aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/python/keras
Commit message (Collapse)AuthorAge
* Fix support for a single tensor to be passed to target_tensorsGravatar Sourabh Bajaj2018-10-08
| | | | PiperOrigin-RevId: 216212953
* Part 1/3 of the feature sync to the Keras 2.2.4 API.Gravatar Francois Chollet2018-10-08
| | | | PiperOrigin-RevId: 216211279
* Merge pull request #22659 from gautam1858:patch-17Gravatar TensorFlower Gardener2018-10-05
|\ | | | | | | PiperOrigin-RevId: 216009475
* | Brings V2 Optimizers into Keras w/ Keras signaturesGravatar A. Unique TensorFlower2018-10-05
| | | | | | | | PiperOrigin-RevId: 215950207
* | Enable masking through a Sequential model.Gravatar Francois Chollet2018-10-04
| | | | | | | | PiperOrigin-RevId: 215790636
* | Makes sure Keras Layer's `__call__` is always used in Eager.Gravatar A. Unique TensorFlower2018-10-04
| | | | | | | | | | | | | | | | | | Currently if a Layer is invoked with the Functional API in Eager, `__call__` is only used during setup, and thereafter `call` is used internally. This limits the ability to add pre/post processing steps to `call` in Eager in the future. Additionally, the Subclassed Model API already always uses `__call__` in Eager. PiperOrigin-RevId: 215778408
* | Merge pull request #22660 from gautam1858:patch-18Gravatar TensorFlower Gardener2018-10-04
|\ \ | | | | | | | | | PiperOrigin-RevId: 215761730
* \ \ Merge pull request #22392 from yanboliang:metricsGravatar TensorFlower Gardener2018-10-04
|\ \ \ | | | | | | | | | | | | PiperOrigin-RevId: 215760505
* | | | assert_nontrivial_match in tf.keras.Model.load_weights (TF format)Gravatar Allen Lavoie2018-10-03
| | | | | | | | | | | | | | | | | | | | | | | | Adds a bit of sanity checking by default to load_weights (e.g. for the case when absolutely nothing matches) while still supporting restore-on-create and the addition of new Layers to checkpointed models. PiperOrigin-RevId: 215652168
* | | | Merge pull request #22591 from EFanZh:fix-docsGravatar TensorFlower Gardener2018-10-03
|\ \ \ \ | | | | | | | | | | | | | | | PiperOrigin-RevId: 215639962
* | | | | Add a require_static_shapes argument to DistributionStrategy class. This ↵Gravatar Anjali Sridhar2018-10-03
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | allows us to identify if we need to set the drop_remainder option when creating Dataset objects. PiperOrigin-RevId: 215633097
* | | | | Fixes bug in Conv2D unit test that made it test a SeparableConv2D layer ↵Gravatar A. Unique TensorFlower2018-10-03
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | instead of a Conv2D layer. PiperOrigin-RevId: 215619966
* | | | | Improve error messages and doc strings for eager-mode tf.keras.Model.fit() + ↵Gravatar Shanqing Cai2018-10-02
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | tf.data objects - Previously, when validation_steps was missing, the error message incorrectly says "please provide either batch_size or steps_per_epoch". Now it reads "please provide either batch_size or validation_steps". - Some whitespace-related fixes. PiperOrigin-RevId: 215503991
* | | | | Update Keras RNN layer to support time major input.Gravatar Scott Zhu2018-10-02
| | | | | | | | | | | | | | | | | | | | PiperOrigin-RevId: 215479788
* | | | | Add support for multiple input/output numpy arrays when using Keras APIs.Gravatar Anjali Sridhar2018-10-02
| | | | | | | | | | | | | | | | | | | | PiperOrigin-RevId: 215459075
* | | | | Merge pull request #22126 from ConcurrencyPractitioner:masterGravatar TensorFlower Gardener2018-10-02
|\ \ \ \ \ | | | | | | | | | | | | | | | | | | PiperOrigin-RevId: 215431884
| | | | * | Update backend.pyGravatar Gautam2018-10-02
| |_|_|/ / |/| | | | | | | | | adding missing import numpy
| | | | * Update backend.py Gravatar Gautam2018-10-02
| |_|_|/ |/| | | | | | | Adding missing import files in the commented examples. When trying out that particular example in commented section the TensorFlow and bumpy imports are missing
* | | | Remove outdated integration test in preparation for update of ↵Gravatar Francois Chollet2018-10-01
