datachain 0.7.0__py3-none-any.whl → 0.7.1__py3-none-any.whl

datachain/__init__.py

@@ -1,4 +1,4 @@
-from datachain.lib import func, models
+from datachain.lib import func
 from datachain.lib.data_model import DataModel, DataType, is_chain_type
 from datachain.lib.dc import C, Column, DataChain, Sys
 from datachain.lib.file import (
@@ -38,6 +38,5 @@ __all__ = [
     "func",
     "is_chain_type",
     "metrics",
-    "models",
     "param",
 ]

datachain/model/__init__.py

@@ -0,0 +1,6 @@
+from . import ultralytics
+from .bbox import BBox, OBBox
+from .pose import Pose, Pose3D
+from .segment import Segment
+
+__all__ = ["BBox", "OBBox", "Pose", "Pose3D", "Segment", "ultralytics"]

datachain/model/bbox.py

@@ -0,0 +1,102 @@
+from pydantic import Field
+
+from datachain.lib.data_model import DataModel
+
+
+class BBox(DataModel):
+    """
+    A data model for representing bounding box.
+
+    Attributes:
+        title (str): The title of the bounding box.
+        coords (list[int]): The coordinates of the bounding box.
+
+    The bounding box is defined by two points:
+        - (x1, y1): The top-left corner of the box.
+        - (x2, y2): The bottom-right corner of the box.
+    """
+
+    title: str = Field(default="")
+    coords: list[int] = Field(default=None)
+
+    @staticmethod
+    def from_list(coords: list[float], title: str = "") -> "BBox":
+        assert len(coords) == 4, "Bounding box must be a list of 4 coordinates."
+        assert all(
+            isinstance(value, (int, float)) for value in coords
+        ), "Bounding box coordinates must be floats or integers."
+        return BBox(
+            title=title,
+            coords=[round(c) for c in coords],
+        )
+
+    @staticmethod
+    def from_dict(coords: dict[str, float], title: str = "") -> "BBox":
+        assert isinstance(coords, dict) and set(coords) == {
+            "x1",
+            "y1",
+            "x2",
+            "y2",
+        }, "Bounding box must be a dictionary with keys 'x1', 'y1', 'x2' and 'y2'."
+        return BBox.from_list(
+            [coords["x1"], coords["y1"], coords["x2"], coords["y2"]],
+            title=title,
+        )
+
+
+class OBBox(DataModel):
+    """
+    A data model for representing oriented bounding boxes.
+
+    Attributes:
+        title (str): The title of the oriented bounding box.
+        coords (list[int]): The coordinates of the oriented bounding box.
+
+    The oriented bounding box is defined by four points:
+        - (x1, y1): The first corner of the box.
+        - (x2, y2): The second corner of the box.
+        - (x3, y3): The third corner of the box.
+        - (x4, y4): The fourth corner of the box.
+    """
+
+    title: str = Field(default="")
+    coords: list[int] = Field(default=None)
+
+    @staticmethod
+    def from_list(coords: list[float], title: str = "") -> "OBBox":
+        assert (
+            len(coords) == 8
+        ), "Oriented bounding box must be a list of 8 coordinates."
+        assert all(
+            isinstance(value, (int, float)) for value in coords
+        ), "Oriented bounding box coordinates must be floats or integers."
+        return OBBox(
+            title=title,
+            coords=[round(c) for c in coords],
+        )
+
+    @staticmethod
+    def from_dict(coords: dict[str, float], title: str = "") -> "OBBox":
+        assert isinstance(coords, dict) and set(coords) == {
+            "x1",
+            "y1",
+            "x2",
+            "y2",
+            "x3",
+            "y3",
+            "x4",
+            "y4",
+        }, "Oriented bounding box must be a dictionary with coordinates."
+        return OBBox.from_list(
+            [
+                coords["x1"],
+                coords["y1"],
+                coords["x2"],
+                coords["y2"],
+                coords["x3"],
+                coords["y3"],
+                coords["x4"],
+                coords["y4"],
+            ],
+            title=title,
+        )

