ljuvela / gelp Goto Github PK

Hello, thank you for your project!
However, I encountered an error during runtime, when I run:
python generate_copysyn.py --model_dir sessions/pretrained --input_wav_dir demo_data/wav --suppress_warnings

error as follows:

WARNING:tensorflow:From /home/sywang/GELP-master/model_causal.py:25: calling Constant.init (from tensorflow.python.
ops.init_ops) with dtype is deprecated and will be removed in a future version.Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
WARNING:tensorflow:
The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:

• https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
• https://github.com/tensorflow/addons
• https://github.com/tensorflow/io (for I/O related ops)
  If you depend on functionality not listed there, please file an issue.

Traceback (most recent call last):
File "generate_copysyn.py", line 218, in
copy_synthesis(args)
File "generate_copysyn.py", line 176, in copy_synthesis
x_fake_flat = ar_synthesis_filter(exc_fake_flat, a, frame_length, frame_step, nfft)
File "/home/sywang/GELP-master/sigproc.py", line 166, in ar_synthesis_filter
A = tf.signal.rfft(a_pad)
File "/home/sywang/anaconda2/envs/gelp-gpu/lib/python3.7/site-packages/tensorflow_core/python/ops/signal/fft_ops.py",
line 124, in _rfft input_tensor = _maybe_pad_for_rfft(input_tensor, fft_rank, fft_length)
File "/home/sywang/anaconda2/envs/gelp-gpu/lib/python3.7/site-packages/tensorflow_core/python/ops/signal/fft_ops.py",
line 99, in _maybe_pad_for_rfft outer_paddings = _array_ops.zeros([outer_dims], fft_length.dtype)
File "/home/sywang/anaconda2/envs/gelp-gpu/lib/python3.7/site-packages/tensorflow_core/python/ops/array_ops.py", line
2338, in zeros output = _constant_if_small(zero, shape, dtype, name)
File "/home/sywang/anaconda2/envs/gelp-gpu/lib/python3.7/site-packages/tensorflow_core/python/ops/array_ops.py", line
2295, in _constant_if_small if np.prod(shape) < 1000:
File "<array_function internals>", line 6, in prod
File "/home/sywang/anaconda2/envs/gelp-gpu/lib/python3.7/site-packages/numpy/core/fromnumeric.py", line 3031, in prod
keepdims=keepdims, initial=initial, where=where)
File "/home/sywang/anaconda2/envs/gelp-gpu/lib/python3.7/site-packages/numpy/core/fromnumeric.py", line 87, in _wrapr
eduction return ufunc.reduce(obj, axis, dtype, out, **passkwargs)
File "/home/sywang/anaconda2/envs/gelp-gpu/lib/python3.7/site-packages/tensorflow_core/python/framework/ops.py", line
736, in array " array.".format(self.name))
NotImplementedError: Cannot convert a symbolic Tensor (rfft/Maximum:0) to a numpy array.

How can I solve this? Thank you very much!