| 972fa89023f8f27948321c388fa3f1f7857833c3 |
|
15-Feb-2018 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Add auc_with_confidence_intervals
This method computes the AUC and corresponding confidence intervals using an efficient algorithm.
PiperOrigin-RevId: 185884228
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 20765b3e1ae3b718699592c98aa9805cb874b6d1 |
|
29-Dec-2017 |
Patrick Nguyen <drpng@google.com> |
Merge changes from github.
PiperOrigin-RevId: 180301735
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| ee9b4eb5ee09bc505a51b1ba9325823444ac1dd2 |
|
18-Nov-2017 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Rename streaming_precision_recall_at_equal_thresholds to precision_recall_at_equal_thresholds.
Add the metric to the tf.contrib.metrics namespace.
Re-order its parameters to be more in line with that of other metrics.
PiperOrigin-RevId: 176178651
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| b9951e775e7a80b96520a1e8e0b5c4a485196796 |
|
09-Nov-2017 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Adds streaming_dynamic_auc to Tensorflow contrib metrics. This metric differs from streaming_auc because it uses every prediction as a threshold rather than linearly spaced fixed thresholds.
PiperOrigin-RevId: 175217002
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 70698a168669e0335872ce9248a6c496328d7871 |
|
02-Nov-2017 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Adding streaming_recall_at_precision to Tensorflow contrib metrics.
PiperOrigin-RevId: 174250716
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 7cb7f88c5ff12a5ce52e82d9f07e1b489df1e0ff |
|
28-Oct-2017 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Add count metric, a helper function that computes the total number or total weight of examples.
PiperOrigin-RevId: 173731046
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| a3667c483ebf839653d71cf42a0a71196a513dc9 |
|
14-Oct-2017 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Add streaming_false_{negative,positive}_rate and streaming_false_{negative,positive}_rate_at_thresholds.
PiperOrigin-RevId: 172191462
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 5acdad4209cc8ee1a5c9421cbe38b0f2538843eb |
|
13-Oct-2017 |
Anna R <annarev@google.com> |
Automated g4 rollback of changelist 172048554
PiperOrigin-RevId: 172065800
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 71568313f00efc0c3521f2e194ed66dc60b61f90 |
|
13-Oct-2017 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Add streaming_false_{negative,positive}_rate and streaming_false_{negative,positive}_rate_at_thresholds.
PiperOrigin-RevId: 172048554
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 8bf7cf3b010ecefceeab9ac9249dfddfe5adec65 |
|
29-Sep-2017 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Add sparse_recall_at_top_k in __init__.py
PiperOrigin-RevId: 170526899
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| cd6c02985e482d344adf1f2bdf5a4980e53f726e |
|
02-Jun-2017 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Add 'streaming_curve_points' metric which returns curve [ROC, PR] approximation at specified number of points.
PiperOrigin-RevId: 157851535
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 8334b2741522b7e32ab96cc7e077cf2293d57957 |
|
21-Feb-2017 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Add sparse_average_precition_at_top_k which takes top-k class indices instead of class logits.
Change: 148111829
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 55db877eef7265ec1a48aeaa3ca22d568aa81812 |
|
13-Feb-2017 |
Andrew Selle <aselle@google.com> |
Documentation changes to adhere to new doc generator
Change: 147382677
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| cb45a7d952ee126efe43ef1b2c08fb3503e2f6bd |
|
30-Jan-2017 |
Martin Wicke <wicke@google.com> |
Seal contrib interfaces (as much a feasible). If you were using a symbol which is now hidden, it should be added to the _allowed_symbols list in the appropriate __init__.py file.
Change: 145943844
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 0e5015bb7d58dc273e019a19875b55bf9c362950 |
|
03-Dec-2016 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Moves most metrics from contrib into core.
Change: 140914784
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 648bbfdf706fb29ae51c62a003137113e79cff26 |
|
23-Nov-2016 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Add binary classification confusion matrix metrics.