datachain/model/pose.py

@@ -0,0 +1,88 @@
+from pydantic import Field
+
+from datachain.lib.data_model import DataModel
+
+
+class Pose(DataModel):
+    """
+    A data model for representing pose keypoints.
+
+    Attributes:
+        x (list[int]): The x-coordinates of the keypoints.
+        y (list[int]): The y-coordinates of the keypoints.
+
+    The keypoints are represented as lists of x and y coordinates, where each index
+    corresponds to a specific body part.
+    """
+
+    x: list[int] = Field(default=None)
+    y: list[int] = Field(default=None)
+
+    @staticmethod
+    def from_list(points: list[list[float]]) -> "Pose":
+        assert len(points) == 2, "Pose must be a list of 2 lists: x and y coordinates."
+        points_x, points_y = points
+        assert (
+            len(points_x) == len(points_y) == 17
+        ), "Pose x and y coordinates must have the same length of 17."
+        assert all(
+            isinstance(value, (int, float)) for value in [*points_x, *points_y]
+        ), "Pose coordinates must be floats or integers."
+        return Pose(
+            x=[round(coord) for coord in points_x],
+            y=[round(coord) for coord in points_y],
+        )
+
+    @staticmethod
+    def from_dict(points: dict[str, list[float]]) -> "Pose":
+        assert isinstance(points, dict) and set(points) == {
+            "x",
+            "y",
+        }, "Pose must be a dict with keys 'x' and 'y'."
+        return Pose.from_list([points["x"], points["y"]])
+
+
+class Pose3D(DataModel):
+    """
+    A data model for representing 3D pose keypoints.
+
+    Attributes:
+        x (list[int]): The x-coordinates of the keypoints.
+        y (list[int]): The y-coordinates of the keypoints.
+        visible (list[float]): The visibility of the keypoints.
+
+    The keypoints are represented as lists of x, y, and visibility values,
+    where each index corresponds to a specific body part.
+    """
+
+    x: list[int] = Field(default=None)
+    y: list[int] = Field(default=None)
+    visible: list[float] = Field(default=None)
+
+    @staticmethod
+    def from_list(points: list[list[float]]) -> "Pose3D":
+        assert (
+            len(points) == 3
+        ), "Pose3D must be a list of 3 lists: x, y coordinates and visible."
+        points_x, points_y, points_v = points
+        assert (
+            len(points_x) == len(points_y) == len(points_v) == 17
+        ), "Pose3D x, y coordinates and visible must have the same length of 17."
+        assert all(
+            isinstance(value, (int, float))
+            for value in [*points_x, *points_y, *points_v]
+        ), "Pose3D coordinates must be floats or integers."
+        return Pose3D(
+            x=[round(coord) for coord in points_x],
+            y=[round(coord) for coord in points_y],
+            visible=points_v,
+        )
+
+    @staticmethod
+    def from_dict(points: dict[str, list[float]]) -> "Pose3D":
+        assert isinstance(points, dict) and set(points) == {
+            "x",
+            "y",
+            "visible",
+        }, "Pose3D must be a dict with keys 'x', 'y' and 'visible'."
+        return Pose3D.from_list([points["x"], points["y"], points["visible"]])

datachain/model/segment.py

@@ -0,0 +1,47 @@
+from pydantic import Field
+
+from datachain.lib.data_model import DataModel
+
+
+class Segment(DataModel):
+    """
+    A data model for representing segment.
+
+    Attributes:
+        title (str): The title of the segment.
+        x (list[int]): The x-coordinates of the segment.
+        y (list[int]): The y-coordinates of the segment.
+
+    The segment is represented as lists of x and y coordinates, where each index
+    corresponds to a specific point.
+    """
+
+    title: str = Field(default="")
+    x: list[int] = Field(default=None)
+    y: list[int] = Field(default=None)
+
+    @staticmethod
+    def from_list(points: list[list[float]], title: str = "") -> "Segment":
+        assert (
+            len(points) == 2
+        ), "Segment must be a list of 2 lists: x and y coordinates."
+        points_x, points_y = points
+        assert len(points_x) == len(
+            points_y
+        ), "Segment x and y coordinates must have the same length."
+        assert all(
+            isinstance(value, (int, float)) for value in [*points_x, *points_y]
+        ), "Segment coordinates must be floats or integers."
+        return Segment(
+            title=title,
+            x=[round(coord) for coord in points_x],
+            y=[round(coord) for coord in points_y],
+        )
+
+    @staticmethod
+    def from_dict(points: dict[str, list[float]], title: str = "") -> "Segment":
+        assert isinstance(points, dict) and set(points) == {
+            "x",
+            "y",
+        }, "Segment must be a dict with keys 'x' and 'y'."
+        return Segment.from_list([points["x"], points["y"]], title=title)

datachain/model/ultralytics/__init__.py

@@ -0,0 +1,27 @@
+"""
+This module contains the YOLO models.
+
+YOLO stands for "You Only Look Once", a family of object detection models that
+are designed to be fast and accurate. The models are trained to detect objects
+in images by dividing the image into a grid and predicting the bounding boxes
+and class probabilities for each grid cell.
+
+More information about YOLO can be found here:
+- https://pjreddie.com/darknet/yolo/
+- https://docs.ultralytics.com/
+"""
+
+from .bbox import YoloBBox, YoloBBoxes, YoloOBBox, YoloOBBoxes
+from .pose import YoloPose, YoloPoses
+from .segment import YoloSegment, YoloSegments
+
+__all__ = [
+    "YoloBBox",
+    "YoloBBoxes",
+    "YoloOBBox",
+    "YoloOBBoxes",
+    "YoloPose",
+    "YoloPoses",
+    "YoloSegment",
+    "YoloSegments",
+]

