when i train my dataset with your code from scratch, i modify the ''model_weight='./model/cityscapes/icnet_scapes_train_30k_bnnomerge.npy'''in train.py to
'model_weight = '' ' so i can run it with scratch, but the bug:
NotFoundError (see above for traceback): Unsuccessful TensorSliceReader constructor: Failed to find any matching files for
whats wrong with my operation?
because i can not download the pretrain model ,so i must use train with scratch
hi,nice work !
when i train my dataset with your code from scratch, i modify the ''model_weight='./model/cityscapes/icnet_scapes_train_30k_bnnomerge.npy'''in train.py to 'model_weight = '' ' so i can run it with scratch, but the bug: NotFoundError (see above for traceback): Unsuccessful TensorSliceReader constructor: Failed to find any matching files for whats wrong with my operation?
because i can not download the pretrain model ,so i must use train with scratch