multimodal/YOLOX/yolox/utils/demo_utils.py

#!/usr/bin/env python3
# Copyright (c) Megvii Inc. All rights reserved.

import os
import random

import cv2
import numpy as np

__all__ = [
    "mkdir", "nms", "multiclass_nms", "demo_postprocess", "random_color", "visualize_assign"
]


def random_color():
    return random.randint(0, 255), random.randint(0, 255), random.randint(0, 255)


def visualize_assign(img, boxes, coords, match_results, save_name=None) -> np.ndarray:
    """visualize label assign result.

    Args:
        img: img to visualize
        boxes: gt boxes in xyxy format
        coords: coords of matched anchors
        match_results: match results of each gt box and coord.
        save_name: name of save image, if None, image will not be saved. Default: None.
    """
    for box_id, box in enumerate(boxes):
        x1, y1, x2, y2 = box
        color = random_color()
        assign_coords = coords[match_results == box_id]
        if assign_coords.numel() == 0:
            # unmatched boxes are red
            color = (0, 0, 255)
            cv2.putText(
                img, "unmatched", (int(x1), int(y1) - 5),
                cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 1
            )
        else:
            for coord in assign_coords:
                # draw assigned anchor
                cv2.circle(img, (int(coord[0]), int(coord[1])), 3, color, -1)
        cv2.rectangle(img, (int(x1), int(y1)), (int(x2), int(y2)), color, 2)

    if save_name is not None:
        cv2.imwrite(save_name, img)

    return img


def mkdir(path):
    if not os.path.exists(path):
        os.makedirs(path)


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