search

MaybeShewill-CV / CRNN_Tensorflow

Convolutional Recurrent Neural Networks(CRNN) for Scene Text Recognition
MIT License
1.03k stars 388 forks source link

please can you help me here #412

Closed padmareddy21 closed 4 years ago

padmareddy21 commented 4 years ago

python tools/test_shadownet.py --image_path data/test_images/card.png --weights_path model/shadownet.ckpt --char_dict_path data/char_dict/char_dict_en.json --ord_map_dict_path data/char_dict/ord_map_en.json I0722 17:55:55.043348 18306 utils.py:129] Note: NumExpr detected 12 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8. I0722 17:55:55.043450 18306 utils.py:141] NumExpr defaulting to 8 threads. Namespace(char_dict_path='data/char_dict/char_dict_en.json', image_path='data/test_images/card.png', ord_map_dict_path='data/char_dict/ord_map_en.json', visualize=None, weights_path='model/shadownet.ckpt') Traceback (most recent call last): File "tools/test_shadownet.py", line 160, in is_vis=args.visualize File "tools/test_shadownet.py", line 76, in recognize cv2.imshow('',image) cv2.error: OpenCV(4.1.2) /io/opencv/modules/highgui/src/window.cpp:376: error: (-215:Assertion failed) size.width>0 && size.height>0 in function 'imshow' That image is readable when I am trying with OpenCV but when I am running with model it is unable to read

MaybeShewill-CV commented 4 years ago

@padmareddy21 That's not a bug relative to this repo. You may find a solution yourself:)