训练报错，请问如何解决？

[ouxiand]

报错信息：训练完成一次后出错，没生产pt文件，请问如何解决？
100%|█████████▉| 14.1M/14.1M [32:20<00:01, 10.3kB/s]
100%|██████████| 14.1M/14.1M [32:20<00:00, 13.4kB/s]
100%|██████████| 14.1M/14.1M [32:20<00:00, 7.63kB/s]

Traceback (most recent call last):
File "/detect/yolov5-car-plate/train.py", line 552, in
train(hyp, opt, device, tb_writer)
File "/detect/yolov5-car-plate/train.py", line 90, in train
ckpt = torch.load(weights, map_location=device) # load checkpoint
File "/root/anaconda3/lib/python3.9/site-packages/torch/serialization.py", line 607, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "/root/anaconda3/lib/python3.9/site-packages/torch/serialization.py", line 882, in _load
result = unpickler.load()
File "/root/anaconda3/lib/python3.9/site-packages/torch/serialization.py", line 875, in find_class
return super().find_class(mod_name, name)
AttributeError: Can't get attribute 'SPPF' on <module 'models.common' from '/detect/yolov5-car-plate/models/common.py'>

数据集是这样的：
0 0.5059158805031446 0.5967854647099929 0.2672955974842768 0.2585604472396925 0.4793828616352201 0.6509433962264151 0.5422759433962264 0.6491963661774982 0.5422759433962264 0.6823899371069182 0.47741745283018866 0.6771488469601677

[leatherking]

版本不对，作者使用的是yolov5-4.0版本，解决方案：
1、用last.pt作预训练模型
2、代码会自动下载最新版yolov5s.pt，在yolo5官方代码asset里面下载yolov5-4.0版本的yolov5s.pt

[ouxiand]

就是用last.pt作预训练模型的，不知道为啥错误很多，改完一个有一个，改到后面糊涂了

[ouxiand]

这是用last.pt训练的
Traceback (most recent call last):
File "/detect/yolov5-car-plate/train.py", line 552, in
train(hyp, opt, device, tb_writer)
File "/detect/yolov5-car-plate/train.py", line 285, in train
for i, (imgs, targets, paths, _) in pbar: # batch -------------------------------------------------------------
File "/root/anaconda3/lib/python3.9/site-packages/tqdm/std.py", line 1195, in iter
for obj in iterable:
File "/detect/yolov5-car-plate/utils/plate_datasets.py", line 104, in iter
yield next(self.iterator)
File "/root/anaconda3/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 521, in next
data = self._next_data()
File "/root/anaconda3/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1183, in _next_data
return self._process_data(data)
File "/root/anaconda3/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1229, in _process_data
data.reraise()
File "/root/anaconda3/lib/python3.9/site-packages/torch/_utils.py", line 434, in reraise
raise exception
TypeError: Caught TypeError in DataLoader worker process 1.
Original Traceback (most recent call last):
File "/root/anaconda3/lib/python3.9/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
data = fetcher.fetch(index)
File "/root/anaconda3/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/root/anaconda3/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 49, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/detect/yolov5-car-plate/utils/plate_datasets.py", line 530, in getitem
img, labels = load_mosaic(self, index)
File "/detect/yolov5-car-plate/utils/plate_datasets.py", line 758, in load_mosaic
x,y = point
TypeError: cannot unpack non-iterable numpy.float32 object

[leatherking]

就是用last.pt作预训练模型的，不知道为啥错误很多，改完一个有一个，改到后面糊涂了

至少没报SPPF的错了，看样子是你数据有点问题

[ouxiand]

@leatherking 能否看看你的数据集，我的数据集发出来了，估计是后面4个点的问题
x1，y1,x2,y2,x3,y3,x4,y4,后面四个点用以下计算：
x1直接除以width出来的数值
y1直接除以height出来的数值

[leatherking]

@leatherking 能否看看你的数据集，我的数据集发出来了，估计是后面4个点的问题 x1，y1,x2,y2,x3,y3,x4,y4,后面四个点用以下计算： x1直接除以width出来的数值 y1直接除以height出来的数值

是的
class, center x, center y, w, h, 左上x, 左上y, 右上x, 右上y, 右下x, 右下y, 左下x, 左下y
x / w
y / h

[ouxiand]

@leatherking 能否发一些你的数据集给验证下 感谢 , （如果可以，[email protected]）