search

herobd / Visual-Template-Free-Form-Parsing

Code for my ICDAR paper "Deep Visual Template-Free Form Parsing"
GNU General Public License v3.0
88 stars 27 forks source link

RecursionError: maximum recursion depth exceeded #7

Open its-charan-here opened 4 years ago

its-charan-here commented 4 years ago

After executing python eval.py -c saved/detector/checkpoint-iteration150000.pth -n 0 -T -a data_loader=special_dataset=simple I am facing Recursion Error, the output looks like this on the console. loaded iteration 125000 added config[data_loader][special_dataset]=simple Traceback (most recent call last): File "eval.py", line 376, in <module> main(args.checkpoint, args.savedir, args.number, index, gpu=args.gpu, shuffle=args.shuffle, setBatch=args.batchsize, config=args.config, thresh=args.thresh, addToConfig=addtoconfig,test=args.test,verbose=args.verbosity) File "eval.py", line 117, in main model = eval(config['arch'])(config['model']) File "/content/drive/My Drive/Yolo Vision template/Visual-Template-Free-Form-Parsing/model/pairing_graph.py", line 49, in __init__ self.detector = eval(checkpoint['config']['arch'])(detector_config) File "/content/drive/My Drive/Yolo Vision template/Visual-Template-Free-Form-Parsing/model/pairing_graph.py", line 49, in __init__ self.detector = eval(checkpoint['config']['arch'])(detector_config) File "/content/drive/My Drive/Yolo Vision template/Visual-Template-Free-Form-Parsing/model/pairing_graph.py", line 49, in __init__ self.detector = eval(checkpoint['config']['arch'])(detector_config) [Previous line repeated 242 more times] File "/content/drive/My Drive/Yolo Vision template/Visual-Template-Free-Form-Parsing/model/pairing_graph.py", line 46, in __init__ checkpoint = torch.load(config['detector_checkpoint']) File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 595, in load return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args) File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 749, in _legacy_load return legacy_load(f) File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 671, in legacy_load with closing(tarfile.open(fileobj=f, mode='r:', format=tarfile.PAX_FORMAT)) as tar, \ File "/usr/lib/python3.6/tarfile.py", line 1591, in open return func(name, filemode, fileobj, **kwargs) File "/usr/lib/python3.6/tarfile.py", line 1621, in taropen return cls(name, mode, fileobj, **kwargs) File "/usr/lib/python3.6/tarfile.py", line 1445, in __init__ self.name = os.path.abspath(name) if name else None File "/usr/lib/python3.6/posixpath.py", line 379, in abspath if not isabs(path): File "/usr/lib/python3.6/posixpath.py", line 67, in isabs sep = _get_sep(s) RecursionError: maximum recursion depth exceeded

What changes are required to be done ?

herobd commented 4 years ago

Is this the pretrained detector, or your own?

its-charan-here commented 3 years ago

it's a pretrained detector

herobd commented 3 years ago

Whoops. The detector snapshot is actual another snapshot of the pairing model. I'll fix that.

herobd commented 3 years ago

Ok, re-download the weights. It has the correct snapshot now.