| | | | | | | | | | | | | | | | | | | | | | | | keras_preprocessing. PiperOrigin-RevId: 215231309
* | | | Simplify batch_dot logicGravatar Shanqing Cai2018-09-28
| | | | | | | | | | | | | | | | | | | | | | | | Remove dead logical branch. PiperOrigin-RevId: 214980627
* | | | Simplify eager/graph Layer.losses conditionalsGravatar Allen Lavoie2018-09-28
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Fixes an issue where losses created while executing eagerly were returned as unevaluated lambdas in a defun. Lazily evaluates Layer losses by default when possible. Even when graph building this is generally a better thing to do (e.g. losses called in a while_loop). Allows calls to Layer.add_loss when executing eagerly, but only for losses which are not conditional on inputs (no activity regularizers). PiperOrigin-RevId: 214947108
| | * | Fix some documentation errorsGravatar EFanZh2018-09-28
| |/ / |/| |
* | | Fix error that occurs when attempting to use TensorFlow optimizers with ↵Gravatar Anjali Sridhar2018-09-27
| | | | | | | | | | | | | | | | | | Keras and DistributionStrategy PiperOrigin-RevId: 214890580
* | | Keras Lambda - enhancements to output_shape computationGravatar A. Unique TensorFlower2018-09-27
| | | | | | | | | | | | PiperOrigin-RevId: 214878428
* | | Merge pull request #21244 from smatzek:eager_in_fit_generatorGravatar TensorFlower Gardener2018-09-27
|\ \ \ | | | | | | | | | | | | PiperOrigin-RevId: 214869987
* | | | Updating the V2 variables API.Gravatar Alexandre Passos2018-09-27
| | | | | | | | | | | | | | | | PiperOrigin-RevId: 214824023
* | | | Add Mirrored distribution strategy support for new metrics with Keras and ↵Gravatar Pavithra Vijay2018-09-26
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Estimator Add support for stateful metrics in model to estimator PiperOrigin-RevId: 214714322
* | | | Automated rollback of commit 7229d08f0b25e24e6dd4833a94a27f404b27a350Gravatar Gunhan Gulsoy2018-09-26
| | | | | | | | | | | | | | | | PiperOrigin-RevId: 214575129
* | | | Keep only weak references to TensorFlow Optimizer objects in tf.kerasGravatar Allen Lavoie2018-09-25
| | | | | | | | | | | | | | | | | | | | | | | | I don't think this annoyed anyone else yet, it's just a nit I noticed while making sure variables can be garbage collected when tracked via tf.keras. PiperOrigin-RevId: 214462105
* | | | Add validation that input shapes should be fully defined when using TPU ↵Gravatar Priya Gupta2018-09-24
| | | | | | | | | | | | | | | | | | | | | | | | strategy with keras. PiperOrigin-RevId: 214376435
* | | | BEGIN_PUBLICGravatar Alexandre Passos2018-09-24
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Temporary rollback to fix forward compatibility. END_PUBLIC Automated rollback of commit 0c48c703c3c1455cf3b2c0e47e2108e053ff83e2. Revert #21798. PiperOrigin-RevId: 214349479
* | | | Move from deprecated self.test_session() to self.cached_session().Gravatar A. Unique TensorFlower2018-09-24
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | self.test_session() has been deprecated in 9962eb5e84b15e309410071b06c2ed2d6148ed44 as its name confuses readers of the test. Moving to cached_session() instead which is more explicit about: * the fact that the session may be reused. * the session is not closed even when doing a "with self.test_session()" statement. PiperOrigin-RevId: 214300210
* | | | This CL adds an init_scope to the Keras set & get learning phase functions. ↵Gravatar A. Unique TensorFlower2018-09-24
| | | | | | | | | | | | | | | | | | | | | | | | | | | | This allows the Keras learning phase to work inside functions and defuns. Note: There might still be bugs in graph mode if the default placeholder is being fed (instead of using set_learning_phase) and a layer is in a function. PiperOrigin-RevId: 214299002
* | | | Merge pull request #21798 from facaiy:ENH/div_no_nan_treate_negative_as_zeroGravatar TensorFlower Gardener2018-09-24
|\ \ \ \ | | | | | | | | | | | | | | | PiperOrigin-RevId: 214290400
* | | | | Experiment using Bazel's pip_install rule to install keras_applications.Gravatar Michael Case2018-09-21
