A slim tensorflow wrapper that provides syntactic sugar for tensor variables. This library will be helpful for practical deep learning researchers not beginners.
I am experimenting on speech-to-text-wavenet.
I tried to add a LSTM layer after conv1d layer, for example:
skip.sg_conv1d(size=1, act='tanh', bn=True, name='conv_1').sg_lstm(last_only=True, name='rnn_1').sg_dense(dim=emotion_size)
The output shape of sg_conv1d is (16, ?, 128)
When running, I got the following error:
sg_layer.py", line 499, in sg_rnnfor i in range(tensor.get_shape().as_list()[1]):TypeError: range() integer end argument expected, got NoneType.
I am experimenting on speech-to-text-wavenet. I tried to add a LSTM layer after conv1d layer, for example:
skip
.sg_conv1d(size=1, act='tanh', bn=True, name='conv_1')
.sg_lstm(last_only=True, name='rnn_1')
.sg_dense(dim=emotion_size)
The output shape of sg_conv1d is (16, ?, 128)When running, I got the following error:
sg_layer.py", line 499, in sg_rnn
for i in range(tensor.get_shape().as_list()[1]):
TypeError: range() integer end argument expected, got NoneType.
Is there have any advice? thanks