search

chiphuyen / stanford-tensorflow-tutorials

This repository contains code examples for the Stanford's course: TensorFlow for Deep Learning Research.
http://cs20.stanford.edu
MIT License
10.33k stars 4.32k forks source link

AttributeError: module 'tensorflow.python.ops.nn' has no attribute 'seq2seq' #64

Open yinseng2001 opened 7 years ago

yinseng2001 commented 7 years ago

self.outputs, self.losses = tf.nn.seq2seq.model_with_buckets( self.encoder_inputs, self.decoder_inputs, self.targets, self.decoder_masks, config.BUCKETS, lambda x, y: _seq2seq_f(x, y, False), softmax_loss_function=self.softmax_loss_function)

what function we can replace with tf.nn.seq2seq.model_with_buckets? thanks

yinseng2001 commented 7 years ago

try this tf.contrib.legacy_seq2seq.model_with_buckets

PoojaPatel05 commented 6 years ago

but then it is shoeing TypeError: model_with_buckets() got an unexpected keyword argument 'num_encoder_symbols' this error

ghost commented 6 years ago

Try this for TypeErrors: https://github.com/tensorflow/models/issues/1736