Comments (2)
Hi @vikram-gupta,
The way we currently use the decoder (simply using the forward method) is zeroing the state vector every time it is called.
This behaviour is defined by the Sequencer module which calls the forget method of the children AbstractRecurrent modules. [1]
It is however possible to use the Sequencer:remember() method to make it save the state and maybe save some computations.
Chen
[1] https://github.com/Element-Research/rnn#sequencer
from neuralconvo.
Thanks @chenb67
from neuralconvo.
Related Issues (20)
- attempt to call method 'topk' (a nil value)
- why need opencl if I user 'th train.lua --cuda --gpu 0'
- Error on saivng model with neuralconvo and distro-cl
- Error on this branch: https://github.com/rustch3n/chatbot-zh-torch7 HOT 1
- how can you ensure that the output is a smooth sentence? HOT 1
- PANIC: unprotected error in call to Lua API (not enough memory)----but 'top' show the memory are still avaialbe
- Perplexity calculation
- The lines are shortened to the first sentence HOT 2
- online learning for the model HOT 1
- The memory usage skyrocket each time it saves HOT 3
- [Discuss:] how to improve the performance? HOT 1
- vocab.t7 not found HOT 2
- Crash on 2nd epoch: invalid arguments: DoubleTensor number FloatTensor - adam.lua HOT 1
- Anyone please share their model ? HOT 4
- Initialising pre-trained model
- Train with error HOT 2
- training_fail_/seq2seq.lua:62: attempt to call field 'recursiveCopy' HOT 10
- When I'm trying to train the model.. I'm facing with this error
- "Wrong size for view" error while evalution HOT 1
- [Question] How do you focus the training on only one person
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 neuralconvo.