miner.py

from pathlib import Path
import math

import cv2
import numpy as np
import onnxruntime as ort
from numpy import ndarray
from pydantic import BaseModel


class BoundingBox(BaseModel):
    x1: int
    y1: int
    x2: int
    y2: int
    cls_id: int
    conf: float


class TVFrameResult(BaseModel):
    frame_id: int
    boxes: list[BoundingBox]
    keypoints: list[tuple[int, int]]


class Miner:
    """ONNX Runtime miner for single-class road-sign detection.

    Pipeline: letterbox → ORT → conf filter (+ rescue) → unletterbox →
    sanity filter → per-class hard NMS → cap max_det.
    """

    class_names = ["road_sign"]
    _model_class_order = ["road_sign"]

    iou_thres = 0.5
    max_det = 150

    _conf_thres_array = np.array([0.175], dtype=np.float32)
    _bonus_array = np.array([0.1], dtype=np.float32)

    min_box_area = 8 * 8
    min_side = 3
    max_aspect_ratio = 12.0

    def __init__(self, path_hf_repo: Path) -> None:
        model_path = path_hf_repo / "weights.onnx"
        print("ORT version:", ort.__version__)

        try:
            ort.preload_dlls()
            print("✅ onnxruntime.preload_dlls() success")
        except Exception as e:
            print(f"⚠️ preload_dlls failed: {e}")

        print("ORT available providers BEFORE session:", ort.get_available_providers())

        sess_options = ort.SessionOptions()
        sess_options.graph_optimization_level = ort.GraphOptimizationLevel.ORT_ENABLE_ALL
        sess_options.intra_op_num_threads = 2
        sess_options.inter_op_num_threads = 1
        sess_options.execution_mode = ort.ExecutionMode.ORT_SEQUENTIAL

        self.session = ort.InferenceSession(
            str(model_path),
            sess_options=sess_options,
            providers=["CPUExecutionProvider"],
        )
        print("ORT session providers:", self.session.get_providers())

        model_class_order = self._read_model_class_order()
        if model_class_order is None:
            model_class_order = list(self._model_class_order)
            print(f"cls order: no usable ONNX metadata, FALLBACK {model_class_order}")
        else:
            print(f"cls order: from ONNX metadata {model_class_order}")
        self.cls_remap = np.array(
            [self.class_names.index(n) for n in model_class_order],
            dtype=np.int32,
        )

        for inp in self.session.get_inputs():
            print("INPUT:", inp.name, inp.shape, inp.type)
        for out in self.session.get_outputs():
            print("OUTPUT:", out.name, out.shape, out.type)

        self.input_name = self.session.get_inputs()[0].name
        self.output_names = [output.name for output in self.session.get_outputs()]
        self.input_shape = self.session.get_inputs()[0].shape
        self.input_height = self._safe_dim(self.input_shape[2], default=1280)
        self.input_width = self._safe_dim(self.input_shape[3], default=1280)

        print(f"✅ ONNX model loaded from: {model_path}")
        print(f"✅ ONNX input: name={self.input_name}, shape={self.input_shape}")
        print(f"✅ ONNX input size: {self.input_width}x{self.input_height}")
        print(
            "per-class conf: "
            + ", ".join(
                f"{n}={t:.3f}"
                for n, t in zip(self.class_names, self._conf_thres_array.tolist())
            )
        )

        self._warmup()

    def _warmup(self, iters: int = 3) -> None:
        try:
            dummy = np.zeros((720, 1280, 3), dtype=np.uint8)
            for _ in range(max(1, iters)):
                self.predict_batch(batch_images=[dummy], offset=0, n_keypoints=0)
            print(f"✅ warmup: {iters} dummy predict_batch call(s) done")
        except Exception as e:
            print(f"⚠️ warmup skipped: {e}")

    def _read_model_class_order(self) -> list[str] | None:
        try:
            import ast

            meta = self.session.get_modelmeta().custom_metadata_map
            names = ast.literal_eval(meta["names"])
            if isinstance(names, dict):
                order = [str(names[i]) for i in sorted(names)]
            else:
                order = [str(n) for n in names]
        except Exception as e:
            print(f"cls order: could not read ONNX names metadata ({e})")
            return None
        if sorted(order) != sorted(self.class_names):
            print(
                f"cls order: ONNX names {order} do not match expected classes "
                f"{self.class_names}; ignoring metadata"
            )
            return None
        return order

    def __repr__(self) -> str:
        return (
            f"ONNXRuntime(session={type(self.session).__name__}, "
            f"providers={self.session.get_providers()})"
        )

