toni-antonova / vae-text-generation Goto Github PK
View Code? Open in Web Editor NEWText Generation Using A Variational Autoencoder
vae-text-generation's People
Contributors
Stargazers
Watchers
Forkers
jaykimbravekjh kinect59 haoyang11 cpuyyp aitazzi raymonddixon dangxuanhong akhileshydv inferno-p linuxperia nikhilpinnaparaju wpmarinho truely802 wentropy ravi-annaswamy lancenorskog iszhuangsha arunkumarramanan isabellahu thzll2001 gitterer shreyassd4 tommyiaq szymczakpau thomkirwanevans khs6848 suchismitha-vedala mrflygerian hyunchul78 franklinrogelio usamamalick saranyab21 amanrose22vae-text-generation's Issues
Training failing(shape mismatch error) at calculating validation loss.
Hi Toni
Thank you for sharing this, I am trying to reuse this repository to encode my sentences. On training the model the test set runs well but as soon as it gets to calculating the validation loss the process fails with a shape mismatch error. It complains generally in this direction -
ValueError: Cannot feed value of shape (75, 3000) for Tensor u'input_15:0', which has shape '(500, 3000)'
Where 3000 - is my max sentence len and 500 - is the batch size. However this number 75 is somehow generated dynamically and is different for different max-len and batch size values. Could you maybe give me a direction what might be going wrong here.
Thanks.
Using transformer
How can we build VAE or Auto-encoder using Transformer or pre-trained Transformer?
wikitokens.pickle
Thank you for the complete code, But would you please tell more about wikitokens.pickle and how to get it?
train function is not working
InvalidArgumentError Traceback (most recent call last)
in ()
epochs=epochs,
batch_size=batch_size,
validation_data=None)
where does this 'sent_encoded' comes from?
# input: encoded sentence vector
# output: encoded sentence vector in dataset with highest cosine similarity
def find_similar_encoding(sent_vect):
all_cosine = []
for sent in sent_encoded:
result = 1 - spatial.distance.cosine(sent_vect, sent)
all_cosine.append(result)
data_array = np.array(all_cosine)
maximum = data_array.argsort()[-3:][::-1][1]
new_vec = sent_encoded[maximum]
return new_vec
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.