mobiledets-yolov4代码出错

问题遇到的现象和发生背景

代码出错的问题

问题相关代码，请勿粘贴截图

Traceback (most recent call last):
File "C:/Users/hpc/codes/mobiledets-yolov4-pytorch-main/train.py", line 270, in
train(freeze, paras, loaders, model, backs, logger, draw=False)
File "C:/Users/hpc/codes/mobiledets-yolov4-pytorch-main/train.py", line 149, in train
for batch_i, (_, imgs, boxes) in enumerate(train_dataloader):
File "C:\Users\hpc.conda\envs\pytorch1.8_gpu\lib\site-packages\torch\utils\data\dataloader.py", line 521, in next
data = self._next_data()
File "C:\Users\hpc.conda\envs\pytorch1.8_gpu\lib\site-packages\torch\utils\data\dataloader.py", line 561, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "C:\Users\hpc.conda\envs\pytorch1.8_gpu\lib\site-packages\torch\utils\data_utils\fetch.py", line 49, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "C:\Users\hpc.conda\envs\pytorch1.8_gpu\lib\site-packages\torch\utils\data_utils\fetch.py", line 49, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "C:\Users\hpc\codes\mobiledets-yolov4-pytorch-main\dataset\datasets.py", line 238, in getitem
img, boxes = random_crop_resize(np.copy(img), np.copy(boxes))
File "C:\Users\hpc\codes\mobiledets-yolov4-pytorch-main\dataset\data_augmentation.py", line 174, in random_crop_resize
limit_l = boxes[:, 1].max()
File "C:\Users\hpc.conda\envs\pytorch1.8_gpu\lib\site-packages\numpy\core_methods.py", line 40, in _amax
return umr_maximum(a, axis, None, out, keepdims, initial, where)
ValueError: zero-size array to reduction operation maximum which has no identity

运行结果及报错内容

我的解答思路和尝试过的方法

我想要达到的结果

应该是读取的数据有问题