Change: 140046076
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 85eeec0d415a1478bbeffc3d4545c795bee64e9f |
|
19-Nov-2016 |
Jonathan Hseu <jhseu@google.com> |
Automated rollback of change 139400135
Change: 139632235
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 7e8728662120df0a80720bb7527613f96d58271e |
|
17-Nov-2016 |
Jonathan Hseu <jhseu@google.com> |
Rename `Tensor` to `Output` in all Python docs
Generated by running:
$ find . -name '*.py' | xargs sed -i 's/a `Tensor`/an `Output`/g'
$ find . -name '*.py' | xargs sed -i 's/A `Tensor`/An `Output`/g'
$ find . -name '*.py' | xargs sed -i 's/`Tensor`/`Output`/g'
$ find . -name '*.py' | xargs sed -i 's/`tf.Tensor`/`tf.Output`/g'
$ find . -name '*.py' | xargs sed -i 's/`Tensors`/`Output`s/g'
$ find . -name '*.py' | xargs sed -i 's/#Tensor)/#Output)/g'
$ find . -name '*.py' | xargs sed -i 's/#Tensor\./#Output./g'
Manually fixed up lines that exceeded 80 characters after the change.
Change: 139400135
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| a771598ad83ca33eb42594d7e804859371ba4ca9 |
|
09-Nov-2016 |
Benoit Steiner <bsteiner@google.com> |
Merge changes from github.
Change: 138675832
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| cbd3cacfb73bbea912b9d01c2540187684f751a7 |
|
03-Nov-2016 |
Illia Polosukhin <ipolosukhin@google.com> |
Replace usages initialize_all_variables -> global_variables_initializer
Change: 138128703
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| c944d1a96e1fbc48d689381cf93e91946087ee01 |
|
24-Oct-2016 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Remove deprecated ignore_mask field from streaming metrics.
Change: 137056449
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 33970acb0a94fbf3f3ef0f56733fd6d6a4af4a01 |
|
14-Oct-2016 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Add streaming_sparse_precision_at_top_k in metric_ops.
Change: 136189470
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| e7b2114e0732a11cf610b388f92a46fa8f9da3c4 |
|
27-Sep-2016 |
Stephan Hoyer <shoyer@google.com> |
Add tf.contrib.metrics.streaming_concat
This op is useful, on small datasets, for evaluating metrics that otherwise
cannot be updated incrementally.
Change: 134332647
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| ff40bc4d422f201b85c36721fb3d7ed1cf84c241 |
|
22-Sep-2016 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Add `streaming_sparse_average_precision_at_k`, aka "mean average precision".
The following were used as references:
en.wikipedia.org/wiki/Information_retrieval#Average_precision
fastml.com/what-you-wanted-to-know-about-mean-average-precision
Change: 133984427
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 4fb94d38b25c73d3bd8bd6a0ea632eb34c2787d6 |
|
16-Sep-2016 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Introduces new tf.contrib.metrics for streaming covariance and pearson product-moment correlation.
Change: 133388403
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| a274c662b3f090193ead4138791896ffb65d680e |
|
02-Sep-2016 |
Martin Wicke <wicke@google.com> |
Add a more principled way to connect metrics the the output of a model. Instead of increasingly opaque tuples, a MetricSpec object is introduced which contains all information needed to connect a metric function to multi-headed models.
Change: 132033966
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 4f353f0ef6e921da1e768b4013beea73f8f8860f |
|
27-Aug-2016 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Add support of weights in metrics in _get_eval_op of Estimator.
Change: 131464187
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 0f7c3b0a886300c332fa66df58b4d4a5d477a4d9 |
|
16-Aug-2016 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Update generated Python Op docs.
Change: 130356783
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 879270bb027075b8968d7a7a6893d87a3d21139e |
|
20-Jul-2016 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Added streaming_mean_tensor which keeps a streaming mean of the N-dimensional tensor (unlike streamin_mean which keeps a scalar).
