Paddledet-Training rotierende Zielerkennung ppyoloe-r Training eigener Datensatz

1. Datenkonvertierung
labelme2coco, ursprünglich wurden die von labelme markierten Punkte von opencv in 4 Koordinaten konvertiert

# encoding=utf-8
import argparse
import collections
import datetime
import glob
import json
import os
import os.path as osp
import sys
import uuid
import cv2
import imgviz
import numpy as np

import labelme

try:
    import pycocotools.mask
except ImportError:
    print("Please install pycocotools:\n\n    pip install pycocotools\n")
    sys.exit(1)


def main():
    input_dir='G:/customer/visionary_s_3d_dete/zhixi'
    output_dir='dataset/zhixi'
    os.makedirs(output_dir)
    os.makedirs(osp.join(output_dir, "JPEGImages"))

    data = dict(
        images=[
            # license, url, file_name, height, width, date_captured, id
        ],
        annotations=[
            # segmentation, area, iscrowd, image_id, bbox, category_id, id
        ],
        categories=[
            # supercategory, id, name
        ],
    )
    data["categories"].append(
        dict(supercategory=None, id=0, name='sack',)
    )

    out_ann_file = osp.join(output_dir, "annotations.json")
    label_files = glob.glob(osp.join(input_dir, "*.json"))
    for image_id, filename in enumerate(label_files):
        print("Generating dataset from:", filename)

        label_file = labelme.LabelFile(filename=filename)

        base = osp.splitext(osp.basename(filename))[0]
        out_img_file = osp.join(output_dir, "JPEGImages", base + ".jpg")

        img = labelme.utils.img_data_to_arr(label_file.imageData)
        imgviz.io.imsave(out_img_file, img)
        data["images"].append(
            dict(
                license=0,
                url=None,
                file_name=osp.relpath(out_img_file, osp.dirname(out_ann_file)),
                height=img.shape[0],
                width=img.shape[1],
                date_captured=None,
                id=image_id,
            )
        )

        masks = {}  # for area
        segmentations = collections.defaultdict(list)  # for segmentation
        for shape in label_file.shapes:
            points = shape["points"]
            label = shape["label"]
            group_id = shape.get("group_id")
            shape_type = shape.get("shape_type")
            mask = labelme.utils.shape_to_mask(
                img.shape[:2], points, shape_type
            )

            if group_id is None:
                group_id = uuid.uuid1()

            instance = (label, group_id)

            if instance in masks:
                masks[instance] = masks[instance] | mask
            else:
                masks[instance] = mask

            if shape_type == "rectangle":
                (x1, y1), (x2, y2) = points
                x1, x2 = sorted([x1, x2])
                y1, y2 = sorted([y1, y2])
                points = [x1, y1, x2, y1, x2, y2, x1, y2]
            if shape_type == "circle":
                (x1, y1), (x2, y2) = points
                r = np.linalg.norm([x2 - x1, y2 - y1])
                # r(1-cos(a/2))<x, a=2*pi/N => N>pi/arccos(1-x/r)
                # x: tolerance of the gap between the arc and the line segment
                n_points_circle = max(int(np.pi / np.arccos(1 - 1 / r)), 12)
                i = np.arange(n_points_circle)
                x = x1 + r * np.sin(2 * np.pi / n_points_circle * i)
                y = y1 + r * np.cos(2 * np.pi / n_points_circle * i)
                points = np.stack((x, y), axis=1).flatten().tolist()
            elif shape_type=="polygon":
                points=np.float32(points)
                rect = cv2.minAreaRect(points)  # 最小外接矩形
                points = cv2.boxPoints(rect).flatten()
                points=points.tolist()
                # points = np.asarray(box).flatten().tolist()

            segmentations[instance].append(points)
        segmentations = dict(segmentations)

        for instance, mask in masks.items():
            mask = np.asfortranarray(mask.astype(np.uint8))
            mask = pycocotools.mask.encode(mask)
            area = float(pycocotools.mask.area(mask))
            bbox = pycocotools.mask.toBbox(mask).flatten().tolist()

            data["annotations"].append(
                dict(
                    id=len(data["annotations"]),
                    image_id=image_id,
                    category_id=0,
                    segmentation=segmentations[instance],
                    area=area,
                    bbox=bbox,
                    iscrowd=0,
                )
            )
    with open(out_ann_file, "w") as f:
        json.dump(data, f)


if __name__ == "__main__":
    main()

2. Ändern Sie die Datei data.yml.
Dieser Pfad sollte entsprechend Ihrer tatsächlichen Situation geändert werden. Wenn es nicht funktioniert, debuggen Sie einfach, um zu sehen, wo das Problem liegt.

metric: RBOX
num_classes: 15

TrainDataset:
  !COCODataSet
    image_dir:
    anno_path: annotations/annotations.json
    dataset_dir: ../dataset/zhixi
    data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd', 'gt_poly']

EvalDataset:
  !COCODataSet
    image_dir:
    anno_path: annotations/annotations.json
    dataset_dir: ../dataset/zhixi
    data_fields: ['image', 'gt_bbox', 'gt_class', 'is_crowd', 'gt_poly']

TestDataset:
  !ImageFolder
    anno_path: annotations/annotations.json
    dataset_dir: ../dataset/zhixi

3.RuntimeError
: (PreconditionNotMet) Die dynamische Bibliothek eines Drittanbieters (cublas64_102.dll;cublas64_10.dll), von der Paddle abhängt, ist nicht richtig konfiguriert. (Fehlercode ist 126)

Lösung: Der Pfad lautet C:\Programme\NVIDIA GPU Computing Toolkit\CUDA\v10.0\bin

Benennen Sie cublas64_100.dll im Bin-Pfad in cublas64_10.dll um

Benennen Sie im Bin-Pfad cusolver64_100 in cusolver64_10 um.
——————————————————
Copyright-Erklärung: Dieser Artikel ist der Originalartikel des CSDN-Bloggers „Earl Li's Finger Sand“ nach CC 4.0 BY -SA-Urheberrechtsvereinbarung, bitte fügen Sie den Original-Quellenlink und diese Erklärung zum Nachdruck bei.
Ursprünglicher Link: https://blog.csdn.net/m0_37690102/article/details/123474171