[pls merge] All pooling layers support data_format (#809)

* arrange examples

* reinforce file

* add slow

* add readme

* change online docs

* yapf

* remove images

* yapf

* fix docstyle

* don't use import *

* example --> examples

* docs example --> examples, tutorial --> tutorials

* fix yapf

* add changelog

* restore conflict vgg19

* all pooling support data_format

* changelog

* yapf

Author: zsdonghao

CHANGELOG.md

@@ -90,16 +90,18 @@ To release a new version, please update the changelog as followed:
   - Release SwitchNormLayer (PR #737)
   - Release QuanConv2d, QuanConv2dWithBN, QuanDenseLayer, QuanDenseLayerWithBN (PR#735)
   - Update Core Layer to support graph (PR ＃751)
+  - All Pooling layers support `data_format` (PR #809)
 - Setup:
   - Creation of installation flaggs `all_dev`, `all_cpu_dev`, and `all_gpu_dev` (PR #739)
-- Tutorials:
+- Examples:
+  - change folder struction (PR #802) 
   - `tutorial_models_vgg19` has been introduced to show how to use `tl.model.vgg19` (PR #698).
   - fix bug of `tutorial_bipedalwalker_a3c_continuous_action.py` (PR #734, Issue #732)
   - `tutorial_models_vgg16` and `tutorial_models_vgg19` has been changed the input scale from [0,255] to [0,1](PR #710)
   - `tutorial_mnist_distributed_trainer.py` and `tutorial_cifar10_distributed_trainer.py` are added to explain the uses of Distributed Trainer (PR #700)
   - add `tutorial_quanconv_cifar10.py` and `tutorial_quanconv_mnist.py` (PR #735)
   - add `tutorial_work_with_onnx.py`(PR #775)
-- Examples:
+- Applications:
   - [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://arxiv.org/abs/1703.06868) (PR #799)
 
 ### Changed
@@ -146,8 +148,8 @@ To release a new version, please update the changelog as followed:
 - @DEKHTIARJonathan: #739 #747 #750 #754
 - @lgarithm: #705 #700
 - @OwenLiuzZ: #698 #710 #775 #776
-- @zsdonghao: #711 #712 #734 #736 #737 #700 #751
-- @luomai: #700 #751 #766
+- @zsdonghao: #711 #712 #734 #736 #737 #700 #751 #809
+- @luomai: #700 #751 #766 #802
 - @XJTUWYD: #735
 - @mutewall: #735
 - @thangvubk: #759

example/adaptive_style_transfer/.gitignore renamed to applications/adaptive_style_transfer/.gitignore

@@ -0,0 +1,60 @@
+## Adaptive Style Transfer in TensorFlow and TensorLayer
+
+### Usage
+
+1. TensorLayer implementation of the ICCV 2017 Paper [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://arxiv.org/abs/1703.06868) which supports any styles in one single model.
+
+2. You can use the  <b>train.py</b> script to train your own model. To train the model, you need to download [MSCOCO dataset](http://cocodataset.org/#download) and [Wikiart dataset](https://www.kaggle.com/c/painter-by-numbers), and put the dataset images under the <b>'dataset/COCO\_train\_2014'</b> folder and <b>'dataset/wiki\_all\_images'</b> folder.
+
+
+3. Alternatively, you can use the <b>test.py</b> script to run my pretrained models. My pretrained models can be downloaded from [here](https://github.com/tensorlayer/pretrained-models/tree/master/models/style_transfer_pretrained_models), and  should be put into the <b>'pretrained_models'</b> folder for testing. The example images for testing can be download from [here](https://github.com/tensorlayer/pretrained-models/tree/master/models/style_transfer_models_and_examples)
+
+
+
+### Results
+
+Here are some result images (Left to Right: Content , Style , Result):
+
+<div align="center">
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/content/content_1.png" width=250 height=250>
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/style/style_5.png" width=250 height=250>
+   <img src="./images/output/style_5_content_1.jpg" width=250 height=250>
+</div>
+
+
+<div align="center">
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/content/content_2.png" width=250 height=250>
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/style/style11.png" width=250 height=250>
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/output/style_11_content2.png" width=250 height=250>
+</div>
+
+<div align="center">
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/content/chicago.jpg" width=250 height=250>
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/style/cat.jpg" width=250 height=250>
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/output/cat_chicago.jpg" width=250 height=250>
+</div>
+
+
+
+<div align="center">
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/content/lance.jpg" width=250 height=250>
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/style/lion.jpg" width=250 height=250>
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/output/lion_lance.jpg" width=250 height=250>
+</div>
+<div align="center">
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/content/content_4.png" width=250 height=250>
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/style/style_6.png" width=250 height=250>
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/output/style_6_content_4.jpg" width=250 height=250>
+</div>
+
+<div align="center">
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/content/lance.jpg" width=250 height=250>
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/style/udnie.jpg" width=250 height=250>
+   <img src="https://github.com/tensorlayer/pretrained-models/blob/master/models/style_transfer_models_and_examples/images/output/udnie_lance.jpg" width=250 height=250>
+</div>
+
+Enjoy!
+
+### License
+
+- This project for academic use only.

applications/adaptive_style_transfer/README.md

@@ -31,8 +31,8 @@ to the library as a developer.
   :caption: Starting with TensorLayer
 
   user/installation
-  user/tutorial
-  user/example
+  user/tutorials
+  user/examples
   user/contributing
   user/get_involved
   user/faq