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.

Sign up for GitHub

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

Jump to bottom

Attempt to make sense of reasoning for loss #20220

Merged
merged 3 commits into from
Jun 22, 2018
Merged

Attempt to make sense of reasoning for loss #20220

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
53a1c8d
Attempt to make sense of reasoning for loss
Naman-Bhalla Jun 22, 2018
5c2f1e6
Add suggested fix.
MarkDaoust Jun 22, 2018
7dd4d00
fix backquotes
MarkDaoust Jun 22, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
2 changes: 1 addition & 1 deletion tensorflow/docs_src/programmers_guide/custom_estimators.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -362,7 +362,7 @@ model's loss. This is the
that will be optimized.

We can calculate the loss by calling @{tf.losses.sparse_softmax_cross_entropy}.
The value returned by this function will be lowest, approximately 0,
When the value returned by this function will be lowest, approximately 0,
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

How about this:

The value returned by this function will be approximately 0 at lowest, when the probability of the correct class (at index label') is near 1.0.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

That sounds better. Thanks.
Should I update the PR with it ?

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I just patched it.

probability of the correct class (at index `label`) is near 1.0. The loss value
returned is progressively larger as the probability of the correct class
decreases.
Expand Down