Comments (4)
I get this indentation error:-
from chatbot-startkit.
Yes Ive got the same error. I guess there is some problem with this implementation. So I had to reimplement it all on my own.
from chatbot-startkit.
This error is generated due to unwanted starting space in some comments. Reduce the starting space of all comments to 4 spaces. Your problem will get solved.
`
def encoder(inputs, rnn_size, number_of_layers, encoder_seq_len, keep_probs, encoder_embed_size, encoder_vocab_size):
'''
Used to define encoder of the seq2seq model (The encoder is made of simple dynamic RNN network).
Inputs:
inputs -
rnn_siz - number of units in the RNN layer
number_of_layer - number of RNN layers that the model uses
encoder_seq_len - vector of lengths (got from placeholder)
keep_probs - dropout rate
encoder_embed_size - size of embedding vector for encoder part
encoder_vocab_size - number of different words that the model uses in a vocabulary
Outputs:
encoder_outputs -
encoder_states - internal states from the RNN layer(s)
'''
def cell(units, rate):
layer = tf.contrib.rnn.BasicLSTMCell(units)
return tf.contrib.rnn.DropoutWrapper(layer,rate)
encoder_cell = tf.contrib.rnn.MultiRNNCell([cell(rnn_size, keep_probs) for _ in range(number_of_layers)])
encoder_embedings = tf.contrib.layers.embed_sequence(inputs, encoder_vocab_size, encoder_embed_size) #used to create embeding layer for the encoder
encoder_outputs, encoder_states = tf.nn.dynamic_rnn(encoder_cell,encoder_embedings, encoder_seq_len,dtype=tf.float32)
return encoder_outputs, encoder_states
`
This function has 4 space in the starting of the comment. make other function comments also like this function
from chatbot-startkit.
@lucko515 you can close this now. It has been solved now.
from chatbot-startkit.
Related Issues (6)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from chatbot-startkit.