datachain/model/ultralytics/bbox.py

@@ -0,0 +1,147 @@
+from typing import TYPE_CHECKING
+
+from pydantic import Field
+
+from datachain.lib.data_model import DataModel
+from datachain.model.bbox import BBox, OBBox
+
+if TYPE_CHECKING:
+    from ultralytics.engine.results import Results
+
+
+class YoloBBox(DataModel):
+    """
+    A class representing a bounding box detected by a YOLO model.
+
+    Attributes:
+        cls: The class of the detected object.
+        name: The name of the detected object.
+        confidence: The confidence score of the detection.
+        box: The bounding box of the detected object
+    """
+
+    cls: int = Field(default=-1)
+    name: str = Field(default="")
+    confidence: float = Field(default=0)
+    box: BBox
+
+    @staticmethod
+    def from_result(result: "Results") -> "YoloBBox":
+        summary = result.summary()
+        if not summary:
+            return YoloBBox(box=BBox())
+        name = summary[0].get("name", "")
+        box = (
+            BBox.from_dict(summary[0]["box"], title=name)
+            if "box" in summary[0]
+            else BBox()
+        )
+        return YoloBBox(
+            cls=summary[0]["class"],
+            name=name,
+            confidence=summary[0]["confidence"],
+            box=box,
+        )
+
+
+class YoloBBoxes(DataModel):
+    """
+    A class representing a list of bounding boxes detected by a YOLO model.
+
+    Attributes:
+        cls: A list of classes of the detected objects.
+        name: A list of names of the detected objects.
+        confidence: A list of confidence scores of the detections.
+        box: A list of bounding boxes of the detected objects
+    """
+
+    cls: list[int]
+    name: list[str]
+    confidence: list[float]
+    box: list[BBox]
+
+    @staticmethod
+    def from_results(results: list["Results"]) -> "YoloBBoxes":
+        cls, names, confidence, box = [], [], [], []
+        for r in results:
+            for s in r.summary():
+                name = s.get("name", "")
+                cls.append(s["class"])
+                names.append(name)
+                confidence.append(s["confidence"])
+                box.append(BBox.from_dict(s.get("box", {}), title=name))
+        return YoloBBoxes(
+            cls=cls,
+            name=names,
+            confidence=confidence,
+            box=box,
+        )
+
+
+class YoloOBBox(DataModel):
+    """
+    A class representing an oriented bounding box detected by a YOLO model.
+
+    Attributes:
+        cls: The class of the detected object.
+        name: The name of the detected object.
+        confidence: The confidence score of the detection.
+        box: The oriented bounding box of the detected object.
+    """
+
+    cls: int = Field(default=-1)
+    name: str = Field(default="")
+    confidence: float = Field(default=0)
+    box: OBBox
+
+    @staticmethod
+    def from_result(result: "Results") -> "YoloOBBox":
+        summary = result.summary()
+        if not summary:
+            return YoloOBBox(box=OBBox())
+        name = summary[0].get("name", "")
+        box = (
+            OBBox.from_dict(summary[0]["box"], title=name)
+            if "box" in summary[0]
+            else OBBox()
+        )
+        return YoloOBBox(
+            cls=summary[0]["class"],
+            name=name,
+            confidence=summary[0]["confidence"],
+            box=box,
+        )
+
+
+class YoloOBBoxes(DataModel):
+    """
+    A class representing a list of oriented bounding boxes detected by a YOLO model.
+
+    Attributes:
+        cls: A list of classes of the detected objects.
+        name: A list of names of the detected objects.
+        confidence: A list of confidence scores of the detections.
+        box: A list of oriented bounding boxes of the detected objects.
+    """
+
+    cls: list[int]
+    name: list[str]
+    confidence: list[float]
+    box: list[OBBox]
+
+    @staticmethod
+    def from_results(results: list["Results"]) -> "YoloOBBoxes":
+        cls, names, confidence, box = [], [], [], []
+        for r in results:
+            for s in r.summary():
+                name = s.get("name", "")
+                cls.append(s["class"])
+                names.append(name)
+                confidence.append(s["confidence"])
+                box.append(OBBox.from_dict(s.get("box", {}), title=name))
+        return YoloOBBoxes(
+            cls=cls,
+            name=names,
+            confidence=confidence,
+            box=box,
+        )