    @staticmethod
    def _safe_dim(value, default: int) -> int:
        return value if isinstance(value, int) and value > 0 else default

    def _letterbox(
        self,
        image: ndarray,
        new_shape: tuple[int, int],
        color=(114, 114, 114),
    ) -> tuple[ndarray, float, tuple[float, float]]:
        h, w = image.shape[:2]
        new_w, new_h = new_shape

        ratio = min(new_w / w, new_h / h)
        resized_w = int(round(w * ratio))
        resized_h = int(round(h * ratio))

        if (resized_w, resized_h) != (w, h):
            interp = cv2.INTER_CUBIC if ratio > 1.0 else cv2.INTER_LINEAR
            image = cv2.resize(image, (resized_w, resized_h), interpolation=interp)

        dw = (new_w - resized_w) / 2.0
        dh = (new_h - resized_h) / 2.0
        left = int(round(dw - 0.1))
        right = int(round(dw + 0.1))
        top = int(round(dh - 0.1))
        bottom = int(round(dh + 0.1))

        padded = cv2.copyMakeBorder(
            image,
            top,
            bottom,
            left,
            right,
            borderType=cv2.BORDER_CONSTANT,
            value=color,
        )
        return padded, ratio, (dw, dh)

    def _preprocess(
        self, image: ndarray
    ) -> tuple[np.ndarray, float, tuple[float, float], tuple[int, int]]:
        orig_h, orig_w = image.shape[:2]
        img, ratio, pad = self._letterbox(image, (self.input_width, self.input_height))
        blob = cv2.dnn.blobFromImage(img, scalefactor=1.0 / 255.0, swapRB=True)
        return blob, ratio, pad, (orig_w, orig_h)

    @staticmethod
    def _clip_boxes(boxes: np.ndarray, image_size: tuple[int, int]) -> np.ndarray:
        w, h = image_size
        boxes[:, 0] = np.clip(boxes[:, 0], 0, w - 1)
        boxes[:, 1] = np.clip(boxes[:, 1], 0, h - 1)
        boxes[:, 2] = np.clip(boxes[:, 2], 0, w - 1)
        boxes[:, 3] = np.clip(boxes[:, 3], 0, h - 1)
        return boxes

    @staticmethod
    def _xywh_to_xyxy(boxes: np.ndarray) -> np.ndarray:
        out = np.empty_like(boxes)
        out[:, 0] = boxes[:, 0] - boxes[:, 2] / 2.0
        out[:, 1] = boxes[:, 1] - boxes[:, 3] / 2.0
        out[:, 2] = boxes[:, 0] + boxes[:, 2] / 2.0
        out[:, 3] = boxes[:, 1] + boxes[:, 3] / 2.0
        return out

    @staticmethod
    def _hard_nms(
        boxes: np.ndarray, scores: np.ndarray, iou_thresh: float
    ) -> np.ndarray:
        n = len(boxes)
        if n == 0:
            return np.array([], dtype=np.intp)
        order = np.argsort(-scores)
        keep: list[int] = []
        while len(order) > 0:
            i = int(order[0])
            keep.append(i)
            if len(order) == 1:
                break
            rest = order[1:]
            xx1 = np.maximum(boxes[i, 0], boxes[rest, 0])
            yy1 = np.maximum(boxes[i, 1], boxes[rest, 1])
            xx2 = np.minimum(boxes[i, 2], boxes[rest, 2])
            yy2 = np.minimum(boxes[i, 3], boxes[rest, 3])
            inter = np.maximum(0.0, xx2 - xx1) * np.maximum(0.0, yy2 - yy1)
            a_i = max(0.0, boxes[i, 2] - boxes[i, 0]) * max(
                0.0, boxes[i, 3] - boxes[i, 1]
            )
            a_r = np.maximum(0.0, boxes[rest, 2] - boxes[rest, 0]) * np.maximum(
                0.0, boxes[rest, 3] - boxes[rest, 1]
            )
            iou = inter / (a_i + a_r - inter + 1e-7)
            order = rest[iou <= iou_thresh]
        return np.array(keep, dtype=np.intp)

    def _per_class_hard_nms(
        self,
        boxes: np.ndarray,
        scores: np.ndarray,
        cls_ids: np.ndarray,
        iou_thresh: float,
    ) -> np.ndarray:
        if len(boxes) == 0:
            return np.array([], dtype=np.intp)
        all_keep: list[int] = []
        for c in np.unique(cls_ids):
            mask = cls_ids == c
            indices = np.where(mask)[0]
            keep = self._hard_nms(boxes[mask], scores[mask], iou_thresh)
            all_keep.extend(indices[keep].tolist())
        all_keep.sort()
        return np.array(all_keep, dtype=np.intp)

