训练一个深度学习检测模型，突然出现：
是因为next(batch_iterator)，可能迭代器读出来的数据为空。
# load train data
# 原先代码
images, targets = next(batch_iterator)
# 更改为：
try:
images, targets = next(batch_iterator)
except:
batch_iterator = iter(data_loader)
images, targets = next(batch_iterator)