There was a problem when training on the shanghaitech dataset

[Yellow-Champagne]

Traceback (most recent call last):
Training Epoch 1 .... 0 batches
File "D:/zgy/LCFCN-master/main.py", line 45, in
main()
File "D:/zgy/LCFCN-master/main.py", line 36, in main
train.train(dataset_name, model_name, metric_name, path_history, path_model, path_opt, path_best_model, args.reset)
File "D:\zgy\LCFCN-master\train.py", line 76, in train
epoch=epoch)
File "D:\zgy\LCFCN-master\utils.py", line 28, in fit
for i, batch in enumerate(dataloader):
File "D:\Anaconda\envs\py-zhu\lib\site-packages\torch\utils\data\dataloader.py", line 614, in next
indices = next(self.sample_iter) # may raise StopIteration
File "D:\Anaconda\envs\py-zhu\lib\site-packages\torch\utils\data\sampler.py", line 160, in iter
for idx in self.sampler:
File "D:\zgy\LCFCN-master\utils.py", line 234, in iter
indices = np.random.randint(0, self.n_samples, self.size)
File "mtrand.pyx", line 993, in mtrand.RandomState.randint
ValueError: low >= high