diff options
author | TensorFlower Gardener <gardener@tensorflow.org> | 2018-08-23 11:57:50 -0700 |
---|---|---|
committer | TensorFlower Gardener <gardener@tensorflow.org> | 2018-08-23 11:57:50 -0700 |
commit | 15113cd567f630cd8806deeb82e608357ebed8c3 (patch) | |
tree | 13239c08934c5cf0eaf11daf0c67b9ec31ef56a2 /tensorflow | |
parent | d232dee9f9efab16608e0f08ab82c1f51aff78a0 (diff) | |
parent | 0c5683c50b2f4afc124ac7c4b61e316b4130b97d (diff) |
Merge pull request #21753 from ageron:add_average_loss_and_loss_doc
PiperOrigin-RevId: 209974388
Diffstat (limited to 'tensorflow')
-rw-r--r-- | tensorflow/docs_src/guide/premade_estimators.md | 2 | ||||
-rw-r--r-- | tensorflow/python/estimator/estimator.py | 6 |
2 files changed, 7 insertions, 1 deletions
diff --git a/tensorflow/docs_src/guide/premade_estimators.md b/tensorflow/docs_src/guide/premade_estimators.md index a1703058c3..9b64d51b98 100644 --- a/tensorflow/docs_src/guide/premade_estimators.md +++ b/tensorflow/docs_src/guide/premade_estimators.md @@ -366,6 +366,8 @@ Running this code yields the following output (or something similar): Test set accuracy: 0.967 ``` +The `eval_result` dictionary also contains the `average_loss` (mean loss per sample), the `loss` (mean loss per mini-batch) and the value of the estimator's `global_step` (the number of training iterations it underwent). + ### Making predictions (inferring) from the trained model We now have a trained model that produces good evaluation results. diff --git a/tensorflow/python/estimator/estimator.py b/tensorflow/python/estimator/estimator.py index f7ee42c7f6..bcbd7b7933 100644 --- a/tensorflow/python/estimator/estimator.py +++ b/tensorflow/python/estimator/estimator.py @@ -431,7 +431,11 @@ class Estimator(object): Returns: A dict containing the evaluation metrics specified in `model_fn` keyed by name, as well as an entry `global_step` which contains the value of the - global step for which this evaluation was performed. + global step for which this evaluation was performed. For canned + estimators, the dict contains the `loss` (mean loss per mini-batch) and + the `average_loss` (mean loss per sample). Canned classifiers also return + the `accuracy`. Canned regressors also return the `label/mean` and the + `prediction/mean`. Raises: ValueError: If `steps <= 0`. |