BadBob / Playground
ONNX Runtime · OpenCV · MIT
04.01

Prepare your project

Install the listed dependencies and run the tests. Try an offline image before opening the camera.

Basics

python -m unittest
Runs automated checks without opening the camera.
Terminalbash
unzip badbob-playground-python.zip
cd badbob-playground-python
python3.12 -m venv .venv
. .venv/bin/activate
python -m pip install -r requirements.txt
python -m unittest discover -s tests -v
04.02

Connect your model

Validate the model and labels before opening a camera.

Basics

OnnxDetector.__init__(...)
Loads the ONNX model and validates its input, output and label count.
prepare_input(...)
Builds a 640×640 RGB input, preserving proportions and padding the remaining area.
OnnxDetector.detect(...)
Prepares the image, runs the model and returns detections.
Keep in mind
Symptom
Boxes drift or the model fails to load.
Cause
Preprocessing, output layout or label order does not match.
Remedy
This adapter supports only the contract below. Core ML files and other ONNX layouts need a different adapter.

This adapter supports only the contract below. Core ML files and other ONNX layouts need a different adapter.

In depth

Coordinates describe box centers and dimensions in the 640×640 input pixels. Labels follow the exact model class order.

ONNXyaml
input:
  color: RGB
  dtype: float32
  shape: [1, 3, 640, 640]
  letterbox: 114
  scale: 1/255
output:
  dtype: float32
  shape: [1, 4+C, N]
  boxes: [cx, cy, width, height]
  class_scores: probabilities
  objectness: false
  embedded_nms: false
detector.pypython
"""Explicit CPU ONNX adapter; another export contract needs another adapter."""

from pathlib import Path
from typing import cast

import cv2
import numpy as np
import onnxruntime as ort

from .geometry import calculate_letterbox, decode_predictions
from .image_contract import validate_image
from .labels import validate_label_metadata
from .types import Detection, Image, Letterbox, Tensor


def prepare_input(frame: Image) -> tuple[Tensor, Letterbox]:
    validate_image(frame)
    transform = calculate_letterbox(frame.shape[1], frame.shape[0])
    resized = cv2.resize(frame, (transform.width, transform.height), interpolation=cv2.INTER_LINEAR)
    canvas = np.full((640, 640, 3), 114, dtype=np.uint8)
    canvas[
        transform.top : transform.top + transform.height,
        transform.left : transform.left + transform.width,
    ] = resized
    rgb = cv2.cvtColor(canvas, cv2.COLOR_BGR2RGB)
    tensor = np.ascontiguousarray(rgb.transpose(2, 0, 1)[None], dtype=np.float32)
    tensor /= np.float32(255)
    return tensor, transform


class OnnxDetector:
    def __init__(self, model: Path, labels: tuple[str, ...]) -> None:
        if not model.is_file() or model.suffix.lower() != ".onnx":
            raise ValueError("Supply an existing local .onnx model")
        if not 1 <= len(labels) <= 1024:
            raise ValueError("Expected 1..1024 class labels")

        self._session: ort.InferenceSession | None = None
        self._classes = len(labels)
        ort.disable_telemetry_events()
        session = ort.InferenceSession(str(model), providers=["CPUExecutionProvider"])
        inputs, outputs = session.get_inputs(), session.get_outputs()
        if (
            len(inputs) != 1
            or inputs[0].type != "tensor(float)"
            or inputs[0].shape != [1, 3, 640, 640]
        ):
            raise ValueError("Expected one float32 RGB NCHW input [1,3,640,640]")
        if len(outputs) != 1 or outputs[0].type != "tensor(float)":
            raise ValueError("Expected one float32 detector output")

        self._validate_output_shape(outputs[0].shape)
        validate_label_metadata(session.get_modelmeta().custom_metadata_map, labels)
        self._input_name, self._output_name = inputs[0].name, outputs[0].name
        self._session = session
        # Validate actual output values before the runner may acquire a camera.
        self.detect(np.full((640, 640, 3), 114, dtype=np.uint8))

    def _validate_output_shape(self, shape: object) -> None:
        if not isinstance(shape, list) or len(shape) != 3 or shape[:2] != [1, 4 + self._classes]:
            raise ValueError("Expected output metadata [1,4+C,N] matching label count")
        candidates = shape[2]
        if isinstance(candidates, int) and not 1 <= candidates <= 100000:
            raise ValueError("Expected 1..100000 detector candidates")
        if candidates is not None and not isinstance(candidates, (str, int)):
            raise ValueError("Invalid detector candidate dimension")

    def detect(self, frame: Image) -> tuple[Detection, ...]:
        session = self._session
        if session is None:
            raise RuntimeError("Detector is closed")

        tensor, transform = prepare_input(frame)
        results = session.run([self._output_name], {self._input_name: tensor})
        output: object = results[0]
        if not isinstance(output, np.ndarray) or output.dtype != np.float32:
            raise ValueError("Expected a float32 NumPy detector tensor")
        return decode_predictions(cast(Tensor, output), self._classes, transform)

    def close(self) -> None:
        # The Python CPU session has no public close(); drop its owner reference.
        self._session = None
04.03

Bring in the camera

Capture and inference share one serial worker. The UI receives only the latest completed image and its detections.

