getting error in build_train_loader

[farhadi76m]

I wanted to train this model in a single GPU (Google Colab), but I've gotten this error! while I settled the --gpu_num 1 and also I changed the number of workers to either 0 and 1 , but it didn't work ! I faced with this error :

Traceback (most recent call last): File "/content/RbA/train_net.py", line 396, in <module> launch( File "/content/detectron2/detectron2/engine/launch.py", line 84, in launch main_func(*args) File "/content/RbA/train_net.py", line 384, in main trainer = Trainer(cfg) File "/content/detectron2/detectron2/engine/defaults.py", line 378, in __init__ data_loader = self.build_train_loader(cfg) File "/content/RbA/train_net.py", line 175, in build_train_loader return build_detection_train_loader(cfg, mapper=mapper) File "/content/detectron2/detectron2/config/config.py", line 208, in wrapped return orig_func(**explicit_args) File "/content/detectron2/detectron2/data/build.py", line 549, in build_detection_train_loader return build_batch_data_loader( File "/content/detectron2/detectron2/data/build.py", line 339, in build_batch_data_loader data_loader = torchdata.DataLoader( File "/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py", line 238, in __init__ assert prefetch_factor > 0 TypeError: '>' not supported between instances of 'NoneType' and 'int'

moreover I just downloaded cityscapes dataset and have ran your sample command in help . could you help me what's my mistake ? thank you