【bug记录】yolov7 AssertionError: train: No labels in ...train_list.cache. Can not train without

问题描述

我在用yolov7跑自己的visdrone数据集时，遇到了如下报错：

train: WARNING: No labels found in datasets/VisDrone/train_list.cache. See https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data                                                 
train: New cache created: datasets/VisDrone/train_list.cache                                                                                                                            
Traceback (most recent call last):                                                                                                                                                      
  File "train.py", line 616, in <module>                                                                                                                                                
    train(hyp, opt, device, tb_writer)                                                                                                                                                  
  File "train.py", line 245, in train                                                                                                                                                   
    dataloader, dataset = create_dataloader(train_path, imgsz, batch_size, gs, opt,                                                                                                     
  File "/disk2/lxs/yolov7/utils/datasets.py", line 69, in create_dataloader                                                                                                             
    dataset = LoadImagesAndLabels(path, imgsz, batch_size,                                                                                                                              
  File "/disk2/lxs/yolov7/utils/datasets.py", line 403, in __init__                                                                                                                     
    assert nf > 0 or not augment, f'{prefix}No labels in {cache_path}. Can not train without labels. See {help_url}'                                                                    
AssertionError: train: No labels in datasets/VisDrone/train_list.cache. Can not train without labels. See https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data   

---

---

解决方案：

提示：如果train_list.txt中使用的是相对路径，建议全部改为绝对路径。生成train_list.txt代码如下

# -*-coding:utf-8-*-
# 生成文件夹中所有文件的路径到txt
import os


def listdir(path, list_name):  # 传入存储的list
    for file in os.listdir(path):
        file_path = os.path.join(path, file)
        if os.path.isdir(file_path):
            listdir(file_path, list_name)
        else:
            list_name.append(file_path)


list_name = []
path = '/disk2/lxs/yolov7/datasets/VisDrone/images/test/'  # 文件夹路径
listdir(path, list_name)
print(list_name)

with open('./datasets/VisDrone/test_list.txt', 'w') as f:  # 要存入的txt
    write = ''
    for i in list_name:
        write = write + str(i) + '\n'
    f.write(write)