inference.py

import cv2
import numpy as np
import onnxruntime
from PIL import Image

class_names = [100, 120, 20, 30, 40, 15, 50, 60, 70, 80]
def preprocess(img, input_size, swap=(2, 0, 1)):
    if len(img.shape) == 3:
        padded_img = np.ones((input_size[0], input_size[1], 3), dtype=np.uint8) * 114
    else:
        padded_img = np.ones(input_size, dtype=np.uint8) * 114

    r = min(input_size[0] / img.shape[0], input_size[1] / img.shape[1])
    resized_img = cv2.resize(
        img,
        (int(img.shape[1] * r), int(img.shape[0] * r)),
        interpolation=cv2.INTER_LINEAR,
    ).astype(np.uint8)
    padded_img[: int(img.shape[0] * r), : int(img.shape[1] * r)] = resized_img

    padded_img = padded_img.transpose(swap)
    padded_img = np.ascontiguousarray(padded_img, dtype=np.float32)
    return padded_img, r

def nms(boxes, scores, nms_thr):
    """Single class NMS implemented in Numpy."""
    x1 = boxes[:, 0]
    y1 = boxes[:, 1]
    x2 = boxes[:, 2]
    y2 = boxes[:, 3]

    areas = (x2 - x1 + 1) * (y2 - y1 + 1)
    order = scores.argsort()[::-1]

    keep = []
    while order.size > 0:
        i = order[0]
        keep.append(i)
        xx1 = np.maximum(x1[i], x1[order[1:]])
        yy1 = np.maximum(y1[i], y1[order[1:]])
        xx2 = np.minimum(x2[i], x2[order[1:]])
        yy2 = np.minimum(y2[i], y2[order[1:]])

        w = np.maximum(0.0, xx2 - xx1 + 1)
        h = np.maximum(0.0, yy2 - yy1 + 1)
        inter = w * h
        ovr = inter / (areas[i] + areas[order[1:]] - inter)

        inds = np.where(ovr <= nms_thr)[0]
        order = order[inds + 1]

    return keep

def multiclass_nms(boxes, scores, nms_thr, score_thr, class_agnostic=True):
    """Multiclass NMS implemented in Numpy"""
    if class_agnostic:
        nms_method = multiclass_nms_class_agnostic
    else:
        nms_method = multiclass_nms_class_aware
    return nms_method(boxes, scores, nms_thr, score_thr)


def multiclass_nms_class_aware(boxes, scores, nms_thr, score_thr):
    """Multiclass NMS implemented in Numpy. Class-aware version."""
    final_dets = []
    num_classes = scores.shape[1]
    for cls_ind in range(num_classes):
        cls_scores = scores[:, cls_ind]
        valid_score_mask = cls_scores > score_thr
        if valid_score_mask.sum() == 0:
            continue
        else:
            valid_scores = cls_scores[valid_score_mask]
            valid_boxes = boxes[valid_score_mask]
            keep = nms(valid_boxes, valid_scores, nms_thr)
            if len(keep) > 0:
                cls_inds = np.ones((len(keep), 1)) * cls_ind
                dets = np.concatenate(
                    [valid_boxes[keep], valid_scores[keep, None], cls_inds], 1
                )
                final_dets.append(dets)
    if len(final_dets) == 0:
        return None
    return np.concatenate(final_dets, 0)


def multiclass_nms_class_agnostic(boxes, scores, nms_thr, score_thr):
    """Multiclass NMS implemented in Numpy. Class-agnostic version."""
    cls_inds = scores.argmax(1)
    cls_scores = scores[np.arange(len(cls_inds)), cls_inds]

    valid_score_mask = cls_scores > score_thr
    if valid_score_mask.sum() == 0:
        return None
    valid_scores = cls_scores[valid_score_mask]
    valid_boxes = boxes[valid_score_mask]
    valid_cls_inds = cls_inds[valid_score_mask]
    keep = nms(valid_boxes, valid_scores, nms_thr)
    if keep:
        dets = np.concatenate(
            [valid_boxes[keep], valid_scores[keep, None], valid_cls_inds[keep, None]], 1
        )
    return dets
    
def demo_postprocess(outputs, img_size, p6=False):

    grids = []
    expanded_strides = []

    if not p6:
        strides = [8, 16, 32]
    else:
        strides = [8, 16, 32, 64]

    hsizes = [img_size[0] // stride for stride in strides]
    wsizes = [img_size[1] // stride for stride in strides]

    for hsize, wsize, stride in zip(hsizes, wsizes, strides):
        xv, yv = np.meshgrid(np.arange(wsize), np.arange(hsize))
        grid = np.stack((xv, yv), 2).reshape(1, -1, 2)
        grids.append(grid)
        shape = grid.shape[:2]
        expanded_strides.append(np.full((*shape, 1), stride))

    grids = np.concatenate(grids, 1)
    expanded_strides = np.concatenate(expanded_strides, 1)
    outputs[..., :2] = (outputs[..., :2] + grids) * expanded_strides
    outputs[..., 2:4] = np.exp(outputs[..., 2:4]) * expanded_strides

    return outputs

def prediction(img):

    img, ratio = preprocess(img, [640, 640])

    session = onnxruntime.InferenceSession("yolox_s.onnx")

    ort_inputs = {session.get_inputs()[0].name: img[None, :, :, :]}
    output = session.run(None, ort_inputs)
    predictions = demo_postprocess(output[0], [640, 640])[0]

    boxes = predictions[:, :4]
    scores = predictions[:, 4:5] * predictions[:, 5:]

    boxes_xyxy = np.ones_like(boxes)
    boxes_xyxy[:, 0] = boxes[:, 0] - boxes[:, 2]/2.
    boxes_xyxy[:, 1] = boxes[:, 1] - boxes[:, 3]/2.
    boxes_xyxy[:, 2] = boxes[:, 0] + boxes[:, 2]/2.
    boxes_xyxy[:, 3] = boxes[:, 1] + boxes[:, 3]/2.
    boxes_xyxy /= ratio
    dets = multiclass_nms(boxes_xyxy, scores, nms_thr=0.45, score_thr=0.1)
    if dets is not None:
        boxes, cls_ids, score = dets[:, :4], dets[:, 4], dets[:, 5]
    return boxes, cls_ids, score

def vis(img, boxes, scores, cls_ids, conf=0.5):
    for i in range(len(boxes)):
        box = boxes[i]
        cls_id = int(cls_ids[i])
        score = scores[i]
        if score < conf:
            continue
        x0 = int(box[0])
        y0 = int(box[1])
        x1 = int(box[2])
        y1 = int(box[3])

        color = (0, 0, 255)
        text = '{} km/h:{:.1f}%'.format(class_names[cls_id], score * 100)
        txt_color = (255, 255, 255)
        font = cv2.FONT_HERSHEY_DUPLEX

        txt_size = cv2.getTextSize(text, font, 0.6, 1)[0]
        cv2.rectangle(img, (x0, y0), (x1, y1), color, 2)

        txt_bk_color = (0, 0, 255)
        cv2.rectangle(
            img,
            (x0, y0 - 1),
            (x0 + txt_size[0] + 1, y0 - int(1.5*txt_size[1])),
            txt_bk_color,
            -1
        )
        cv2.putText(img, text, (x0, y0-int(0.5*txt_size[1])), font, 0.6, txt_color, thickness=1)
        img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    return Image.fromarray(img)