    def _conf_filter_mask(
        self, scores: np.ndarray, cls_ids: np.ndarray
    ) -> np.ndarray:
        if len(scores) == 0:
            return np.zeros(0, dtype=bool)
        thr = self._conf_thres_array[cls_ids]
        keep = scores >= thr
        for c in np.unique(cls_ids):
            b = float(self._bonus_array[c])
            if b <= 0.0:
                continue
            cm = cls_ids == c
            if keep[cm].any():
                continue
            idx = np.where(cm)[0]
            top = int(idx[int(np.argmax(scores[idx]))])
            if scores[top] >= self._conf_thres_array[c] - b:
                keep[top] = True
        return keep

    def _filter_sane_boxes(
        self,
        boxes: np.ndarray,
        scores: np.ndarray,
        cls_ids: np.ndarray,
        orig_size: tuple[int, int],
    ) -> tuple[np.ndarray, np.ndarray, np.ndarray]:
        if len(boxes) == 0:
            return boxes, scores, cls_ids
        orig_w, orig_h = orig_size
        image_area = float(orig_w * orig_h)
        keep = []
        for i, box in enumerate(boxes):
            x1, y1, x2, y2 = box.tolist()
            bw = x2 - x1
            bh = y2 - y1
            if bw <= 0 or bh <= 0:
                continue
            if bw < self.min_side or bh < self.min_side:
                continue
            area = bw * bh
            if area < self.min_box_area:
                continue
            if area > 0.95 * image_area:
                continue
            ar = max(bw / max(bh, 1e-6), bh / max(bw, 1e-6))
            if ar > self.max_aspect_ratio:
                continue
            keep.append(i)
        if not keep:
            return (
                np.empty((0, 4), dtype=np.float32),
                np.empty((0,), dtype=np.float32),
                np.empty((0,), dtype=np.int32),
            )
        k = np.array(keep, dtype=np.intp)
        return boxes[k], scores[k], cls_ids[k]

    def _nms_and_cap(
        self,
        boxes: np.ndarray,
        scores: np.ndarray,
        cls_ids: np.ndarray,
    ) -> tuple[np.ndarray, np.ndarray, np.ndarray]:
        if len(boxes) > 1:
            keep = self._per_class_hard_nms(boxes, scores, cls_ids, self.iou_thres)
            boxes, scores, cls_ids = boxes[keep], scores[keep], cls_ids[keep]
        if len(scores) > self.max_det:
            top = np.argsort(-scores)[: self.max_det]
            boxes, scores, cls_ids = boxes[top], scores[top], cls_ids[top]
        return boxes, scores, cls_ids

    @staticmethod
    def _build_results(
        boxes: np.ndarray, scores: np.ndarray, cls_ids: np.ndarray
    ) -> list[BoundingBox]:
        results: list[BoundingBox] = []
        for box, conf, cls_id in zip(boxes, scores, cls_ids):
            x1, y1, x2, y2 = box.tolist()
            if x2 <= x1 or y2 <= y1:
                continue
            results.append(
                BoundingBox(
                    x1=int(math.floor(x1)),
                    y1=int(math.floor(y1)),
                    x2=int(math.ceil(x2)),
                    y2=int(math.ceil(y2)),
                    cls_id=int(cls_id),
                    conf=float(conf),
                )
            )
        return results

    def _decode_final_dets(
        self,
        preds: np.ndarray,
        ratio: float,
        pad: tuple[float, float],
        orig_size: tuple[int, int],
    ) -> list[BoundingBox]:
        if preds.ndim == 3 and preds.shape[0] == 1:
            preds = preds[0]
        if preds.ndim != 2 or preds.shape[1] < 6:
            raise ValueError(f"Unexpected ONNX final-det output shape: {preds.shape}")

        boxes = preds[:, :4].astype(np.float32)
        scores = preds[:, 4].astype(np.float32)
        cls_ids = self.cls_remap[preds[:, 5].astype(np.int32)]

        keep = self._conf_filter_mask(scores, cls_ids)
        boxes, scores, cls_ids = boxes[keep], scores[keep], cls_ids[keep]
        if len(boxes) == 0:
            return []

        pad_w, pad_h = pad
        boxes[:, [0, 2]] -= pad_w
        boxes[:, [1, 3]] -= pad_h
        boxes /= ratio
        boxes = self._clip_boxes(boxes, orig_size)

        boxes, scores, cls_ids = self._filter_sane_boxes(
            boxes, scores, cls_ids, orig_size
        )
        if len(boxes) == 0:
            return []

