float | None = None,
         match_iou: float = 0.3,
@@ -209,7 +211,7 @@ class Detector:
     def _run(
         self,
         source: Any,
-        conf: float = 0.25,
+        conf: float = 0.5,
         imgsz: int | None = None,
         device: str | None = None,
         max_det: int = 300,

{easydetect-0.2.3 → easydetect-0.3.0}/easydetect/predictor.py

@@ -128,6 +128,12 @@ def read_names(model_path: Path) -> dict[int, str]:
 #: Default for ``iou``: above this IoU, two boxes are one object.
 IOU = 0.7
 
+#: Default for ``conf``. D-FINE gives an unsure box 0.3-0.5 where YOLO would
+#: give it under 0.25, so YOLO's 0.25 shows mostly mistakes here: dfine-m on
+#: COCO val2017 (NMS 0.7) shows boxes 32% right at 0.25, 70% at 0.5, while
+#: still finding 67% of the objects. See docs/performance.md.
+CONF = 0.5
+
 
 def drop_duplicates(xyxy: np.ndarray, iou: float = IOU) -> np.ndarray:
     """Indices of the boxes to keep, from boxes sorted best first.
@@ -277,7 +283,7 @@ class Predictor:
         boxes: np.ndarray,
         scores: np.ndarray,
         orig_shape: tuple[int, int],
-        conf: float = 0.25,
+        conf: float = CONF,
         max_det: int = 300,
         classes: list[int] | None = None,
         iou: float | None = IOU,
@@ -322,7 +328,7 @@ class Predictor:
     def __call__(
         self,
         img: np.ndarray,
-        conf: float = 0.25,
+        conf: float = CONF,
         max_det: int = 300,
         classes: list[int] | None = None,
         iou: float | None = IOU,

{easydetect-0.2.3 → easydetect-0.3.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "easydetect"
-version = "0.2.3"
+version = "0.3.0"
 description = "Easy real-time object detection you can ship: D-FINE with PyTorch training, OpenVINO inference on CPU/GPU/NPU, and a browser app to label and train. Apache-2.0 throughout."
 readme = "README.md"
 requires-python = ">=3.10"

{easydetect-0.2.3 → easydetect-0.3.0}/tests/test_predictor.py

@@ -201,3 +201,15 @@ def test_the_whole_path_merges_pieces_only_when_asked():
     assert sorted(merged[:, 5].tolist()) == [0, 56]         # one person, one chair
     chair = merged[merged[:, 5] == 56][0]
     assert chair[:4].round().tolist() == [285, 455, 373, 640]   # the whole of it
+
+
+def test_the_defaults_are_the_measured_ones():
+    """conf 0.5, NMS 0.7, contain off: docs/performance.md, 'Confidence and overlap defaults'."""
+    import inspect
+
+    from easydetect import Detector
+
+    for method in (Detector.predict, Detector.track):
+        params = inspect.signature(method).parameters
+        assert params["conf"].default == 0.5 and params["iou"].default == 0.7
+        assert params["contain"].default is None

{easydetect-0.2.3 → easydetect-0.3.0}/tools/hub_README.md

@@ -29,7 +29,7 @@ pip install easydetect          # OpenVINO and ONNX Runtime, no PyTorch
 from easydetect import Detector
 
 model = Detector("dfine-s")                 # downloads dfine-s/ from this repo once
-results = model("photo.jpg", conf=0.25)
+results = model("photo.jpg", conf=0.5)
 results[0].save("result.jpg")
 
 for r in model.predict(0, stream=True, show=True):   # webcam; q or Esc quits