search

CGATOxford / DanQ_tensorflow

tensorflow adaptation of DanQ
2 stars 0 forks source link

Flatten LSTM #1

Open purvanshi opened 6 years ago

purvanshi commented 6 years ago

In tf_danq.ipynb
brnn = tf.contrib.layers.flatten(brnn)

The output from BDNN returns a tuple with the forward and backward outputs. Directly flattening causes an issues when inputting to the dense layer.

ValueError: The last dimension of the inputs to Dense should be defined. Found None.

logust79 commented 6 years ago

Hi @purvanshi , the notebook is broken for the time being, and we are working to fix it. Thanks!

Licko0909 commented 5 years ago

嗨@purvanshi，笔记本暂时坏了，我们正在努力修复它。 谢谢！

Thank you for your work, I am very interested in this, I hope to be able to run the notebook, is this jupyter notebook fixed? Can I use it?