search

pannous / tensorflow-speech-recognition

🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks
Other
2.16k stars 639 forks source link

Error When Run densenet_layer.py #21

Closed ragipunal closed 7 years ago

ragipunal commented 7 years ago

Hello Everybody, I have a problem. ./number_classifier_tflearn.py ./speaker_classifier_tflearn.py run and success but densenet_layer.py not working I follow this steps on docker.

docker run -it -v C:\WorkData\GitRespostory\tensorflow-speech-recognition:/tf_speech gcr.io/tensorflow/tensorflow:latest-devel

after on shell command screen show

cd /tensorflow git pull

then run this steps

apt-get update apt-get install -y libasound-dev portaudio19-dev libportaudio2 libportaudiocpp0 cd /tf_speech pip install -r requirements.txt pip install h5py pip install librosa

Note: spoken_words.tar file manuel download and copy to folder. and now python densenet_layer.py

but show this error, please help me.

Traceback (most recent call last): File "densenet_layer.py", line 69, in <module> net.train(data=batch,batch_size=10,steps=5000,dropout=0.6,display_step=10,test_step=100) # run File "/tf_speech/layer/net.py", line 385, in train loss,_= session.run([self.cost,self.optimizer], feed_dict=feed_dict) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 766, in run run_metadata_ptr) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 943, in _run % (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape()))) ValueError: Cannot feed value of shape (10, 262144) for Tensor u'data/Placeholder:0', which has shape '(?, 4096, 4096)'

pannous commented 7 years ago

Thanks for reporting! It is fixed now.