problem when use the pytorch version,have no idea with it

Traceback (most recent call last):
File "src/netprobe_pytorch.py", line 291, in
split=args.split, cl_args=args, verbose=True)
File "src/netprobe_pytorch.py", line 52, in create_probe
data = loadseg.SegmentationData(args.dataset)
File "/home/czy/NetDissect/src/loadseg.py", line 63, in __init__
self.image = [decode_index_dict(r) for r in DictUnicodeReader(f)]
File "/home/czy/NetDissect/src/unicsv.py", line 48, in __init__
self.reader = csv.DictReader(f, dialect=dialect, **kwds)
File "/home/czy/.conda/envs/python36/lib/python3.6/csv.py", line 87, in __init__
self.reader = reader(f, dialect, *args, **kwds)
TypeError: argument 1 must be an iterator

Start by reproducing the PyTorch entry point in src/netprobe_pytorch.py, then trace create_probe into src/loadseg.py and src/unicsv.py where the traceback reaches csv.DictReader. Check the dataset-loading path and Python compatibility, and consider the issue done when the PyTorch version starts without this TypeError.

索引モデルが issue の本文から書いたものです。