datachain 0.7.0__tar.gz → 0.7.1__tar.gz

{datachain-0.7.0/src/datachain.egg-info → datachain-0.7.1}/PKG-INFO

@@ -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
@@ -98,6 +98,7 @@ 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 → datachain-0.7.1}/examples/computer_vision/openimage-detect.py

@@ -1,19 +1,11 @@
 import json
 
 from PIL import Image
-from pydantic import BaseModel
 
-from datachain import C, DataChain, File
+from datachain import C, DataChain, File, model
 from datachain.sql.functions import path
 
 
-class BBox(BaseModel):
-    x_min: int
-    x_max: int
-    y_min: int
-    y_max: int
-
-
 def openimage_detect(args):
     if len(args) != 2:
         raise ValueError("Group jpg-json mismatch")
@@ -30,11 +22,13 @@ def openimage_detect(args):
         detections = json.load(stream_json).get("detections", [])
 
     for i, detect in enumerate(detections):
-        bbox = BBox(
-            x_min=int(detect["XMin"] * img.width),
-            x_max=int(detect["XMax"] * img.width),
-            y_min=int(detect["YMin"] * img.height),
-            y_max=int(detect["YMax"] * img.height),
+        bbox = model.BBox.from_list(
+            [
+                detect["XMin"] * img.width,
+                detect["XMax"] * img.width,
+                detect["YMin"] * img.height,
+                detect["YMax"] * img.height,
+            ]
         )
 
         fstream = File(
@@ -56,7 +50,7 @@ source = "gs://datachain-demo/openimages-v6-test-jsonpairs/"
         openimage_detect,
         partition_by=path.file_stem(C("file.path")),
         params=["file"],
-        output={"file": File, "bbox": BBox},
+        output={"file": File, "bbox": model.BBox},
     )
     .show()
 )

datachain-0.7.1/examples/computer_vision/ultralytics-bbox.py

@@ -0,0 +1,22 @@
+from io import BytesIO
+
+from PIL import Image
+from ultralytics import YOLO
+
+from datachain import C, DataChain, File
+from datachain.model.ultralytics import YoloBBoxes
+
+
+def process_bboxes(yolo: YOLO, file: File) -> YoloBBoxes:
+    results = yolo(Image.open(BytesIO(file.read())))
+    return YoloBBoxes.from_results(results)
+
+
+(
+    DataChain.from_storage("gs://datachain-demo/openimages-v6-test-jsonpairs/")
+    .filter(C("file.path").glob("*.jpg"))
+    .limit(20)
+    .setup(yolo=lambda: YOLO("yolo11n.pt"))
+    .map(boxes=process_bboxes)
+    .show()
+)

datachain-0.7.1/examples/computer_vision/ultralytics-pose.py

@@ -0,0 +1,22 @@
+from io import BytesIO
+
+from PIL import Image
+from ultralytics import YOLO
+
+from datachain import C, DataChain, File
+from datachain.model.ultralytics import YoloPoses
+
+
+def process_poses(yolo: YOLO, file: File) -> YoloPoses:
+    results = yolo(Image.open(BytesIO(file.read())))
+    return YoloPoses.from_results(results)
+
+
+(
+    DataChain.from_storage("gs://datachain-demo/openimages-v6-test-jsonpairs/")
+    .filter(C("file.path").glob("*.jpg"))
+    .limit(20)
+    .setup(yolo=lambda: YOLO("yolo11n-pose.pt"))
+    .map(poses=process_poses)
+    .show()
+)

datachain-0.7.1/examples/computer_vision/ultralytics-segment.py

@@ -0,0 +1,22 @@
+from io import BytesIO
+
+from PIL import Image
+from ultralytics import YOLO
+
+from datachain import C, DataChain, File
+from datachain.model.ultralytics import YoloSegments
+
+
+def process_segments(yolo: YOLO, file: File) -> YoloSegments:
+    results = yolo(Image.open(BytesIO(file.read())))
+    return YoloSegments.from_results(results)
+
+
+(
+    DataChain.from_storage("gs://datachain-demo/openimages-v6-test-jsonpairs/")
+    .filter(C("file.path").glob("*.jpg"))
+    .limit(20)
+    .setup(yolo=lambda: YOLO("yolo11n-seg.pt"))
+    .map(segments=process_segments)
+    .show()
+)

{datachain-0.7.0 → datachain-0.7.1}/pyproject.toml

@@ -110,7 +110,8 @@ examples = [
   "unstructured[pdf,embed-huggingface]<0.16.0",
   "pdfplumber==0.11.4",
   "huggingface_hub[hf_transfer]",
-  "onnx==1.16.1"
+  "onnx==1.16.1",
+  "ultralytics==8.3.29"
 ]
 
 [project.urls]

{datachain-0.7.0 → datachain-0.7.1}/src/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-0.7.1/src/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-0.7.1/src/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-0.7.1/src/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-0.7.1/src/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-0.7.1/src/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-0.7.1/src/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-0.7.1/src/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,
+        )