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

train_multi_gpus.py error #53

Closed zuoxiang95 closed 7 years ago

zuoxiang95 commented 7 years ago

when i run train_multi_gpus.py, i get this error: Traceback (most recent call last): File "train_multi_gpus.py", line 137, in main() File "train_multi_gpus.py", line 117, in main g = Graph(); print("Training Graph loaded") File "train_multi_gpus.py", line 58, in init is_training=is_training) # (N, T', hp.n_mels*hp.r) File "/data1/zuoxiang/tacotron/networks.py", line 85, in decode1 dec = attention_decoder(dec, memory, num_units=hp.embed_size) # (N, T', E) File "/data1/zuoxiang/tacotron/modules.py", line 247, in attention_decoder probability_fn=tf.nn.softmax) TypeError: init() got an unexpected keyword argument 'probability_fn'

zuoxiang95 commented 7 years ago

i have changed num_gpus = 4 in heperparams.py

zuoxiang95 commented 7 years ago

because my tensorflow's version is not 1.2.0 . after i update the tensorflow's version to 1.2.0, it can work very well.