Seq2seq #989
Merged
Seq2seq #989
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 7 commits
May 25, 2019 09:49
JingqingZ
reviewed
May 31, 2019
tensorlayer/models/seq2seq.py
Outdated
| decoder_seq_length: int | ||
| The length of your target sequence | ||
| cell_enc : str, tf.function | ||
| The RNN function cell for your encoder stack, i.e. tf.keras.layers.GRUCell |
There was a problem hiding this comment.
'i.e.' means 'in other words'. Please use 'e.g.' (means 'for example') here and other places accordingly.
JingqingZ
reviewed
May 31, 2019
tensorlayer/models/seq2seq.py
Outdated
| n_layer : int | ||
| The number of your RNN layers for both encoder and decoder block | ||
| embbedding_layer : tl.function | ||
| The embedding layer function, i.e. tl.layers.Embedding(vocabulary_size=voc_size, embedding_size=emb_dim) |
There was a problem hiding this comment.
Typo here and please change this comment to:
embedding_layer : tl.Layer
A embedding layer, e.g. tl.layers.Embedding(vocabulary_size=voc_size, embedding_size=emb_dim)
JingqingZ
reviewed
May 31, 2019
tensorlayer/models/seq2seq.py
Outdated
| The number of your RNN layers for both encoder and decoder block | ||
| embbedding_layer : tl.function | ||
| The embedding layer function, i.e. tl.layers.Embedding(vocabulary_size=voc_size, embedding_size=emb_dim) | ||
| is_train : bool |
There was a problem hiding this comment.
is_train is never used in init and it is not going to be supported when a model is constructed in future versions. Please remove it.
JingqingZ
reviewed
May 31, 2019
tensorlayer/models/seq2seq.py
Outdated
| n_layer=3, | ||
| embedding_layer=None, | ||
| is_train=True, | ||
| name="seq2seq_" |
There was a problem hiding this comment.
name=None by default. There is an auto-naming mechanism in tl.models.Model().
JingqingZ
reviewed
May 31, 2019
tensorlayer/models/seq2seq.py
Outdated
| self.reshape_layer_individual_sequence = tl.layers.Reshape([-1, 1, self.vocabulary_size]) | ||
|
|
||
| def inference(self, encoding, seq_length, start_token, top_n): | ||
|
|
There was a problem hiding this comment.
Some documentation is needed here.
There was a problem hiding this comment.
Did you use beam search? Or just random sampling?
JingqingZ
requested changes
May 31, 2019
JingqingZ
approved these changes
May 31, 2019
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
ADD Stacked Layer Seq2Seq