Open ratsuki opened 6 years ago
Hi ratsuki,
This error is caused by the version incompatibility of Tensorflow. I have updated the code, and now it should be OK to run with TF1.0+.
when i run this command
python convert_icdar.py --source_dir D://LSGAN-master/data --target_dir D://LSGAN-master/data
i have this problem
C:\Users\USER\AppData\Local\conda\conda\envs\py35\lib\site-packages\h5py__init__.py:34: FutureWarning: Conversion of the second argument of issubdtype from float
to np.floating
is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type
.
from ._conv import register_converters as _register_converters
La syntaxe de la commande n’est pas correcte.
anyone have idea please
.............
the error is: Variable g_h0_lin/Matrix/Adam/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?