Basics

Runner._run()
Handles capture and inference on one worker thread.
LatestResult.take()
Takes the latest completed image and its detections; results cannot build up in a queue.
Runner.stop()
Stops accepting new results and releases resources after active work finishes.
Keep in mind
Symptom
The preview lags and memory use grows.
Cause
The camera produces frames faster than inference handles them, so an unbounded queue builds up.
Remedy
Capture and inference share one serial worker. The UI receives only the latest completed image and its detections.
In depth

Request stop, reject late results and wait for active work before releasing its resources. Backend cancellation depends on platform support.

runner.pypython
"""One joined worker, no input queue, and one complete owned output pair."""

import threading
from collections.abc import Callable

from .types import Detector, FrameResult, FrameSource


class LatestResult:
    def __init__(self) -> None:
        self._lock = threading.Lock()
        self._pending: FrameResult | None = None
        self._closed = False

    def publish(self, result: FrameResult) -> bool:
        with self._lock:
            if self._closed:
                return False
            self._pending = result
            return True

    def take(self) -> FrameResult | None:
        with self._lock:
            result, self._pending = self._pending, None
            return result

    def close(self) -> None:
        with self._lock:
            self._closed = True
            self._pending = None


class Runner:
    def __init__(
        self, detector_factory: Callable[[], Detector], source_factory: Callable[[], FrameSource]
    ):
        self.results = LatestResult()
        self.finished = threading.Event()
        self.stop_requested = threading.Event()
        self.error: str | None = None
        self._detector_factory = detector_factory
        self._source_factory = source_factory
        self._thread: threading.Thread | None = None

    def start(self) -> None:
        if self._thread is not None or self.stop_requested.is_set():
            raise RuntimeError("A Runner starts once; create a new Runner for another session")
        self._thread = threading.Thread(target=self._run, name="badbob-inference", daemon=False)
        self._thread.start()

    def stop(self) -> None:
        self.stop_requested.set()
        self.results.close()
        if self._thread is not None:
            self._thread.join()

    def _capture(self, detector: Detector, source: FrameSource) -> None:
        sequence = 0
        while not self.stop_requested.is_set():
            frame = source.read()
            if frame is None:
                return
            if self.stop_requested.is_set():
                return

            # Own the pixels even when a backend or test double reuses its buffer.
            owned_frame = frame.copy()
            detections = detector.detect(owned_frame)
            if self.stop_requested.is_set():
                return
            sequence += 1
            self.results.publish(FrameResult(owned_frame, detections, sequence))

    def _run(self) -> None:
        detector: Detector | None = None
        source: FrameSource | None = None
        try:
            detector = self._detector_factory()
            if self.stop_requested.is_set():
                return
            source = self._source_factory()
            self._capture(detector, source)
        except Exception as error:
            self.error = f"{type(error).__name__}: {error}"
            self.results.close()
        finally:
            self._release(source, detector)
            self.finished.set()

    def _release(self, source: FrameSource | None, detector: Detector | None) -> None:
        for resource in (source, detector):
            if resource is None:
                continue
            try:
                resource.close()
            except Exception as error:
                self.error = self.error or f"Cleanup failed: {error}"
                self.results.close()
04.04

Put predictions in place

Undo letterbox scaling and padding, then clip boxes before drawing.

Basics

calculate_letterbox(...) · unproject_box(...)
Preserves the aspect ratio and maps boxes back to the original image.
decode_predictions(...)
Validates predictions and removes overlapping boxes of the same class.
Keep in mind

Treat image size, crop, orientation and coordinates as one contract. Test it with known boxes before trusting an overlay.

geometry.pypython
"""Letterbox geometry and bounded class-aware suppression."""

import math

import numpy as np

from .types import Box, Detection, Letterbox, Tensor


def calculate_letterbox(width: int, height: int, edge: int = 640) -> Letterbox:
    if width <= 0 or height <= 0 or not 0 < edge <= 4096:
        raise ValueError("Positive image dimensions and input edge <=4096 required")

    scale = min(edge / width, edge / height)
    resized_width = max(1, math.floor(width * scale + 0.5))
    resized_height = max(1, math.floor(height * scale + 0.5))
    return Letterbox(
        width,
        height,
        resized_width,
        resized_height,
        (edge - resized_width) // 2,
        (edge - resized_height) // 2,
        edge,
    )


