Comments (2)
Yes you can use. You can create your own vocabulary, and then extract their own word2vec representation using any trained embedding, like Google News via Gensim.
Then, at training/testing time, you should set the trainable parameter to false for the word embedding. Then, you should load the pre-trained embedding to initialize the embedding lookup table that is created:
session.run(word2vec.assign(my_own_word2vec_matrix))
But bear in mind that it will not result in a better performance. These embeddings are trained with different objectives in mind..
from show-attend-and-tell.
from show-attend-and-tell.
Related Issues (20)
- memory error when i train model. HOT 1
- AttributeError: 'Meteor' object has no attribute 'lock' HOT 1
- Unable to change the max_length of captions to train for another dataset HOT 1
- how to reproduce the scores in paper? HOT 12
- Does word embedding use pre-trained word embedding or not?
- Got error when test model with evaluate_model.ipynb. HOT 1
- What's the best performance of this code?
- Didn't use Karpathy's split HOT 1
- Any One Implemented Beam Search with this code
- Problem with testing HOT 3
- when resizing images to (224,224), why cropping?
- problem in prepro.py HOT 5
- What's the best performance of this code? HOT 4
- problems with prepro.py
- A lack of parts of implement of the papar
- problem with slover.py
- InvalidArgumentError: 2 root error(s) found.
- alphas
- IOError in train.py
- no "./data/val/val.features.hkl" file available.
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 show-attend-and-tell.