datachain/model/ultralytics/pose.py

@@ -0,0 +1,113 @@
+from typing import TYPE_CHECKING
+
+from pydantic import Field
+
+from datachain.lib.data_model import DataModel
+from datachain.model.bbox import BBox
+from datachain.model.pose import Pose3D
+
+if TYPE_CHECKING:
+    from ultralytics.engine.results import Results
+
+
+class YoloPoseBodyPart:
+    """An enumeration of body parts for YOLO pose keypoints."""
+
+    nose = 0
+    left_eye = 1
+    right_eye = 2
+    left_ear = 3
+    right_ear = 4
+    left_shoulder = 5
+    right_shoulder = 6
+    left_elbow = 7
+    right_elbow = 8
+    left_wrist = 9
+    right_wrist = 10
+    left_hip = 11
+    right_hip = 12
+    left_knee = 13
+    right_knee = 14
+    left_ankle = 15
+    right_ankle = 16
+
+
+class YoloPose(DataModel):
+    """
+    A data model for YOLO pose keypoints.
+
+    Attributes:
+        cls: The class of the pose.
+        name: The name of the pose.
+        confidence: The confidence score of the pose.
+        box: The bounding box of the pose.
+        pose: The 3D pose keypoints.
+    """
+
+    cls: int = Field(default=-1)
+    name: str = Field(default="")
+    confidence: float = Field(default=0)
+    box: BBox
+    pose: Pose3D
+
+    @staticmethod
+    def from_result(result: "Results") -> "YoloPose":
+        summary = result.summary()
+        if not summary:
+            return YoloPose(box=BBox(), pose=Pose3D())
+        name = summary[0].get("name", "")
+        box = (
+            BBox.from_dict(summary[0]["box"], title=name)
+            if "box" in summary[0]
+            else BBox()
+        )
+        pose = (
+            Pose3D.from_dict(summary[0]["keypoints"])
+            if "keypoints" in summary[0]
+            else Pose3D()
+        )
+        return YoloPose(
+            cls=summary[0]["class"],
+            name=name,
+            confidence=summary[0]["confidence"],
+            box=box,
+            pose=pose,
+        )
+
+
+class YoloPoses(DataModel):
+    """
+    A data model for a list of YOLO pose keypoints.
+
+    Attributes:
+        cls: The classes of the poses.
+        name: The names of the poses.
+        confidence: The confidence scores of the poses.
+        box: The bounding boxes of the poses.
+        pose: The 3D pose keypoints of the poses.
+    """
+
+    cls: list[int]
+    name: list[str]
+    confidence: list[float]
+    box: list[BBox]
+    pose: list[Pose3D]
+
+    @staticmethod
+    def from_results(results: list["Results"]) -> "YoloPoses":
+        cls, names, confidence, box, pose = [], [], [], [], []
+        for r in results:
+            for s in r.summary():
+                name = s.get("name", "")
+                cls.append(s["class"])
+                names.append(name)
+                confidence.append(s["confidence"])
+                box.append(BBox.from_dict(s.get("box", {}), title=name))
+                pose.append(Pose3D.from_dict(s.get("keypoints", {})))
+        return YoloPoses(
+            cls=cls,
+            name=names,
+            confidence=confidence,
+            box=box,
+            pose=pose,
+        )

datachain/model/ultralytics/segment.py

@@ -0,0 +1,91 @@
+from typing import TYPE_CHECKING
+
+from pydantic import Field
+
+from datachain.lib.data_model import DataModel
+from datachain.model.bbox import BBox
+from datachain.model.segment import Segment
+
+if TYPE_CHECKING:
+    from ultralytics.engine.results import Results
+
+
+class YoloSegment(DataModel):
+    """
+    A data model for a single YOLO segment.
+
+    Attributes:
+        cls (int): The class of the segment.
+        name (str): The name of the segment.
+        confidence (float): The confidence of the segment.
+        box (BBox): The bounding box of the segment.
+        segment (Segments): The segments of the segment.
+    """
+
+    cls: int = Field(default=-1)
+    name: str = Field(default="")
+    confidence: float = Field(default=0)
+    box: BBox
+    segment: Segment
+
+    @staticmethod
+    def from_result(result: "Results") -> "YoloSegment":
+        summary = result.summary()
+        if not summary:
+            return YoloSegment(box=BBox(), segment=Segment())
+        name = summary[0].get("name", "")
+        box = (
+            BBox.from_dict(summary[0]["box"], title=name)
+            if "box" in summary[0]
+            else BBox()
+        )
+        segment = (
+            Segment.from_dict(summary[0]["segments"], title=name)
+            if "segments" in summary[0]
+            else Segment()
+        )
+        return YoloSegment(
+            cls=summary[0]["class"],
+            name=summary[0]["name"],
+            confidence=summary[0]["confidence"],
+            box=box,
+            segment=segment,
+        )
+
+
+class YoloSegments(DataModel):
+    """
+    A data model for a list of YOLO segments.
+
+    Attributes:
+        cls (list[int]): The classes of the segments.
+        name (list[str]): The names of the segments.
+        confidence (list[float]): The confidences of the segments.
+        box (list[BBox]): The bounding boxes of the segments.
+        segment (list[Segments]): The segments of the segments.
+    """
+
+    cls: list[int]
+    name: list[str]
+    confidence: list[float]
+    box: list[BBox]
+    segment: list[Segment]
+
+    @staticmethod
+    def from_results(results: list["Results"]) -> "YoloSegments":
+        cls, names, confidence, box, segment = [], [], [], [], []
+        for r in results:
+            for s in r.summary():
+                name = s.get("name", "")
+                cls.append(s["class"])
+                names.append(name)
+                confidence.append(s["confidence"])
+                box.append(BBox.from_dict(s.get("box", {}), title=name))
+                segment.append(Segment.from_dict(s.get("segments", {}), title=name))
+        return YoloSegments(
+            cls=cls,
+            name=names,
+            confidence=confidence,
+            box=box,
+            segment=segment,
+        )

datachain/toolkit/split.py

@@ -58,10 +58,14 @@ def train_test_split(dc: DataChain, weights: list[float]) -> list[DataChain]:
 
     weights_normalized = [weight / sum(weights) for weight in weights]
 
