search

Kyubyong / tacotron

A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model
Apache License 2.0
1.83k stars 436 forks source link

Getting around: raise ValueError("Can't load save_path when it is None.") ? #112

Closed CoderReece closed 6 years ago

CoderReece commented 6 years ago

I can't get synthesize to execute. python synthesize.py Graph loaded Traceback (most recent call last): File "synthesize.py", line 48, in <module> synthesize() File "synthesize.py", line 32, in synthesize saver.restore(sess, tf.train.latest_checkpoint(hp.logdir)); print("Restored!") File "C:\Users\Reece\Miniconda3\lib\site-packages\tensorflow\python\training\saver.py", line 1796, in restore raise ValueError("Can't load save_path when it is None.") ValueError: Can't load save_path when it is None.

CoderReece commented 6 years ago

Didn't realise it had a configuration. Stupid me.

ishandutta2007 commented 6 years ago

Yeah but in configuration what should be changed to what ? I have already created logdir/01

ishandutta2007 commented 6 years ago

you have to copy the following to logdir/01

checkpoint                     
graph.pbtxt                       
model_gs_200k.data-00000-of-00001  
model_gs_200k.index                
model_gs_200k.meta
rookiefront commented 4 years ago

您必须将以下内容复制到 logdir/01

checkpoint                     
graph.pbtxt                       
model_gs_200k.data-00000-of-00001  
model_gs_200k.index                
model_gs_200k.meta

model_gs_200k Where does the weight come from image He only generated these files for me，I don't know what i should do