aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/contrib/gan
Commit message (Collapse)AuthorAge
* 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
* Updating doc references to tf.distributions to tfp.distributions.Gravatar Brian Patton2018-09-20
| | | | PiperOrigin-RevId: 213915666
* Move from deprecated self.test_session() to self.cached_session().Gravatar A. Unique TensorFlower2018-09-10
| | | | | | | | 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: 212336464
* Merge pull request #21061 from lgeiger:tfgan-fix-summaryGravatar TensorFlower Gardener2018-09-04
|\ | | | | | | PiperOrigin-RevId: 211502883
* | [TFGAN] StarGAN Estimator ImplementationGravatar A. Unique TensorFlower2018-08-27
| | | | | | | | PiperOrigin-RevId: 210334354
* | Move from deprecated self.test_session() to self.cached_session().Gravatar A. Unique TensorFlower2018-08-21
| | | | | | | | | | | | | | | | 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: 209701635
| * [tfgan] Respect use_loss_summaries in GANEstimatorGravatar Lukas Geiger2018-08-18
| | | | | | | | Since the refactor done in 47dea684efa41981e10299c2737317c504ce41af the `use_loss_summaries` argument of GANEstimator isn't respected anymore. This PR restores the original behavior and passes `use_loss_summaries` down to the loss functions.
* | Add stargan image summaries to show result of transforming image to eachGravatar Wesley Qian2018-08-13
| | | | | | | | | | | | domain. PiperOrigin-RevId: 208513708
* | Expose stargan_loss in train.py.Gravatar Wesley Qian2018-08-13
| | | | | | | | PiperOrigin-RevId: 208497573
* | Fix estimator dependencies in contrib/.Gravatar Michael Case2018-08-09
| | | | | | | | PiperOrigin-RevId: 208126204
* | Merge pull request #20735 from lgeiger:patch-1Gravatar TensorFlower Gardener2018-08-06
|\ \ | | | | | | | | | PiperOrigin-RevId: 207596874
* | | Add StarGAN Loss to TFGAN.Gravatar Wesley Qian2018-07-29
| | | | | | | | | | | | | | | | | | | | | | | | - stargan_loss is added to train.py as other xgan_loss. - StarGANModel wrappers for generator_loss, discrminator_loss, and gradient_penalty are defined in losses/tuple_losses_impl.py. PiperOrigin-RevId: 206509200
* | | Update test for StarGANModel to conform the original GANModel test.Gravatar Wesley Qian2018-07-25
| | | | | | | | | | | | PiperOrigin-RevId: 206027004
* | | [tfgan] Issue #18041: Make pooling consistent in `gan_loss`.Gravatar A. Unique TensorFlower2018-07-23
| | | | | | | | | | | | PiperOrigin-RevId: 205731279
* | | Extend random pool to work with arbitrarily nested tensor structures.Gravatar A. Unique TensorFlower2018-07-23
| | | | | | | | | | | | PiperOrigin-RevId: 205703156
* | | Change partial reconstruction loss in cyclegan_loss to the standard abs_diff.Gravatar Wesley Qian2018-07-23
| |/ |/| | | | | PiperOrigin-RevId: 205702476
* | Use paramaterized tests in `train_test.py`.Gravatar A. Unique TensorFlower2018-07-22
| | | | | | | | PiperOrigin-RevId: 205555784
* | Merge pull request #20820 from lgeiger:tfgan-fix-testGravatar TensorFlower Gardener2018-07-18
|\ \ | | | | | | | | | PiperOrigin-RevId: 205042372
* | | Add StarGAN model for TFGAN.Gravatar Wesley Qian2018-07-17
| | | | | | | | | | | | | | | | | | | | | | | | | | | - Defined namedtuple for StarGAN model. - Function for StarGAN model creation. - Test for StarGAN model creation. - Fix small lint issue in train.py. PiperOrigin-RevId: 204923505
| * | [tfgan] Fix assertion in regularization unittestGravatar Lukas Geiger2018-07-15
|/ / | | | | | | | | `self.assertTrue(3.0)` always evaluates to `True`. This PR fixes assertion so it will correctly check the loss value.