        boxes, scores, cls_ids = self._nms_and_cap(boxes, scores, cls_ids)
        return self._build_results(boxes, scores, cls_ids)

    def _decode_raw_yolo(
        self,
        preds: np.ndarray,
        ratio: float,
        pad: tuple[float, float],
        orig_size: tuple[int, int],
    ) -> list[BoundingBox]:
        if preds.ndim != 3 or preds.shape[0] != 1:
            raise ValueError(f"Unexpected raw ONNX output shape: {preds.shape}")
        preds = preds[0]
        if preds.shape[0] <= 16 and preds.shape[1] > preds.shape[0]:
            preds = preds.T
        if preds.ndim != 2 or preds.shape[1] < 5:
            raise ValueError(f"Unexpected raw output shape: {preds.shape}")

        boxes_xywh = preds[:, :4].astype(np.float32)
        cls_part = preds[:, 4:].astype(np.float32)
        if cls_part.shape[1] == 1:
            scores = cls_part[:, 0]
            cls_ids = np.zeros(len(scores), dtype=np.int32)
        else:
            cls_ids = np.argmax(cls_part, axis=1).astype(np.int32)
            scores = cls_part[np.arange(len(cls_part)), cls_ids]
        cls_ids = self.cls_remap[cls_ids]

        keep = self._conf_filter_mask(scores, cls_ids)
        boxes_xywh, scores, cls_ids = (
            boxes_xywh[keep],
            scores[keep],
            cls_ids[keep],
        )
        if len(boxes_xywh) == 0:
            return []
        boxes = self._xywh_to_xyxy(boxes_xywh)

        pad_w, pad_h = pad
        boxes[:, [0, 2]] -= pad_w
        boxes[:, [1, 3]] -= pad_h
        boxes /= ratio
        boxes = self._clip_boxes(boxes, orig_size)

        boxes, scores, cls_ids = self._filter_sane_boxes(
            boxes, scores, cls_ids, orig_size
        )
        if len(boxes) == 0:
            return []

        boxes, scores, cls_ids = self._nms_and_cap(boxes, scores, cls_ids)
        return self._build_results(boxes, scores, cls_ids)

    def _postprocess(
        self,
        output: np.ndarray,
        ratio: float,
        pad: tuple[float, float],
        orig_size: tuple[int, int],
    ) -> list[BoundingBox]:
        if output.ndim == 2 and output.shape[1] >= 6:
            return self._decode_final_dets(output, ratio, pad, orig_size)
        if output.ndim == 3 and output.shape[0] == 1 and output.shape[2] == 6:
            return self._decode_final_dets(output, ratio, pad, orig_size)
        return self._decode_raw_yolo(output, ratio, pad, orig_size)

    def _predict_single(self, image: np.ndarray) -> list[BoundingBox]:
        if image is None:
            raise ValueError("Input image is None")
        if not isinstance(image, np.ndarray):
            raise TypeError(f"Input is not numpy array: {type(image)}")
        if image.ndim != 3:
            raise ValueError(f"Expected HWC image, got shape={image.shape}")
        if image.shape[0] <= 0 or image.shape[1] <= 0:
            raise ValueError(f"Invalid image shape={image.shape}")
        if image.shape[2] != 3:
            raise ValueError(f"Expected 3 channels, got shape={image.shape}")
        if image.dtype != np.uint8:
            image = image.astype(np.uint8)

        input_tensor, ratio, pad, orig_size = self._preprocess(image)
        expected = (1, 3, self.input_height, self.input_width)
        if input_tensor.shape != expected:
            raise ValueError(
                f"Bad input tensor shape={input_tensor.shape}, expected={expected}"
            )

        outputs = self.session.run(
            self.output_names, {self.input_name: input_tensor}
        )
        return self._postprocess(outputs[0], ratio, pad, orig_size)

    def predict_batch(
        self,
        batch_images: list[ndarray],
        offset: int,
        n_keypoints: int,
    ) -> list[TVFrameResult]:
        results: list[TVFrameResult] = []
        for frame_number_in_batch, image in enumerate(batch_images):
            try:
                boxes = self._predict_single(image)
            except Exception as e:
                print(
                    f"⚠️ Inference failed for frame "
                    f"{offset + frame_number_in_batch}: {e}"
                )
                boxes = []
            results.append(
                TVFrameResult(
                    frame_id=offset + frame_number_in_batch,
                    boxes=boxes,
                    keypoints=[(0, 0) for _ in range(max(0, int(n_keypoints)))],
                )
            )
        return results