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

Error executing train.py #2

Closed arunbaby0 closed 7 years ago

arunbaby0 commented 7 years ago

I am getting an error when I execute train.py

Traceback (most recent call last): File "train.py", line 277, in <module> main() File "train.py", line 255, in main g = Graph(is_training=True); print("Training Graph loaded") File "train.py", line 234, in __init__ self.memory = encode(self.x, is_training=is_training) File "/SpeakerID-IIT/tts/voices/taco/tacotron-master/networks.py", line 47, in encode memory = gru(enc, hp.embed_size//2, True) # (N, T, 128*2) File "/SpeakerID-IIT/tts/voices/taco/tacotron-master/modules.py", line 103, in gru outputs, _ = tf.nn.bidirectional_dynamic_rnn(cell, cell_bw, inputs, dtype=tf.float32) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn.py", line 363, in bidirectional_dynamic_rnn seq_dim=time_dim, batch_dim=batch_dim) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/array_ops.py", line 2346, in reverse_sequence name=name) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 2776, in reverse_sequence batch_dim=batch_dim, name=name) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 504, in apply_op values, as_ref=input_arg.is_ref).dtype.name File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 716, in internal_convert_to_tensor ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/constant_op.py", line 176, in _constant_tensor_conversion_function return constant(v, dtype=dtype, name=name) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/constant_op.py", line 165, in constant tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape, verify_shape=verify_shape)) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/tensor_util.py", line 360, in make_tensor_proto raise ValueError("None values not supported.") ValueError: None values not supported.

marcossilva commented 7 years ago

It's working here for me. Which tensorflow version do you have installed?

basuam commented 7 years ago

@arunbaby0 : It is working for me too. I'm not an expert but I agree with @marcossilva , check that you really comply with the "Requirements".

arunbaby0 commented 7 years ago

I am using tensorflow version 1.0. And I installed all the requirments.

Durham commented 7 years ago

This may be related issue https://stackoverflow.com/questions/39808336/tensorflow-bidirectional-dynamic-rnn-none-values-error

I installed latest tensorflow 1.1 specifically for trying this code, before upgrading I had various issues (although not this one). I think you should try upgrading to tensorflow 1.1. and see if it helps.

basuam commented 7 years ago

@arunbaby0 Did you solve your problem? If so, can you close this issue? Thank you for your help.

arunbaby0 commented 7 years ago

@Durham Thanks a lot. It started working after I upgraded to 1.1.0. I think it's better to update the requirements to TF 1.1 in the requirements section.