| * [tfgan] Remove outdated estimator TODOGravatar Lukas Geiger2018-07-12
|/ | | | | Training discriminator and generator with different ratios can already be done using `get_hooks_fn`. This was resolved in #14723
* Add build rules that were accidentally removed.Gravatar A. Unique TensorFlower2018-07-10
| | | | PiperOrigin-RevId: 203926475
* [tfgan] Deprecate GANHead and simplify GANEstimator.Gravatar A. Unique TensorFlower2018-07-10
| | | | PiperOrigin-RevId: 203914111
* Merge pull request #18565 from alexpantyukhin/ganhead_constructor_validateGravatar Martin Wicke2018-06-27
|\ | | | | add checking for input values in GANHead constructor
* | [tfgan] Add default serving key to unittestGravatar Lukas Geiger2018-06-15
| |
| * Merge branch 'ganhead_constructor_validate' of ↵Gravatar apantykhin2018-06-06
| |\ | | | | | | | | | | | | | | | | | | https://github.com/alexpantyukhin/tensorflow into ganhead_constructor_validate # Conflicts: # tensorflow/contrib/gan/python/estimator/python/head_impl.py
| * | remove optimizer checking.Gravatar apantykhin2018-06-06
| | |
* | | [tfgan] Add possibility to export GANEstimator saved modelGravatar Lukas Geiger2018-05-25
| | |
| | * Merge branch 'master' into ganhead_constructor_validateGravatar Alexander Pantyukhin2018-05-22
| |/| | |/ |/|
* | Make op unique name generation case insensitive (#18413)Gravatar Paul Van Eck2018-05-14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * Make op unique name generation case insensitive Unique name generation for operations depends on checking a dict for names currently in use. This commit makes it so that the names stored in this dict are always lowercase so that we can check if a name already exists regardless of the capitalization. This helps in filesystems where file paths are case insensitive and tensor dumps (like with tfdbg) try to follow directory structures that correspond to the tensor names. If two tensors have names with the same spelling, but different capitalizations, then this can lead to unintended side effects/errors on these case-insensitive file systems. * Change variable name to match unique_name * Adjust op names to fix tests
* | [tfgan] Allow to add custom eval metrics to GANEstimator (#19133)Gravatar Lukas Geiger2018-05-08
| |
* | [tfgan] Add discriminator and generator losses to eval_metrics (#19117)Gravatar Lukas Geiger2018-05-07
| |
* | Fixed Typos (#18806)Gravatar Nicholas Nadeau, P.Eng., AVS2018-05-03
| | | | | | * fixed typos
* | Merge changes from github.Gravatar Yifei Feng2018-04-23
| | | | | | | | PiperOrigin-RevId: 194031845
* | Support non-equal set sizes for FID computation.Gravatar A. Unique TensorFlower2018-04-23
| | | | | | | | PiperOrigin-RevId: 193917167
* | Create copy of locals() before copying, since modifying locals does not ↵Gravatar A. Unique TensorFlower2018-04-16
| | | | | | | | | | | | always affect the values. https://docs.python.org/2/library/functions.html#locals. PiperOrigin-RevId: 193116254
| * add checking for input values in GANHead constructorGravatar apantykhin2018-04-16
|/
* Merge changes from github.Gravatar Michael Case2018-04-10
| | | | PiperOrigin-RevId: 192388250
* test previously untested eval codepaths.Gravatar A. Unique TensorFlower2018-04-10
| | | | PiperOrigin-RevId: 192341561
* Windows: Enable tensorflow/contrib in Bazel build (Second try)Gravatar A. Unique TensorFlower2018-04-02
| | | | | | This reverts commit 4e108ef30d7cd7ae5e1c550ec5ae27e79b8c6e39. PiperOrigin-RevId: 191391075
* Add CycleGAN specific summary.Gravatar A. Unique TensorFlower2018-04-02
| | | | PiperOrigin-RevId: 191302480
* Remove all_opensource_files. It's not needed any more.Gravatar Martin Wicke2018-03-28
| | | | PiperOrigin-RevId: 190878279
* Merge changes from github.Gravatar Jacques Pienaar2018-03-21
| | | | PiperOrigin-RevId: 189945839
* Make L2 norm computation more stable.Gravatar Surya Bhupatiraju2018-03-19
| | | | | | Avoids the potentially numerically instable square root in the linalg_ops.norm() function because we 'undo' that operation with a math_ops.square() operation anyway. PiperOrigin-RevId: 189677716
* Automated g4 rollback of changelist 189231636Gravatar A. Unique TensorFlower2018-03-15
| | | | PiperOrigin-RevId: 189258641
* Add mean-only FID and diagonal-covariance-only FID variants to TFGAN.Gravatar Surya Bhupatiraju2018-03-15
| | | | PiperOrigin-RevId: 189232299
* Merge changes from github.Gravatar Jacques Pienaar2018-03-15
| | | | PiperOrigin-RevId: 189231636
* Merge changes from github.Gravatar Shanqing Cai2018-03-12
| | | | PiperOrigin-RevId: 188817194
* Merge changes from github.Gravatar Ankur Taly2018-02-16
| | | | PiperOrigin-RevId: 186073337
* Avoid running //third_party/tensorflow/contrib/gan:train_test under tsanGravatar A. Unique TensorFlower2018-02-16
| | | | PiperOrigin-RevId: 186005130
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-14 21:04:32 +0000