+    resolution = 2**31 - 1  # Maximum positive value for a 32-bit signed integer.
+
     return [
         dc.filter(
-            C("sys__rand") % 1000 >= round(sum(weights_normalized[:index]) * 1000),
-            C("sys__rand") % 1000 < round(sum(weights_normalized[: index + 1]) * 1000),
+            C("sys__rand") % resolution
+            >= round(sum(weights_normalized[:index]) * resolution),
+            C("sys__rand") % resolution
+            < round(sum(weights_normalized[: index + 1]) * resolution),
         )
         for index, _ in enumerate(weights_normalized)
     ]

{datachain-0.7.0.dist-info → datachain-0.7.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.7.0
+Version: 0.7.1
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -19,85 +19,86 @@ License-File: LICENSE
 Requires-Dist: pyyaml
 Requires-Dist: tomlkit
 Requires-Dist: tqdm
-Requires-Dist: numpy <3,>=1
-Requires-Dist: pandas >=2.0.0
+Requires-Dist: numpy<3,>=1
+Requires-Dist: pandas>=2.0.0
 Requires-Dist: pyarrow
 Requires-Dist: typing-extensions
-Requires-Dist: python-dateutil >=2
-Requires-Dist: attrs >=21.3.0
-Requires-Dist: s3fs >=2024.2.0
-Requires-Dist: gcsfs >=2024.2.0
-Requires-Dist: adlfs >=2024.2.0
-Requires-Dist: dvc-data <4,>=3.10
-Requires-Dist: dvc-objects <6,>=4
-Requires-Dist: shtab <2,>=1.3.4
-Requires-Dist: sqlalchemy >=2
-Requires-Dist: multiprocess ==0.70.16
+Requires-Dist: python-dateutil>=2
+Requires-Dist: attrs>=21.3.0
+Requires-Dist: s3fs>=2024.2.0
+Requires-Dist: gcsfs>=2024.2.0
+Requires-Dist: adlfs>=2024.2.0
+Requires-Dist: dvc-data<4,>=3.10
+Requires-Dist: dvc-objects<6,>=4
+Requires-Dist: shtab<2,>=1.3.4
+Requires-Dist: sqlalchemy>=2
+Requires-Dist: multiprocess==0.70.16
 Requires-Dist: cloudpickle
-Requires-Dist: orjson >=3.10.5
-Requires-Dist: pydantic <3,>=2
-Requires-Dist: jmespath >=1.0
-Requires-Dist: datamodel-code-generator >=0.25
-Requires-Dist: Pillow <12,>=10.0.0
-Requires-Dist: msgpack <2,>=1.0.4
+Requires-Dist: orjson>=3.10.5
+Requires-Dist: pydantic<3,>=2
+Requires-Dist: jmespath>=1.0
+Requires-Dist: datamodel-code-generator>=0.25
+Requires-Dist: Pillow<12,>=10.0.0
+Requires-Dist: msgpack<2,>=1.0.4
 Requires-Dist: psutil
-Requires-Dist: huggingface-hub
-Requires-Dist: iterative-telemetry >=0.0.9
+Requires-Dist: huggingface_hub
+Requires-Dist: iterative-telemetry>=0.0.9
 Requires-Dist: platformdirs
-Requires-Dist: dvc-studio-client <1,>=0.21
+Requires-Dist: dvc-studio-client<1,>=0.21
 Requires-Dist: tabulate
-Provides-Extra: dev
-Requires-Dist: datachain[docs,tests] ; extra == 'dev'
-Requires-Dist: mypy ==1.13.0 ; extra == 'dev'
-Requires-Dist: types-python-dateutil ; extra == 'dev'
-Requires-Dist: types-pytz ; extra == 'dev'
-Requires-Dist: types-PyYAML ; extra == 'dev'
-Requires-Dist: types-requests ; extra == 'dev'
-Requires-Dist: types-tabulate ; extra == 'dev'
 Provides-Extra: docs
-Requires-Dist: mkdocs >=1.5.2 ; extra == 'docs'
-Requires-Dist: mkdocs-gen-files >=0.5.0 ; extra == 'docs'
-Requires-Dist: mkdocs-material >=9.3.1 ; extra == 'docs'
-Requires-Dist: mkdocs-section-index >=0.3.6 ; extra == 'docs'
-Requires-Dist: mkdocstrings-python >=1.6.3 ; extra == 'docs'
-Requires-Dist: mkdocs-literate-nav >=0.6.1 ; extra == 'docs'
-Provides-Extra: examples
-Requires-Dist: datachain[tests] ; extra == 'examples'
-Requires-Dist: numpy <2,>=1 ; extra == 'examples'
-Requires-Dist: defusedxml ; extra == 'examples'
-Requires-Dist: accelerate ; extra == 'examples'
-Requires-Dist: unstructured[embed-huggingface,pdf] <0.16.0 ; extra == 'examples'
-Requires-Dist: pdfplumber ==0.11.4 ; extra == 'examples'
-Requires-Dist: huggingface-hub[hf_transfer] ; extra == 'examples'
-Requires-Dist: onnx ==1.16.1 ; extra == 'examples'
-Provides-Extra: hf