def validate_transform(transform: Letterbox) -> None:
    if (
        transform.original_width <= 0
        or transform.original_height <= 0
        or not 0 < transform.width <= transform.edge <= 4096
        or not 0 < transform.height <= transform.edge
        or not 0 <= transform.left <= transform.edge - transform.width
        or not 0 <= transform.top <= transform.edge - transform.height
    ):
        raise ValueError("Invalid letterbox geometry")


def unproject_box(box: Box, transform: Letterbox) -> Box:
    validate_transform(transform)
    values = (box.x, box.y, box.width, box.height, box.x + box.width, box.y + box.height)
    if not all(math.isfinite(value) for value in values) or min(box.width, box.height) < 0:
        raise ValueError("Box coordinates must be finite with nonnegative dimensions")

    def x(value: float) -> float:
        return (
            min(1.0, max(0.0, (value - transform.left) / transform.width))
            * transform.original_width
        )

    def y(value: float) -> float:
        return (
            min(1.0, max(0.0, (value - transform.top) / transform.height))
            * transform.original_height
        )

    left, top = x(box.x), y(box.y)
    return Box(left, top, x(box.x + box.width) - left, y(box.y + box.height) - top)


def intersection_over_union(first: Box, second: Box) -> float:
    width = max(0.0, min(first.x + first.width, second.x + second.width) - max(first.x, second.x))
    height = max(
        0.0, min(first.y + first.height, second.y + second.height) - max(first.y, second.y)
    )
    intersection = width * height
    union = first.width * first.height + second.width * second.height - intersection
    return intersection / union if union > 0 else 0.0


def validate_predictions(data: Tensor, classes: int, confidence: float, overlap: float) -> None:
    if (
        data.dtype != np.float32
        or data.ndim != 3
        or not 1 <= classes <= 1024
        or data.shape[:2] != (1, 4 + classes)
        or not 1 <= data.shape[2] <= 100000
    ):
        raise ValueError("Expected float32 [1,4+C,N], C<=1024 and 1<=N<=100000")
    if not all(math.isfinite(value) and 0 <= value <= 1 for value in (confidence, overlap)):
        raise ValueError("Confidence and overlap must be finite probabilities in [0,1]")
    if not np.isfinite(data).all() or (data[0, 2:4] < 0).any():
        raise ValueError("Unsupported detector coordinates: finite nonnegative sizes required")
    if (data[0, 4:] < 0).any() or (data[0, 4:] > 1).any():
        raise ValueError("Expected class probabilities in [0,1], not logits/objectness")


def decode_predictions(
    data: Tensor,
    classes: int,
    transform: Letterbox,
    confidence: float = 0.25,
    overlap: float = 0.45,
) -> tuple[Detection, ...]:
    validate_transform(transform)
    validate_predictions(data, classes, confidence, overlap)
    labels = np.argmax(data[0, 4:], axis=0)
    scores = np.max(data[0, 4:], axis=0)
    indices = np.flatnonzero(scores >= confidence)
    indices = indices[np.argsort(-scores[indices], kind="stable")]
    candidates: list[Detection] = []

    for index in indices:
        cx, cy, width, height = (float(value) for value in data[0, :4, index])
        box = unproject_box(Box(cx - width / 2, cy - height / 2, width, height), transform)
        if box.width <= 0 or box.height <= 0:
            continue
        candidates.append(Detection(box, int(labels[index]), float(scores[index])))
        if len(candidates) == 3000:
            break

    return suppress_overlaps(candidates, overlap)


def suppress_overlaps(candidates: list[Detection], overlap: float) -> tuple[Detection, ...]:
    selected: list[Detection] = []
    for candidate in candidates:
        if any(
            previous.label == candidate.label
            and intersection_over_union(previous.box, candidate.box) > overlap
            for previous in selected
        ):
            continue
        selected.append(candidate)
        if len(selected) == 300:
            break

    return tuple(selected)
04.05

Build. Run. Try your model.

Select a camera explicitly, or process an image offline. Press Q or Escape to stop.

Basics

parse_options(...)
Validates arguments and selects exactly one input: image or camera.
main(...)
Validates the selected source and delegates image or camera processing.
Keep in mind
Symptom
Stopping takes longer than expected.
Cause
A native capture or inference call is still running.
Remedy
Request stop, reject late results and wait for active work before releasing its resources. Backend cancellation depends on platform support.
Terminalbash
python -m badbob_camera --model detector.onnx --labels labels.txt --image frame.png --output result.png

python -m badbob_camera --model detector.onnx --labels labels.txt --camera 0

04.06 / Best practices

Small details. Better examples.

  • Keep capture and inference off the UI thread. Bound the queue instead of collecting a backlog of old frames.
  • Treat image size, crop, orientation and coordinates as one contract. Test it with known boxes before trusting an overlay.
  • Request stop, reject late results and wait for active work before releasing its resources. Backend cancellation depends on platform support.