Exception when calling bidirectional_dynamic_rnn, ValueError: None values not supported.
Shirley-Ji opened this issue · comments
Hi guys,
I put this package onto the Google Cloud to get deployed with GPU environment configured, then changed the text length in Hyperparams to be [20-3000], then schedule it to run only with Genesis wav files, I got the following error "ValueError: None values not supported." after a while. Any body hit this and any suggestions?
max_len = 100 if not sanity_check else 3000 # maximum length of text
min_len = 10 if not sanity_check else 20 # minimum length of text
the call stack is the following:
File "/root/.local/lib/python2.7/site-packages/tacotron/train.py", line 109, in main
g = Graph(); print("Training Graph loaded")
File "/root/.local/lib/python2.7/site-packages/tacotron/train.py", line 45, in init
self.memory = encode(self.x, is_training=is_training) # (N, T, E)
File "/root/.local/lib/python2.7/site-packages/tacotron/networks.py", line 62, in encode
memory = gru(enc, hp.embed_size//2, True) # (N, T, E)
File "/root/.local/lib/python2.7/site-packages/tacotron/modules.py", line 219, in gru
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 2328, 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 702, 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 110, 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 99, 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.