WARNING:root:NaN or Inf found in input tensor.

[FengHaobo]

When I use my own data set, the loss appears nan, and it reports WARNING:root:NaN or Inf found in input tensor. What is the reason?

**Traceback (most recent call last):
File "train.py", line 114, in
main()
File "train.py", line 105, in main
model = train(cfg, args)
File "train.py", line 44, in train
model = do_train(cfg, model, train_loader, optimizer, scheduler, checkpointer, device, arguments, args)
File "D:\Document\PersonalDocuments\FileCollection\All_Programs\Python\MyPaperExperiment\lufficc\original\SSD-master\ssd\engine\trainer.py", line
76, in do_train
for iteration, (images, targets, _) in enumerate(data_loader, start_iter):
File "D:\Software\ProgrammingTools\Anaconda\envs\torch1.6\lib\site-packages\torch\utils\data\dataloader.py", line 363, in next
data = self._next_data()
File "D:\Software\ProgrammingTools\Anaconda\envs\torch1.6\lib\site-packages\torch\utils\data\dataloader.py", line 989, in _next_data
return self._process_data(data)
File "D:\Software\ProgrammingTools\Anaconda\envs\torch1.6\lib\site-packages\torch\utils\data\dataloader.py", line 1014, in _process_data
data.reraise()
File "D:\Software\ProgrammingTools\Anaconda\envs\torch1.6\lib\site-packages\torch_utils.py", line 395, in reraise
raise self.exc_type(msg)
cv2.error: Caught error in DataLoader worker process 1.
Original Traceback (most recent call last):
File "D:\Software\ProgrammingTools\Anaconda\envs\torch1.6\lib\site-packages\torch\utils\data_utils\worker.py", line 185, in _worker_loop
data = fetcher.fetch(index)
File "D:\Software\ProgrammingTools\Anaconda\envs\torch1.6\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "D:\Software\ProgrammingTools\Anaconda\envs\torch1.6\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "D:\Document\PersonalDocuments\FileCollection\All_Programs\Python\MyPaperExperiment\lufficc\original\SSD-master\ssd\data\datasets\voc.py", l
ine 44, in getitem
image, boxes, labels = self.transform(image, boxes, labels)
File "D:\Document\PersonalDocuments\FileCollection\All_Programs\Python\MyPaperExperiment\lufficc\original\SSD-master\ssd\data\transforms\transfor
ms.py", line 75, in call
img, boxes, labels = t(img, boxes, labels)
File "D:\Document\PersonalDocuments\FileCollection\All_Programs\Python\MyPaperExperiment\lufficc\original\SSD-master\ssd\data\transforms\transfor
ms.py", line 135, in call
self.size))
cv2.error: OpenCV(4.5.4) 👎 error: (-5:Bad argument) in function 'resize'

Overload resolution failed:

• Conversion error: src
• Expected Ptrcv::UMat for argument 'src'**

[glt999]

Have you solved it? I also encountered this problem