search

msracver / FCIS

Fully Convolutional Instance-aware Semantic Segmentation
MIT License
1.57k stars 415 forks source link

AssertionError: shape inconsistent for fcis_cls_seg_weight inferred when using own dataset #114

Open NikTRSK opened 6 years ago

NikTRSK commented 6 years ago

Hello,

I'm trying to use FCIS with my own dataset and I've run into the following error message:

Traceback (most recent call last):
  File "experiments/fcis/fcis_end2end_train_test.py", line 14, in <module>
    test.main()
  File "experiments/fcis/../../fcis/test.py", line 52, in main
    args.vis, args.ignore_cache, args.shuffle, config.TEST.HAS_RPN, config.dataset.proposal, args.thresh, logger=logger, output_path=final_output_path)
  File "experiments/fcis/../../fcis/function/test_fcis.py", line 49, in test_fcis
    sym_instance.check_parameter_shapes(arg_params, aux_params, data_shape_dict, is_train=False)
  File "experiments/fcis/../../fcis/../lib/utils/symbol.py", line 53, in check_parameter_shapes
    arg_params[k].shape)
AssertionError: shape inconsistent for fcis_cls_seg_weight inferred (98L, 1024L, 1L, 1L) provided (7938L, 1024L, 1L, 1L)

Has anyone run into a similar problem?