All notable changes to this project will be documented in this file.

The format is based on Keep a Changelog and this project adheres to Semantic Versioning.

• API:
  • tl.alphas and tl.alphas_like added following the tf.ones/zeros and tf.zeros_like/ones_like (by @DEKHTIARJonathan in #580)
• Tutorials:
  • tutorial_tfslim has been introduced to show how to use SlimNetsLayer (by @2wins in #560).
• Test:
  • test_utils_predict.py added to reproduce and fix issue #288 (by @2wins in #566)
  • Layer_DeformableConvolution_Test added to reproduce issue #572 with deformable convolution (by @DEKHTIARJonathan in #573)
  • Array_Op_Alphas_Test and Array_Op_Alphas_Like_Test added to test tensorlayer/array_ops.py file (by @DEKHTIARJonathan in #580)
  • test_optimizer_amsgrad.py added to test AMSGrad optimizer (by @DEKHTIARJonathan in #636)
• CI Tool:
  • https://github.com/apps/stale/ added to clean stale issues (by @DEKHTIARJonathan in #573)
  • Changelog Probot Configuration added (by @DEKHTIARJonathan in #637)
• Layer:
  • ElementwiseLambdaLayer added to use custom function to connect multiple layer inputs (by @One-sixth in #579)
• Documentation:
  • Release semantic version added on index page (by @DEKHTIARJonathan in #633)
  • Optimizers page added (by @DEKHTIARJonathan in #636)
  • AMSGrad added on Optimizers page added (by @DEKHTIARJonathan in #636)
• Optimizer:
  • AMSGrad Optimizer added based on On the Convergence of Adam and Beyond (ICLR 2018) (by @DEKHTIARJonathan in #636)

• Tensorflow CPU & GPU dependencies moved to separated requirement files in order to allow PyUP.io to parse them (by @DEKHTIARJonathan in #573)
• The document of LambdaLayer for linking it with ElementwiseLambdaLayer (by @zsdonghao in #587)
• RTD links point to stable documentation instead of latest used for development (by @DEKHTIARJonathan in #633)

• Issue #498 - Deprecation Warning Fix in tl.layers.RNNLayer with inspect (by @DEKHTIARJonathan in #574)
• Issue #498 - Deprecation Warning Fix in tl.files with truth value of an empty array is ambiguous (by @DEKHTIARJonathan in #575)
• Issue #565 related to tl.utils.predict fixed - np.hstack problem in which the results for multiple batches are stacked along axis=1 (by @2wins in #566)
• Issue #572 with tl.layers.DeformableConv2d fixed (by @DEKHTIARJonathan in #573)
• Typo of the document of ElementwiseLambdaLayer (by @zsdonghao in #588)

@lgarithm @DEKHTIARJonathan @2wins @One-sixth @zsdonghao

• Github Templates added (by @DEKHTIARJonathan)
  • New issues Template
  • New PR Template
• Travis Deploy Automation on new Tag (by @DEKHTIARJonathan)
  • Deploy to PyPI and create a new version.
  • Deploy to Github Releases and upload the wheel files
• PyUP.io has been added to ensure we are compatible with the latest libraries (by @DEKHTIARJonathan)
• deconv2d now handling dilation_rate (by @zsdonghao)
• Documentation unittest added (by @DEKHTIARJonathan)
• test_layers_core has been added to ensure that LayersConfig is abstract.

• All Tests Refactored - Now using unittests and runned with PyTest (by @DEKHTIARJonathan)
• Documentation updated (by @zsdonghao)
• Package Setup Refactored (by @DEKHTIARJonathan)
• Dataset Downlaod now using library progressbar2 (by @DEKHTIARJonathan)
• deconv2d function transformed into Class (by @zsdonghao)
• conv1d function transformed into Class (by @zsdonghao)
• super resolution functions transformed into Class (by @zsdonghao)
• YAPF coding style improved and enforced (by @DEKHTIARJonathan)

• Backward Compatibility Restored with deprecation warnings (by @DEKHTIARJonathan)
• Tensorflow Deprecation Fix (Issue #498):
  • AverageEmbeddingInputlayer (by @zsdonghao)
  • load_mpii_pose_dataset (by @zsdonghao)
• maxPool2D initializer issue #551 (by @zsdonghao)
• LayersConfig class has been enforced as abstract
• Pooling Layer Issue #557 fixed (by @zsdonghao)

• scipy>=1.0,<1.1 => scipy>=1.1,<1.2

@zsdonghao @luomai @DEKHTIARJonathan