Changelogs » Tf-keras-vis

PyUp Safety actively tracks 267,561 Python packages for vulnerabilities and notifies you when to upgrade.

Tf-keras-vis

0.5.3

Bugfix
  ---
  
  * Fix a problem that model's training-mode can NOT turn off (See issues / 26 for details).

0.5.2

Bugfix
  ---
  
  * Fix a problem that a Error occurs when `max_N` is None or under 0 in ScoreCAM

0.5.0

Major Feature
  ---
  
  * Add new methods (ScoreCAM and Faster-ScoreCAM)
  
  
  Breaking Changes
  ---
  * `tf_keras_vis.utils.print_gpus()` was deleted.
  * `tf_keras_vis.utils.losses.SmoothedLoss` was deleted.
  
  BugFix and Other Changes
  ---
  * Fixes a problem that ActivationMaximization couldn't calculate and normalize losses correctly when multiple samples.
  * Fixes a problem that the output of ActivationMaximization was restricted when input_ranges contain None.
  * Improve to raise ValueError when input shape doesn't have channels dimension in GradCAM.
  * Fixes a problem that GradCAM++ couldn't calculate scores correctly when multiple samples.
  * Add `tf_keras_vis.utils. num_of_gpus()` instead of `tf_keras_vis.utils. print_gpus()`.

0.4.0

Major Feature
  ---
  
  * Add GradCAM++ algorism implemented as GradcamPlusPlus class
  
  Bugfixes
  --
  
  * The noise of SmoothGrad is too strong.
  * Rotation in InputModifier across channles-dim.

0.3.3

Improvements
  ---
  
  * Refactoring and Vectorizing some processing in `Gradcam` and `Saliency`
  * Remove `.travis.yml` because there is Github Action as CI tools

0.3.2

This release includes the patch for improving Issue 15 that is **serious bugs**. So We highly recommend to update tf-keras-vis.
  
  BugFix and Other Changes
  ---
  
  * Fixes bug that tf_keras_vis.utils.normalize() can't batchwisely do normalization.
  * Add `expand_cam` argument to GradCAM__call__() for returning non-interpolated cam values.
  * In setup.py, rename `development` of extras_require to `develop`.

0.3.1

We re-uploaded tf-keras-vis to PyPI as v0.3.1 because wrong library was uploaded.

0.3.0

Bug Fixes
  ---
  
  * Fixes a lot of bugs in ActivationMaximization and Gradcam
  
  Breaking Changes
  ---
  
  * `tf_keras_vis.activation_maximization.ActivationMaximization.__call__()`'s `regularizers` argument no longer accepts `dict` object.
  * Rename `tf_keras_vis.gradcam.Gradcam.__call__()`'s `seek_penultimate_layer` argument to `seek_penultimate_conv_layer `.
  * Rename `tf_keras_vis.utils.listify`'s `empty_list_if_none` argument to `return_empty_list_if_none`.

0.2.5

Bugfix
  ---
  
  * Fixes a bug that tf-keras-vis can't install on Python 3.8.x

0.2.4

Improvements
  ---
  
  * Python 3.8 are available
  * Added docker-images that contains tf-keras-vis v0.2.4

0.2.2

Improvement
  ---
  
  * Add a argument to Gradcam__call__() to fix issues/4

0.2.1

Document issues fixes and other changes
  ---
  
  * Fixes examples of docker command in README.md
  * Remove unnecessary comments in source
  
  > [!NOTE]
  > This release is for updating description page on PyPI, so it NOT contains any changes of library's behaviors.

0.2.0

Bug Fixes and Other Changes
  ---
  
  * In Saliency and Gradcam, support seed_input that don't have samples (batch) dimension.
  * Fixes a lot of bugs
  * Dockerfiles changed to tensorlfow image base.
  * Added tests and .travis.yml .
  
  Breaking Changes
  ---
  
  * `tf_keras_vis.utils.losses.SmoothingLoss` class renamed to `tf_keras_vis.utils.losses.SmoothedLoss`.

0.1.0