DOTA数据集 分割图像 Lable和Image数量对不上 问题

分割 DOTA 图像

为了训练 DOTA 数据集，我们以多尺度方式将高分辨率的原始 DOTA 图像分割成 1024x1024 分辨率的图像。

from ultralytics.data.split_dota import split_test, split_trainval

# split train and val set, with labels.
split_trainval(
    data_root="path/to/DOTAv1.0/",
    save_dir="path/to/DOTAv1.0-split/",
    rates=[0.5, 1.0, 1.5],  # multiscale
    gap=500,
)
# split test set, without labels.
split_test(
    data_root="path/to/DOTAv1.0/",
    save_dir="path/to/DOTAv1.0-split/",
    rates=[0.5, 1.0, 1.5],  # multiscale
    gap=500,
)

从源码文件ultralytics.data.split_dota文件中可以看出分割以后 lable和image对不上，导致image数量多余lable数量。

# Ultralytics YOLO 🚀, AGPL-3.0 license

import itertools
from glob import glob
from math import ceil
from pathlib import Path

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

from ultralytics.data.utils import exif_size, img2label_paths
from ultralytics.utils.checks import check_requirements

check_requirements("shapely")
from shapely.geometry import Polygon


def bbox_iof(polygon1, bbox2, eps=1e-6):
    """
    Calculate iofs between bbox1 and bbox2.

    Args:
        polygon1 (np.ndarray): Polygon coordinates, (n, 8).
        bbox2 (np.ndarray): Bounding boxes, (n ,4).
    """
    polygon1 = polygon1.reshape(-1, 4, 2)
    lt_point = np.min(polygon1, axis=-2)
    rb_point = np.max(polygon1, axis=-2)
    bbox1 = np.concatenate([lt_point, rb_point], axis=-1)

    lt = np.maximum(bbox1[:, None, :2], bbox2[..., :2])
    rb = np.minimum(bbox1[:, None, 2:], bbox2[..., 2:])
    wh = np.clip(rb - lt, 0, np.inf)
    h_overlaps = wh[..., 0] * wh[..., 1]

    l, t, r, b = (bbox2[..., i] for i in range(4))
    polygon2 = np.stack([l, t, r, t, r, b, l, b], axis=-1).reshape(-1, 4, 2)

    sg_polys1 = [Polygon(p) for p in polygon1]
    sg_polys2 = [Polygon(p) for p in polygon2]
    overlaps = np.zeros(h_overlaps.shape)
    for p in zip(*np.nonzero(h_overlaps)):
        overlaps[p] = sg_polys1[p[0]].intersection(sg_polys2[p[-1]]).area
    unions = np.array([p.area for p in sg_polys1], dtype=np.float32)
    unions = unions[..., None]

    unions = np.clip(unions,