diff options
Diffstat (limited to 'tensorflow/contrib/losses')
-rw-r--r-- | tensorflow/contrib/losses/README.md | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/tensorflow/contrib/losses/README.md b/tensorflow/contrib/losses/README.md index f373c94c1b..7b73c4483a 100644 --- a/tensorflow/contrib/losses/README.md +++ b/tensorflow/contrib/losses/README.md @@ -12,10 +12,10 @@ All loss functions take a pair of tensors, `predictions` and ground truth `[batch_size, d1, ... dN]` where `batch_size` is the number of samples in the batch and `d1` ... `dN` are the remaining dimensions. -THe `weight` parameter can be used to adjust the relative weight samples within +The `weight` parameter can be used to adjust the relative weight samples within the batch. The result of each loss is a scalar average of all sample losses with non-zero weights. Any parameter named `logit` should be the raw model outputs, not a normalized -probablility distribution (i.e., `[0.0, 1.0]`). `target` for losses taking +probability distribution (i.e., `[0.0, 1.0]`). `target` for losses taking `logit` _should_ be a normalized probability distribution. |