Change: 127977144
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 93367103edc6f79fd779bc1ed873f9f9da1dec3f |
|
08-Jul-2016 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Moving aggregate metrics functions to tf.contrib.
Change: 126943819
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 4399d0ab0ada9b35d3167dee1e130559bc661c85 |
|
03-Jul-2016 |
A. Unique TensorFlower <gardener@tensorflow.org> |
Add streaming_mean_iou to metric_ops.
streaming_mean_iou computes the mean intersection-over-union, a typical
evaluation metric in the task of semantic image segmentation.
Factor out the utility function, remove_squeezable_dimensions, to
metric_ops_util.py, move its test and make changes for the other
dependencies as well.
Change: 126530424
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 122cdce33e3e0a01a7f82645617317530aa571fb |
|
02-Jun-2016 |
A. Unique TensorFlower <nobody@tensorflow.org> |
Update copyright for 3p/tf.
Change: 123901292
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 12c1176d6a434cc73c2b9cff904f67e3a80edf52 |
|
21-May-2016 |
A. Unique TensorFlower <nobody@tensorflow.org> |
Adds a metric for a streaming precision recall curve.
A few values (determined by given thresholds) are computed on the curve.
Change: 122881711
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 3a720e45238190a9c4e5fcc69c3777edc6aeefcb |
|
17-May-2016 |
A. Unique TensorFlower <nobody@tensorflow.org> |
Improve contrib gen_docs markup.
Change: 122482108
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 9ef6ee228110878418898d65063b2bd08489326a |
|
13-May-2016 |
A. Unique TensorFlower <nobody@tensorflow.org> |
Registering tf.contrib.metrics with documentation
Change: 122223545
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 1b5e110a67b1f70c3491874d842b62a04b244cf5 |
|
10-May-2016 |
A. Unique TensorFlower <nobody@tensorflow.org> |
Add multiclass multilabel precision and recall metric operations.
Change: 121975222
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| fd25fa1854690ba4f7432057ebdb318d88d9231e |
|
09-May-2016 |
A. Unique TensorFlower <nobody@tensorflow.org> |
Add multiclass multilabel precision and recall metric operations.
Change: 121871361
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 3f84717445b6da22c82155ed6a43214b21bedc9f |
|
09-May-2016 |
A. Unique TensorFlower <nobody@tensorflow.org> |
Add multiclass multilabel precision and recall metric operations.
Change: 121863903
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 8bf6ef1337359993a8be057c0dc90da8f5a6e4fa |
|
05-May-2016 |
A. Unique TensorFlower <nobody@tensorflow.org> |
Merge changes from github.
Change: 121586635
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| e8304043aaff8d676ff4a69ef6e10cd2833746ed |
|
27-Apr-2016 |
A. Unique TensorFlower <nobody@tensorflow.org> |
Adding a series of streaming metrics to contrib including: streaming_accuracy, streaming_auc, streaming_mean, streaming_mean_absolute_error, streaming_mean_cosine_distance, streaming_mean_relative_error, streaming_mean_squared_error, streaming_percentage_less,streaming_precision, streaming_recall, streaming_recall_at_k, streaming_root_mean_squared_error.
Change: 120882499
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| 8875de24429ffa666c1a219ccd71713d307b102e |
|
19-Apr-2016 |
Illia Polosukhin <ilblackdragon@gmail.com> |
Added classification metrics file and accuracy op.
Change: 120250915
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|
| c5073debf15bc794504cbcb18a939e7b8a67ef8a |
|
08-Apr-2016 |
A. Unique TensorFlower <nobody@tensorflow.org> |
Initial API in contrib/metrics/ and adding one Op (auc_using_histogram).
Add AUC Op based on internal histograms: auc_using_histogram().
* Works fine with large class imbalance (no special handling when entire batch is one class)
* Runs in O(batch_size + histogram_width) time, so works for huge batches
Change: 119324088
/external/tensorflow/tensorflow/contrib/metrics/__init__.py
|