-Requires-Dist: numba >=0.60.0 ; extra == 'hf'
-Requires-Dist: datasets[audio,vision] >=2.21.0 ; extra == 'hf'
-Provides-Extra: remote
-Requires-Dist: lz4 ; extra == 'remote'
-Requires-Dist: requests >=2.22.0 ; extra == 'remote'
-Provides-Extra: tests
-Requires-Dist: datachain[hf,remote,torch,vector] ; extra == 'tests'
-Requires-Dist: pytest <9,>=8 ; extra == 'tests'
-Requires-Dist: pytest-sugar >=0.9.6 ; extra == 'tests'
-Requires-Dist: pytest-cov >=4.1.0 ; extra == 'tests'
-Requires-Dist: pytest-mock >=3.12.0 ; extra == 'tests'
-Requires-Dist: pytest-servers[all] >=0.5.8 ; extra == 'tests'
-Requires-Dist: pytest-benchmark[histogram] ; extra == 'tests'
-Requires-Dist: pytest-xdist >=3.3.1 ; extra == 'tests'
-Requires-Dist: virtualenv ; extra == 'tests'
-Requires-Dist: dulwich ; extra == 'tests'
-Requires-Dist: hypothesis ; extra == 'tests'
-Requires-Dist: open-clip-torch ; extra == 'tests'
-Requires-Dist: aiotools >=1.7.0 ; extra == 'tests'
-Requires-Dist: requests-mock ; extra == 'tests'
-Requires-Dist: scipy ; extra == 'tests'
+Requires-Dist: mkdocs>=1.5.2; extra == "docs"
+Requires-Dist: mkdocs-gen-files>=0.5.0; extra == "docs"
+Requires-Dist: mkdocs-material>=9.3.1; extra == "docs"
+Requires-Dist: mkdocs-section-index>=0.3.6; extra == "docs"
+Requires-Dist: mkdocstrings-python>=1.6.3; extra == "docs"
+Requires-Dist: mkdocs-literate-nav>=0.6.1; extra == "docs"
 Provides-Extra: torch
-Requires-Dist: torch >=2.1.0 ; extra == 'torch'
-Requires-Dist: torchvision ; extra == 'torch'
-Requires-Dist: transformers >=4.36.0 ; extra == 'torch'
+Requires-Dist: torch>=2.1.0; extra == "torch"
+Requires-Dist: torchvision; extra == "torch"
+Requires-Dist: transformers>=4.36.0; extra == "torch"
+Provides-Extra: remote
+Requires-Dist: lz4; extra == "remote"
+Requires-Dist: requests>=2.22.0; extra == "remote"
 Provides-Extra: vector
-Requires-Dist: usearch ; extra == 'vector'
+Requires-Dist: usearch; extra == "vector"
+Provides-Extra: hf
+Requires-Dist: numba>=0.60.0; extra == "hf"
+Requires-Dist: datasets[audio,vision]>=2.21.0; extra == "hf"
+Provides-Extra: tests
+Requires-Dist: datachain[hf,remote,torch,vector]; extra == "tests"
+Requires-Dist: pytest<9,>=8; extra == "tests"
+Requires-Dist: pytest-sugar>=0.9.6; extra == "tests"
+Requires-Dist: pytest-cov>=4.1.0; extra == "tests"
+Requires-Dist: pytest-mock>=3.12.0; extra == "tests"
+Requires-Dist: pytest-servers[all]>=0.5.8; extra == "tests"
+Requires-Dist: pytest-benchmark[histogram]; extra == "tests"
+Requires-Dist: pytest-xdist>=3.3.1; extra == "tests"
+Requires-Dist: virtualenv; extra == "tests"
+Requires-Dist: dulwich; extra == "tests"
+Requires-Dist: hypothesis; extra == "tests"
+Requires-Dist: open_clip_torch; extra == "tests"
+Requires-Dist: aiotools>=1.7.0; extra == "tests"
+Requires-Dist: requests-mock; extra == "tests"
+Requires-Dist: scipy; extra == "tests"
+Provides-Extra: dev
+Requires-Dist: datachain[docs,tests]; extra == "dev"
+Requires-Dist: mypy==1.13.0; extra == "dev"
+Requires-Dist: types-python-dateutil; extra == "dev"
+Requires-Dist: types-pytz; extra == "dev"
+Requires-Dist: types-PyYAML; extra == "dev"
+Requires-Dist: types-requests; extra == "dev"
+Requires-Dist: types-tabulate; extra == "dev"
+Provides-Extra: examples
+Requires-Dist: datachain[tests]; extra == "examples"
+Requires-Dist: numpy<2,>=1; extra == "examples"
+Requires-Dist: defusedxml; extra == "examples"
+Requires-Dist: accelerate; extra == "examples"
+Requires-Dist: unstructured[embed-huggingface,pdf]<0.16.0; extra == "examples"
+Requires-Dist: pdfplumber==0.11.4; extra == "examples"
+Requires-Dist: huggingface_hub[hf_transfer]; extra == "examples"
+Requires-Dist: onnx==1.16.1; extra == "examples"
+Requires-Dist: ultralytics==8.3.29; extra == "examples"
 
