训练问题

[Waynepoo]

你好，我在训练过程中遇到： Traceback (most recent call last): File "/mnt/data/ocr/crnn/Lets_OCR-master/recognizer/crnn/lib/dataset.py", line 55, in getitem img = Image.open(buf).convert('L') File "/opt/conda/lib/python3.6/site-packages/PIL/Image.py", line 2818, in open raise IOError("cannot identify image file %r" % (filename if filename else fp)) OSError: cannot identify image file <_io.BytesIO object at 0x7fae42db1e08>

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "train.py", line 163, in cost = trainBatch(net, criterion, optimizer, train_iter) File "train.py", line 70, in trainBatch data = train_iter.next() File "/opt/conda/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 346, in next data = self.dataset_fetcher.fetch(index) # may raise StopIteration File "/opt/conda/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 "/opt/conda/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/mnt/data/ocr/crnn/Lets_OCR-master/recognizer/crnn/lib/dataset.py", line 58, in getitem return self[index + 1] File "/mnt/data/ocr/crnn/Lets_OCR-master/recognizer/crnn/lib/dataset.py", line 58, in getitem return self[index + 1] File "/mnt/data/ocr/crnn/Lets_OCR-master/recognizer/crnn/lib/dataset.py", line 58, in getitem return self[index + 1] [Previous line repeated 325 more times] File "/mnt/data/ocr/crnn/Lets_OCR-master/recognizer/crnn/lib/dataset.py", line 55, in getitem img = Image.open(buf).convert('L') File "/opt/conda/lib/python3.6/site-packages/PIL/Image.py", line 2804, in open im = _open_core(fp, filename, prefix) File "/opt/conda/lib/python3.6/site-packages/PIL/Image.py", line 2790, in _open_core im = factory(fp, filename) File "/opt/conda/lib/python3.6/site-packages/PIL/ImageFile.py", line 106, in init self._open() File "/opt/conda/lib/python3.6/site-packages/PIL/IptcImagePlugin.py", line 93, in _open tag, size = self.field() File "/opt/conda/lib/python3.6/site-packages/PIL/IptcImagePlugin.py", line 69, in field tag = i8(s[1]), i8(s[2]) RecursionError: maximum recursion depth exceeded

能帮忙看看吗 ，谢谢

[Yaoxingtian]

@Waynepoo 您好！ 请问您解决这个问题了吗，我也遇到到这个问题了，可以分享一下吗，谢谢！

[Bonnie-gift]

我也遇到了 求帮助