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

How is the obama-0075.params file generated #14

Open
olivercox opened this issue Nov 29, 2016 · 1 comment
Open

How is the obama-0075.params file generated #14

olivercox opened this issue Nov 29, 2016 · 1 comment

Comments

@olivercox
Copy link

olivercox commented Nov 29, 2016

I've had a look at the char_lstm tutorial and notice a file named obama-0075.params that is included in the zip file download.

Could you explain how this file is generated or point me in the right direction?

@olivercox
Copy link
Author

olivercox commented Nov 30, 2016

Think I may have answered my own question, assuming I'm right in thinking that changing the num_epoch variable controls this.

# We will show a quick demo with only 1 epoch. In practice, we can set it to be 100
num_epoch = 75
# learning rate 
learning_rate = 0.01
...
model = mx.model.FeedForward(
    ctx=mx.cpu(0),
    symbol=symbol,
    num_epoch=num_epoch,
    learning_rate=learning_rate,
    momentum=0,
    wd=0.0001,
    initializer=mx.init.Xavier(factor_type="in", magnitude=2.34))

Could anyone explain the use of epoch in the FeedForward method?

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

1 participant