货运列车目标检测实验记录

最新推荐文章于 2024-03-28 07:33:33 发布

layandtry

最新推荐文章于 2024-03-28 07:33:33 发布

阅读量778

点赞数

分类专栏：深度学习文章标签：深度学习 python

本文链接：https://blog.csdn.net/wlw8023diya/article/details/117166587

版权

本文记录了一次使用YOLOv4进行货运列车目标检测的实验过程，包括问题描述、分析、解决方法。在实验中，作者遇到训练权重问题，如标签文件错误、代码缩进问题和数据转换错误。通过调整代码和环境，最终解决了这些问题，并进行了新权重的训练。下一步计划使用新权重进行输入预测。

摘要由CSDN通过智能技术生成

问题描述1

Traceback (most recent call last):
  File "train.py", line 274, in <module>
    fit_one_epoch(net,yolo_losses,epoch,epoch_size,epoch_size_val,gen,gen_val,Freeze_Epoch,Cuda)
  File "train.py", line 51, in fit_one_epoch
    for iteration, batch in enumerate(gen):
  File "/home/ubuntu-gpu/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 819, in __next__
    return self._process_data(data)
  File "/home/ubuntu-gpu/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 846, in _process_data
    data.reraise()
  File "/home/ubuntu-gpu/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/_utils.py", line 369, in reraise
    raise self.exc_type(msg)
FileNotFoundError: Caught FileNotFoundError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/home/ubuntu-gpu/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
    data = fetcher.fetch(index)
  File "/home/ubuntu-gpu/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/ubuntu-gpu/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/home/ubuntu-gpu/wangmiao/yolov4-pytorch-master/utils/dataloader.py", line 238, in __getitem__
    img, y = self.get_random_data(lines[index], self.image_size[0:2], random=self.is_train)
  File "/home/ubuntu-gpu/wangmiao/yolov4-pytorch-master/utils/dataloader.py", line 36, in get_random_data
    image = Image.open(line[0])
  File "/home/ubuntu-gpu/anaconda3/envs/pytorch/lib/python3.6/site-packages/PIL/Image.py", line 2891, in open
    fp = builtins.open(filename, "rb")
FileNotFoundError: [Errno 2] No such file or directory: 'D:\\yolov4\\yolov4-pytorch-master/VOCdevkit/VOC2007/JPEGImages/797.jpg'

分析：

158     anchors_path = 'model_data/yolo_anchors.txt'
159     classes_path = 'model_data/traindataset_classes.txt'
        model_path = "model_data/yolo4_weights.pth"
        
            ：lr = 1e-3
238         Batch_size = 4
239         Init_Epoch = 0
240         Freeze_Epoch = 50

解决方法：

暂无

实验室服务器：

在yolov4-master-model_raw：
VOC数据集：VOCdevkit----》VOCtrainval_11-May-2012

训练的权重


Epoch15-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch44-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch73-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch16-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch45-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch74-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch17-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch46-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch75-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch18-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch47-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch76-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch19-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch10-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch3-Total_Loss0.0770-Val_Loss0.0039.pth   
Epoch69-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch11-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch40-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch6-Total_Loss0.0029-Val_Loss0.0027.pth
Epoch12-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch41-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch70-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch13-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch42-Total_Loss0.0027-Val_Loss0.0027.pth 
 Epoch71-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch14-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch43-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch72-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch48-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch77-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch1-Total_Loss27.2862-Val_Loss0.1112.pth  
Epoch49-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch78-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch20-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch4-Total_Loss0.0044-Val_Loss0.0040.pth   
Epoch79-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch21-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch50-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch7-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch22-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch51-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch80-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch23-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch52-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch81-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch24-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch53-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch82-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch25-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch54-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch83-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch26-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch55-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch84-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch27-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch56-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch85-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch28-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch57-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch86-Total_Loss0.0027-Val_Loss0.0027.pth
Epoch29-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch58-Total_Loss0.0027-Val_Loss0.0027.pth  
Epoch87-Total_Loss0.0027-Val_Loss0