 ================
 |logo| DataChain

{datachain-0.7.0.dist-info → datachain-0.7.1.dist-info}/RECORD

@@ -1,4 +1,4 @@
-datachain/__init__.py,sha256=nnTyB5MpCfBZ6D85JPz-5hUT7i-68Is-47Bxgew8lRw,930
+datachain/__init__.py,sha256=OGzc8xZWtwqxiiutjU4AxCRPY0lrX_csgERiTrq4G0o,908
 datachain/__main__.py,sha256=hG3Y4ARGEqe1AWwNMd259rBlqtphx1Wk39YbueQ0yV8,91
 datachain/asyn.py,sha256=5aKrjnUxk0mtnZeFKNJd1DCE0MsnSoyJBZkr0y9H_a0,9313
 datachain/cache.py,sha256=s0YHN7qurmQv-eC265TjeureK84TebWWAnL07cxchZQ,2997
@@ -71,10 +71,14 @@ datachain/lib/convert/values_to_tuples.py,sha256=varRCnSMT_pZmHznrd2Yi05qXLLz_v9
 datachain/lib/func/__init__.py,sha256=wlAKhGV0QDg9y7reSwoUF8Vicfqh_YOUNIXLzxICGz4,403
 datachain/lib/func/aggregate.py,sha256=H1ziFQdaK9zvnxvttfnEzkkyGvEEmMAvmgCsBV6nfm8,10917
 datachain/lib/func/func.py,sha256=HAJZ_tpiRG2R-et7pr0WnoyNZYtpbPn3_HBuL3RQpbU,4800
-datachain/lib/models/__init__.py,sha256=AGvjPbUokJiir3uelTa4XGtNSECkMFc5Xmi_N3AtxPQ,119
-datachain/lib/models/bbox.py,sha256=aiYNhvEcRK3dEN4MBcptmkPKc9kMP16ZQdu7xPk6hek,1555
-datachain/lib/models/pose.py,sha256=peuJPNSiGuTXfCfGIABwv8PGYistvTTBmtf-8X8E_eA,1077
-datachain/lib/models/yolo.py,sha256=eftoJDUa8iOpFTF1EkKVAd5Q-3HRd6X4eCIZ9h5p4nI,972
+datachain/model/__init__.py,sha256=R9faX5OHV1xh2EW-g2MPedwbtEqt3LodJRyluB-QylI,189
+datachain/model/bbox.py,sha256=LLtzc8OiL-cxqqlPWXA4MFTo8HRS3GW2gOxA0Sf_cxI,3158
+datachain/model/pose.py,sha256=0URrnS99Ugq0yspCXC2z-hgpybEA5tWLJXpxqVLnAlI,3088
+datachain/model/segment.py,sha256=dMxtm-05fNseEoEKpZj9iDN7fwGK1udyAreN-V-cRks,1597
+datachain/model/ultralytics/__init__.py,sha256=EvcNX9qUyxKXXlKCPpsXeRrabyXk5E9EkN-tyiYkfS4,750
+datachain/model/ultralytics/bbox.py,sha256=OZ9XBdyMOYc401P-RhfSN9QaYvMpnx2Phu9ptaJgZBY,4316
+datachain/model/ultralytics/pose.py,sha256=71KBTcoST2wcEtsyGXqLVpvUtqbp9gwZGA15pEPtX5A,2959
+datachain/model/ultralytics/segment.py,sha256=Z1ab0tZRJubSYNH4KkFlzhYeGNTfAyC71KmkQcToHDQ,2760
 datachain/query/__init__.py,sha256=7DhEIjAA8uZJfejruAVMZVcGFmvUpffuZJwgRqNwe-c,263
 datachain/query/batch.py,sha256=5fEhORFe7li12SdYddaSK3LyqksMfCHhwN1_A6TfsA4,3485
 datachain/query/dataset.py,sha256=sQny-ZemB2HueC4mPg-7qSaqUD85MMO-DQyVVP8K1CA,53765
@@ -104,11 +108,11 @@ datachain/sql/sqlite/base.py,sha256=aHSZVvh4XSVkvZ07h3jMoRlHI4sWD8y3SnmGs9xMG9Y,
 datachain/sql/sqlite/types.py,sha256=lPXS1XbkmUtlkkiRxy_A_UzsgpPv2VSkXYOD4zIHM4w,1734
 datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR0,469
 datachain/toolkit/__init__.py,sha256=eQ58Q5Yf_Fgv1ZG0IO5dpB4jmP90rk8YxUWmPc1M2Bo,68
-datachain/toolkit/split.py,sha256=6FcEJgUsJsUcCqKW5aXuJy4DvbcQ7_dFbsfNPhn8EVg,2377
+datachain/toolkit/split.py,sha256=ZgDcrNiKiPXZmKD591_1z9qRIXitu5zwAsoVPB7ykiU,2508
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.7.0.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.7.0.dist-info/METADATA,sha256=Cm0v22C-aT14JBG4NjNQmM7kvhYZFAf6rh0yDAMRWFU,18037
-datachain-0.7.0.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
-datachain-0.7.0.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.7.0.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.7.0.dist-info/RECORD,,
+datachain-0.7.1.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.7.1.dist-info/METADATA,sha256=9ICI9nDBKNq39JJR2q_RxuYBCFkUD4o81T2FEO8LKDU,18006
+datachain-0.7.1.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+datachain-0.7.1.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.7.1.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.7.1.dist-info/RECORD,,

