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 to let the Net Forward without a leveldb #37

Closed
lifeiteng opened this issue Jan 18, 2014 · 3 comments
Closed

How to let the Net Forward without a leveldb #37

lifeiteng opened this issue Jan 18, 2014 · 3 comments
Labels

Comments

@lifeiteng
Copy link

if I don't use a leveldb, how can I make Forward using the trained Net?
I used this functions (copy data to bottom)
const vector<Blob>& Forward(const vector<Blob > & bottom);

But, doesn't work.

Anyone help me? Thank you.

@sguada
Copy link
Contributor

sguada commented Jan 19, 2014

You can take a look into the Python or Matlab wrapper, they don't use leveldb but pass the data.

@lifeiteng
Copy link
Author

In order to get the probability of softmax layer,
I have changed the (Net.top_vecs())[0][0] = blop_input_ptr, and use the result[1] as the probability blob.
but the values in the probability blob (result[1]) are all the same for different single blop_input_ptr.

I'm confused!

@lifeiteng
Copy link
Author

I have solved it.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

2 participants