使用yolov5時出現“assertionerror:no labels found in */*/*/JPEGImages.cache can not train without labels”問題

目前，衆所周知yoloV5模型以速度見長，而對比yolo之前幾個系列的精度是如何表現的呢？YOLOv5在小任務上的精度與YOLOv4大緻相同（在BCCD資料集上yolov4為0.895 mAP；yolov5為0.892 mAP），而在較大的任務（如COCO）上，YOLOv4的性能更高。

是以，在沒有那麼高的精度追求時，yolov5非常适合被選擇部署在邊緣裝置上。網上也有很多資源、部落格說明怎樣使用yolov5進行自制資料集的訓練和推理，本人也是參考網上教程進行yolov5模型訓練，但是，卻遇上了一個很容易被遇上的問題，在此，想借助我的解決方案給大家分享一下。

我遇上的問題如下：

assertionerror: no labels found in */jpegimages.cache. can not train without labels.

首先，我們在YOLOv5官方Github上進行搜尋一下：

可以看出還是有寫多人都遇上了這個問題，通過閱讀這些回答和分析問題處代碼後，我們可以很容易的發現，其實這個問題就是資料準備時出了問題。到底出了什麼問題呢？别急，我們先來看看官方給出的資料準備格式内容：

其yolov5/data/coco.yaml檔案的内容如下：

# download command/URL (optional)
download: https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip

# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
train: ../coco/images/train2017/
val: ../coco/images/train2017/

# number of classes
nc: 80

# class names
names: ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
        'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
        'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
        'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
        'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
        'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
        'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 
        'cell phone', 'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 
        'teddy bear', 'hair drier', 'toothbrush']

           

可以看出，yaml檔案中的訓練集和驗證集資料位址都是為一個裝圖像資料的檔案夾（…/coco/images/train2017/ …/coco/images/train2017/），而不是我之前使用VOC2yolo代碼轉換生成的train.txt和val.txt。雖然，根據yaml檔案中給出的代碼注釋（# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]）可以看出訓練資料能使用三種方式提供給模型進行，但是，其實最為關鍵的是使用VOC2YOLO代碼（網上搜尋一大堆）轉換VOC資料格式至YOLO資料格式隻會生成四樣東西：labels檔案夾（存放yolo格式的注釋檔案）、train.txt（訓練資料的位址）、val.txt（驗證資料的位址）、test.txt（測試資料的位址），而未将訓練、驗證、測試資料按照圖像和标注檔案統一到image和labels檔案夾中，與官方給的資料準備格式一緻。

是以，需要重寫資料準備代碼voc2yolov5.py：

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
import random
from shutil import copyfile

# 根據自己的資料标簽修改
classes=["person"]


def clear_hidden_files(path):
    dir_list = os.listdir(path)
    for i in dir_list:
        abspath = os.path.join(os.path.abspath(path), i)
        if os.path.isfile(abspath):
            if i.startswith("._"):
                os.remove(abspath)
        else:
            clear_hidden_files(abspath)

def convert(size, box):
    dw = 1./size[0]
    dh = 1./size[1]
    x = (box[0] + box[1])/2.0
    y = (box[2] + box[3])/2.0
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x*dw
    w = w*dw
    y = y*dh
    h = h*dh
    return (x,y,w,h)

def convert_annotation(image_id):
    in_file = open('VOCdevkit/VOC2007/Annotations/%s.xml' %image_id)
    out_file = open('VOCdevkit/VOC2007/YOLOLabels/%s.txt' %image_id, 'w')
    tree=ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)

    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
        bb = convert((w,h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
    in_file.close()
    out_file.close()