{datachain-0.7.0.dist-info → datachain-0.7.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.5.0)
+Generator: setuptools (75.6.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

datachain/lib/models/__init__.py

@@ -1,5 +0,0 @@
-from . import yolo
-from .bbox import BBox
-from .pose import Pose, Pose3D
-
-__all__ = ["BBox", "Pose", "Pose3D", "yolo"]

datachain/lib/models/bbox.py

@@ -1,45 +0,0 @@
-from typing import Optional
-
-from pydantic import Field
-
-from datachain.lib.data_model import DataModel
-
-
-class BBox(DataModel):
-    """
-    A data model for representing bounding boxes.
-
-    Attributes:
-        title (str): The title of the bounding box.
-        x1 (float): The x-coordinate of the top-left corner of the bounding box.
-        y1 (float): The y-coordinate of the top-left corner of the bounding box.
-        x2 (float): The x-coordinate of the bottom-right corner of the bounding box.
-        y2 (float): The y-coordinate of the bottom-right corner of the bounding box.
-
-    The bounding box is defined by two points:
-        - (x1, y1): The top-left corner of the box.
-        - (x2, y2): The bottom-right corner of the box.
-    """
-
-    title: str = Field(default="")
-    x1: float = Field(default=0)
-    y1: float = Field(default=0)
-    x2: float = Field(default=0)
-    y2: float = Field(default=0)
-
-    @staticmethod
-    def from_xywh(bbox: list[float], title: Optional[str] = None) -> "BBox":
-        """
-        Converts a bounding box in (x, y, width, height) format
-        to a BBox data model instance.
-
-        Args:
-            bbox (list[float]): A bounding box, represented as a list
-                                of four floats [x, y, width, height].
-
-        Returns:
-            BBox2D: An instance of the BBox data model.
-        """
-        assert len(bbox) == 4, f"Bounding box must have 4 elements, got f{len(bbox)}"
-        x, y, w, h = bbox
-        return BBox(title=title or "", x1=x, y1=y, x2=x + w, y2=y + h)

datachain/lib/models/pose.py

@@ -1,37 +0,0 @@
-from pydantic import Field
-
-from datachain.lib.data_model import DataModel
-
-
-class Pose(DataModel):
-    """
-    A data model for representing pose keypoints.
-
-    Attributes:
-        x (list[float]): The x-coordinates of the keypoints.
-        y (list[float]): The y-coordinates of the keypoints.
-
-    The keypoints are represented as lists of x and y coordinates, where each index
-    corresponds to a specific body part.
-    """
-
-    x: list[float] = Field(default=None)
-    y: list[float] = Field(default=None)
-
-
-class Pose3D(DataModel):
-    """
-    A data model for representing 3D pose keypoints.
-
-    Attributes:
-        x (list[float]): The x-coordinates of the keypoints.
-        y (list[float]): The y-coordinates of the keypoints.
-        visible (list[float]): The visibility of the keypoints.
-
-    The keypoints are represented as lists of x, y, and visibility values,
-    where each index corresponds to a specific body part.
-    """
-
-    x: list[float] = Field(default=None)
-    y: list[float] = Field(default=None)
-    visible: list[float] = Field(default=None)

datachain/lib/models/yolo.py

@@ -1,39 +0,0 @@
-"""
-This module contains the YOLO models.
-
-YOLO stands for "You Only Look Once", a family of object detection models that
-are designed to be fast and accurate. The models are trained to detect objects
-in images by dividing the image into a grid and predicting the bounding boxes
-and class probabilities for each grid cell.
-
-More information about YOLO can be found here:
-- https://pjreddie.com/darknet/yolo/
-- https://docs.ultralytics.com/
-"""
-
-
-class PoseBodyPart:
-    """
-    An enumeration of body parts for YOLO pose keypoints.
-
-    More information about the body parts can be found here:
-    https://docs.ultralytics.com/tasks/pose/
-    """
-
-    nose = 0
-    left_eye = 1
-    right_eye = 2
-    left_ear = 3
-    right_ear = 4
-    left_shoulder = 5
-    right_shoulder = 6
-    left_elbow = 7
-    right_elbow = 8
-    left_wrist = 9
-    right_wrist = 10
-    left_hip = 11
-    right_hip = 12
-    left_knee = 13
-    right_knee = 14
-    left_ankle = 15
-    right_ankle = 16