TensorFlow-Pointer-Networks

TensorFlow-Pointer-Networks copied to clipboard

if i run with tf 1.0.0, exception arise as `tf.nn.ops have no attribution of rnn` i run the notebook with tf 0.12 got issue below: `--------------------------------------------------------------------------- TypeError Traceback (most recent...

fooSynaptic

# Merge input and previous attentions into one vector of the right size. x = core_rnn_cell_impl._linear([inp, attns], cell.output_size, True) which attns = array_ops.zeros(batch_attn_size, dtype=dtype) why use zeros attns ？

fword

Can I feed the shift of decoder outputs? Or just zeros? Thank you @ikostrikov @j-min @GalDude33 @chenghuige

guotong1988

Input a `decoder_inputs` list of two elements. Is it right? Thank you @ikostrikov @j-min @GalDude33 @chenghuige

guotong1988

which version of tensorflow can run you code ? I can't run your code because of the version of tensorflow

SHUht

Why compute prediction over decoder_inputs instead of encoder_inputs?

1

Hi, Thanks for sharing the code. I have a doubt in _pointer.py_. In the below code fragment: ```python if feed_prev and i > 0: inp = tf.pack(decoder_inputs) inp = tf.transpose(inp,...

QK-Rahul

derylucio