| | | | | | | | | | | | | | | | | | | | PiperOrigin-RevId: 214076591
| | | * | Fix long linesGravatar Martin Wicke2018-09-21
| | | | |
* | | | | keras/training.py: Improve error message.Gravatar Asim Shankar2018-09-21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Inspired by: https://stackoverflow.com/questions/52428939/eager-mode-optimizers/ PiperOrigin-RevId: 213948133
* | | | | Move from deprecated self.test_session() to self.cached_session().Gravatar A. Unique TensorFlower2018-09-21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | self.test_session() has been deprecated in 9962eb5e84b15e309410071b06c2ed2d6148ed44 as its name confuses readers of the test. Moving to cached_session() instead which is more explicit about: * the fact that the session may be reused. * the session is not closed even when doing a "with self.test_session()" statement. PiperOrigin-RevId: 213944932
* | | | | Move from deprecated self.test_session() to self.cached_session().Gravatar A. Unique TensorFlower2018-09-21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | self.test_session() has been deprecated in 9962eb5e84b15e309410071b06c2ed2d6148ed44 as its name confuses readers of the test. Moving to cached_session() instead which is more explicit about: * the fact that the session may be reused. * the session is not closed even when doing a "with self.test_session()" statement. PiperOrigin-RevId: 213944355
| | | | * Fix bad indentationGravatar Yanbo Liang2018-09-20
| | | | |
* | | | | Add more specific ReLU implementation tests.Gravatar Francois Chollet2018-09-20
| | | | | | | | | | | | | | | | | | | | PiperOrigin-RevId: 213890403
* | | | | This CL adds a Keras-based mobilenet_v2 feature extractor for object ↵Gravatar A. Unique TensorFlower2018-09-20
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | detection models. As part of this CL, we use the Keras mobilenet_v2 application's keyword argument layer injection API to allow the generated network to support the object detection hyperparameters. PiperOrigin-RevId: 213872175
* | | | | Callbacks should count the steps correctly in the multi step caseGravatar Sourabh Bajaj2018-09-20
| | | | | | | | | | | | | | | | | | | | PiperOrigin-RevId: 213829360
* | | | | Create a steps_per_run variable to be updated correctly in the fit loop to ↵Gravatar Sourabh Bajaj2018-09-19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | make sure we run fit for the right number of steps. PiperOrigin-RevId: 213706042
| | | | * Fix bug in metrics sparse_categorical_accuracy and ↵Gravatar Yanbo Liang2018-09-19
| | | | | | | | | | | | | | | | | | | | sparse_top_k_categorical_accuracy
* | | | | Re-enable flaky keras_testGravatar Anjali Sridhar2018-09-19
| | | | | | | | | | | | | | | | | | | | PiperOrigin-RevId: 213665390
* | | | | Add a space to the error message.Gravatar Amit Patankar2018-09-19
| |_|_|/ |/| | | | | | | | | | | PiperOrigin-RevId: 213661062
* | | | Force-place embedding variables on CPUs ein eager mode.Gravatar Alexandre Passos2018-09-19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This avoids problems which happen because most optimizers do not have sparse updating gpu kernels implemented. Fixes #22042 PiperOrigin-RevId: 213654354
* | | | Add Keras TPU support for the new metrics.Gravatar Pavithra Vijay2018-09-17
| | | | | | | | | | | | | | | | PiperOrigin-RevId: 213378552
* | | | Keep only weak references to variables in graph functionsGravatar Allen Lavoie2018-09-17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This enables cleanup of the variables referenced in defunned methods of objects when the object is garbage collected. Since one PolymorphicFunction is created per @defun, decorated methods before this change held on to all of the variables referenced in that method for any instance of the class (i.e. variables which should have been object-scoped were scoped to the lifetime of the class definition). Raises an exception if variables used in the function have been deleted when it is called, which means no local variables. PiperOrigin-RevId: 213337256
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-27 21:29:03 +0000