diff --git a/scripts/libraries/ml/ml/postprocessing.py b/scripts/libraries/ml/ml/postprocessing.py index cd6b833fa..7842df13c 100644 --- a/scripts/libraries/ml/ml/postprocessing.py +++ b/scripts/libraries/ml/ml/postprocessing.py @@ -206,3 +206,57 @@ class yolo_v5_postprocess: nms.add_bounding_box(xmin[i], ymin[i], xmax[i], ymax[i], bb_scores[i], bb_classes[i]) return nms.get_bounding_boxes(threshold=self.nms_threshold, sigma=self.nms_sigma) + + +class yolo_v8_postprocess: + _YOLO_V8_CX = const(0) + _YOLO_V8_CY = const(1) + _YOLO_V8_CW = const(2) + _YOLO_V8_CH = const(3) + _YOLO_V8_CLASSES = const(4) + + def __init__(self, threshold=0.6, nms_threshold=0.1, nms_sigma=0.1): + self.threshold = threshold + self.nms_threshold = nms_threshold + self.nms_sigma = nms_sigma + + def __call__(self, model, inputs, outputs): + oh, ow, oc = model.output_shape[0] + class_count = ow - _YOLO_V8_CLASSES + + # Reshape the output to a 2D array + column_outputs = outputs[0].reshape((oh * (_YOLO_V8_CLASSES + class_count), oc)) + + # Threshold all the scores + score_indices = np.max(column_outputs[_YOLO_V8_CLASSES:, :], axis=0) + score_indices = np.nonzero(score_indices > self.threshold)[0] + if not len(score_indices): + return _NO_DETECTION + + # Get the bounding boxes that have a valid score + bb = np.take(column_outputs, score_indices, axis=1) + + # Get the score information + bb_scores = np.max(bb[_YOLO_V8_CLASSES:, :], axis=0) + + # Get the class information + bb_classes = np.argmax(bb[_YOLO_V8_CLASSES:, :], axis=0) + + # Compute the bounding box information + x_center = bb[_YOLO_V8_CX, :] + y_center = bb[_YOLO_V8_CY, :] + w_rel = bb[_YOLO_V8_CW, :] * 0.5 + h_rel = bb[_YOLO_V8_CH, :] * 0.5 + + # Scale the bounding boxes to have enough integer precision for NMS + ib, ih, iw, ic = model.input_shape[0] + xmin = (x_center - w_rel) * iw + ymin = (y_center - h_rel) * ih + xmax = (x_center + w_rel) * iw + ymax = (y_center + h_rel) * ih + + nms = NMS(iw, ih, inputs[0].roi) + for i in range(bb.shape[1]): + nms.add_bounding_box(xmin[i], ymin[i], xmax[i], ymax[i], + bb_scores[i], bb_classes[i]) + return nms.get_bounding_boxes(threshold=self.nms_threshold, sigma=self.nms_sigma)