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

Need help, how to choose one column of a tensor #253

Closed
chenghuige opened this issue Nov 17, 2015 · 1 comment
Closed

Need help, how to choose one column of a tensor #253

chenghuige opened this issue Nov 17, 2015 · 1 comment

Comments

@chenghuige
Copy link

predict_op = tf.argmax(py_x, 1) # at predict time, evaluate the argmax of the logistic regression

here what to do if I want to choose one column of py_x, like py_x[1] ?

Also it would be of great help if we have example of showing how to do text classification using tensorflow( sparse feature).

Example of showing how to evaluate using auc instead of precision is greatly appreciated.

@vrv
Copy link

vrv commented Nov 17, 2015

I think tf.slice(...) might be what you want for getting 1 column. Let us know if that doesn't work!

You might also want to follow #206

As for text classification: I'm sure that will be added over time (either by us or externally).

@vrv vrv closed this as completed Nov 17, 2015
tensorflow-copybara pushed a commit that referenced this issue Dec 6, 2019
Signed-off-by: Uday Bondhugula <uday@polymagelabs.com>

Closes #253

COPYBARA_INTEGRATE_REVIEW=tensorflow/mlir#253 from bondhugula:dimop a4b464f24ae63fd259114558d87e11b8ee4dae86
PiperOrigin-RevId: 284169689
Change-Id: I4b0aaf508668ebd35e3abc12e0e2d661f996995d
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