wd = os.getcwd()
wd = os.getcwd()
data_base_dir = os.path.join(wd, "VOCdevkit/")
if not os.path.isdir(data_base_dir):
    os.mkdir(data_base_dir)
work_sapce_dir = os.path.join(data_base_dir, "VOC2007/")
if not os.path.isdir(work_sapce_dir):
    os.mkdir(work_sapce_dir)
annotation_dir = os.path.join(work_sapce_dir, "Annotations/")
if not os.path.isdir(annotation_dir):
        os.mkdir(annotation_dir)
clear_hidden_files(annotation_dir)
image_dir = os.path.join(work_sapce_dir, "JPEGImages/")
if not os.path.isdir(image_dir):
        os.mkdir(image_dir)
clear_hidden_files(image_dir)
yolo_labels_dir = os.path.join(work_sapce_dir, "YOLOLabels/")
if not os.path.isdir(yolo_labels_dir):
        os.mkdir(yolo_labels_dir)
clear_hidden_files(yolo_labels_dir)
yolov5_images_dir = os.path.join(data_base_dir, "images/")
if not os.path.isdir(yolov5_images_dir):
        os.mkdir(yolov5_images_dir)
clear_hidden_files(yolov5_images_dir)
yolov5_labels_dir = os.path.join(data_base_dir, "labels/")
if not os.path.isdir(yolov5_labels_dir):
        os.mkdir(yolov5_labels_dir)
clear_hidden_files(yolov5_labels_dir)
yolov5_images_train_dir = os.path.join(yolov5_images_dir, "train/")
if not os.path.isdir(yolov5_images_train_dir):
        os.mkdir(yolov5_images_train_dir)
clear_hidden_files(yolov5_images_train_dir)
yolov5_images_test_dir = os.path.join(yolov5_images_dir, "val/")
if not os.path.isdir(yolov5_images_test_dir):
        os.mkdir(yolov5_images_test_dir)
clear_hidden_files(yolov5_images_test_dir)
yolov5_labels_train_dir = os.path.join(yolov5_labels_dir, "train/")
if not os.path.isdir(yolov5_labels_train_dir):
        os.mkdir(yolov5_labels_train_dir)
clear_hidden_files(yolov5_labels_train_dir)
yolov5_labels_test_dir = os.path.join(yolov5_labels_dir, "val/")
if not os.path.isdir(yolov5_labels_test_dir):
        os.mkdir(yolov5_labels_test_dir)
clear_hidden_files(yolov5_labels_test_dir)

train_file = open(os.path.join(wd, "yolov5_train.txt"), 'w')
test_file = open(os.path.join(wd, "yolov5_val.txt"), 'w')
train_file.close()
test_file.close()
train_file = open(os.path.join(wd, "yolov5_train.txt"), 'a')
test_file = open(os.path.join(wd, "yolov5_val.txt"), 'a')
list_imgs = os.listdir(image_dir) # list image files
probo = random.randint(1, 100)
print("Probobility: %d" % probo)
for i in range(0,len(list_imgs)):
    path = os.path.join(image_dir,list_imgs[i])
    if os.path.isfile(path):
        image_path = image_dir + list_imgs[i]
        voc_path = list_imgs[i]
        (nameWithoutExtention, extention) = os.path.splitext(os.path.basename(image_path))
        (voc_nameWithoutExtention, voc_extention) = os.path.splitext(os.path.basename(voc_path))
        annotation_name = nameWithoutExtention + '.xml'
        annotation_path = os.path.join(annotation_dir, annotation_name)
        label_name = nameWithoutExtention + '.txt'
        label_path = os.path.join(yolo_labels_dir, label_name)
    probo = random.randint(1, 100)
    print("Probobility: %d" % probo)
    if(probo < 80): # train dataset
        if os.path.exists(annotation_path):
            train_file.write(image_path + '\n')
            convert_annotation(nameWithoutExtention) # convert label
            copyfile(image_path, yolov5_images_train_dir + voc_path)
            copyfile(label_path, yolov5_labels_train_dir + label_name)
    else: # test dataset
        if os.path.exists(annotation_path):
            test_file.write(image_path + '\n')
            convert_annotation(nameWithoutExtention) # convert label
            copyfile(image_path, yolov5_images_test_dir + voc_path)
            copyfile(label_path, yolov5_labels_test_dir + label_name)
train_file.close()
test_file.close()
           

通過這個代碼，你就會得到兩個檔案夾：images和labels，分别存放着圖像資料和标注資訊，且兩個檔案夾中都含有：train和val兩個檔案夾，訓練時，修改yaml檔案就可以使用images下train和val的路徑，進而解決“assertionerror:no labels found in ***/JPEGImages.cache can not train without labels”的問題。