Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Ask about the implementation #1

Closed
terryqj0107 opened this issue Aug 7, 2018 · 5 comments
Closed

Ask about the implementation #1

terryqj0107 opened this issue Aug 7, 2018 · 5 comments

Comments

@terryqj0107
Copy link

Excuse me . What framework is used to implement the neural network in this system? Is it the LSTM encapsulated by matlab? Is there a duplicate version of tensorflow?

@xjli
Copy link
Collaborator

xjli commented Aug 7, 2018

No using any framework for the LSTM and neural networks models in this system. All the neural models are with pure Python. But you are free to use any framework, like tensorflow, pytorch etc.

@terryqj0107
Copy link
Author

Can this system use GPU to train the neural models?If so,how to implement?

@xjli
Copy link
Collaborator

xjli commented Aug 7, 2018

Yes, you can. You can write an agent (.py) file which is derived from agent.py, this agent can be implemented with pytorch, tensorflow etc., and add this agent into the run.py file, say agt=20, then use your own agent to run. See some agent examples from agt=1,2,3,...,13

@xjli
Copy link
Collaborator

xjli commented Aug 7, 2018

@terryqj0107 , you can see one example here in DDQ, https://github.com/MiuLab/DDQ/blob/master/src/deep_dialog/agents/agent_dqn.py, this agent_dqn.py is implemented with pytorch under the framework.

@terryqj0107
Copy link
Author

ok,thank you very much

@xjli xjli closed this as completed Aug 7, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants