CHINESE-OCR
CHINESE-OCR copied to clipboard
ckpt的路径问题
ckpt_path = '/Users/xiaofeng/Code/Github/dataset/CHINESE_OCR/ctpn/ctpn/retrain/ckpt' ckpt = tf.train.get_checkpoint_state(ckpt_path) reader = tf.train.NewCheckpointReader(ckpt.model_checkpoint_path) var_to_shape_map = reader.get_variable_to_shape_map() for key in var_to_shape_map:
这里怎么改呢
I got the same problem, I used tensorflow 1.14.0. I changed ckpt_path and tensorflow to 1.7.0. Cannot fix it. I think the author deleted the pretrained model as checkpoint. Can anyone resolve it?
I Have sovled the problem
view this issue
https://github.com/xiaofengShi/CHINESE-OCR/issues/83 Just download the modes step by step and set your path! @mangoHoli