├── grid.gif ├── dict ├── 001.tif ├── 002.tif ├── 003.tif ├── 004.tif ├── 005.tif ├── 006.tif ├── 007.tif ├── 008.tif ├── 009.tif ├── 010.tif ├── 011.tif ├── 012.tif ├── 013.tif ├── 014.tif ├── 015.tif └── 016.tif ├── deploy.py ├── README.md ├── train.py ├── model.py └── LICENSE /grid.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/grid.gif -------------------------------------------------------------------------------- /dict/001.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/dict/001.tif -------------------------------------------------------------------------------- /dict/002.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/dict/002.tif -------------------------------------------------------------------------------- /dict/003.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/dict/003.tif -------------------------------------------------------------------------------- /dict/004.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/dict/004.tif -------------------------------------------------------------------------------- /dict/005.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/dict/005.tif -------------------------------------------------------------------------------- /dict/006.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/dict/006.tif -------------------------------------------------------------------------------- /dict/007.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/dict/007.tif -------------------------------------------------------------------------------- /dict/008.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/dict/008.tif -------------------------------------------------------------------------------- /dict/009.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/dict/009.tif -------------------------------------------------------------------------------- /dict/010.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/dict/010.tif -------------------------------------------------------------------------------- /dict/011.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/dict/011.tif -------------------------------------------------------------------------------- /dict/012.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/dict/012.tif -------------------------------------------------------------------------------- /dict/013.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/dict/013.tif -------------------------------------------------------------------------------- /dict/014.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/dict/014.tif -------------------------------------------------------------------------------- /dict/015.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/dict/015.tif -------------------------------------------------------------------------------- /dict/016.tif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/iwyoo/tf_ConvWTA/HEAD/dict/016.tif -------------------------------------------------------------------------------- /deploy.py: -------------------------------------------------------------------------------- 1 | import tensorflow as tf 2 | import numpy as np 3 | from PIL import Image 4 | import os 5 | 6 | from model import ConvWTA 7 | 8 | dict_dir = "dict" 9 | if not os.path.isdir(dict_dir): 10 | os.makedirs(dict_dir) 11 | recon_dir = "recon" 12 | if not os.path.isdir(recon_dir): 13 | os.makedirs(recon_dir) 14 | 15 | sess = tf.Session() 16 | ae = ConvWTA(sess, num_features=60) 17 | ae.restore("ckpt/model.ckpt") 18 | 19 | # Data read & train 20 | from tensorflow.examples.tutorials.mnist import input_data 21 | mnist = input_data.read_data_sets("mnist/", one_hot=True) 22 | 23 | # Save deconv kernels as images. 24 | f = ae.features() 25 | for idx in range(f.shape[-1]): 26 | Image.fromarray(f[:,:,0,idx]).save("{}/{:03d}.tif".format(dict_dir, idx+1)) 27 | 28 | # Save recon images 29 | x = tf.placeholder(tf.float32, [1, 28, 28, 1]) 30 | y = ae.reconstruct(x) 31 | 32 | for i in range(20): 33 | image = mnist.test.images[i, :] 34 | image = image.reshape([1, 28, 28, 1]) 35 | result = sess.run(y, {x:image}) 36 | Image.fromarray(result[0,:,:,0]).save("{}/{:03d}.tif".format(recon_dir, i+1)) 37 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # tf_ConvWTA 2 | Tensorflow implementation of convolutional Winner-Take-All Autoencdoer [1]. 3 | 4 | ## Usage 5 | ```python 6 | ae = ConvWTA(sess) 7 | 8 | # 1. to train an Autoencoder 9 | loss = ae.loss(x) 10 | train = optimizer.minimize(loss) 11 | sess.run(train, feed_dict={...}) 12 | 13 | # 2. to get the sparse codes 14 | h = ae.encoder(x) 15 | sess.run(h, feed_dict={...}) 16 | 17 | # 3. to get the reconstructed results 18 | y = ae.reconstruct(x) 19 | sess.run(y, feed_dict={...}) 20 | 21 | # 4. to get the learned features 22 | f = ae.features() # np.float32 array with shape [11, 11, 1, 16] 23 | 24 | # 4-1. to train a different number of features 25 | ae = ConvWTA(sess, num_features=32) 26 | 27 | # 5. to save & restore the variables 28 | ae.save(save_path) 29 | ae.restore(save_path) 30 | ``` 31 | 32 | ## Result 33 | - MNIST [2] 34 | 35 | ![alt tag](grid.gif) 36 | 37 | ## Reference 38 | - [1] Makhzani, Alireza, and Brendan J. Frey. "Winner-take-all autoencoders." Advances in Neural Information Processing Systems. 2015. 39 | - [2] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. "Gradient-based learning applied to document recognition." Proceedings of the IEEE, 86(11):2278-2324, November 1998. 40 | 41 | ## Author 42 | Inwan Yoo / iwyoo@unist.ac.kr 43 | -------------------------------------------------------------------------------- /train.py: -------------------------------------------------------------------------------- 1 | import tensorflow as tf 2 | tf.set_random_seed(2017) 3 | 4 | from model import ConvWTA 5 | 6 | import os 7 | ckpt_dir = "ckpt/" 8 | if not os.path.isdir(ckpt_dir): 9 | os.makedirs(ckpt_dir) 10 | ckpt_path = "ckpt/model.ckpt" 11 | 12 | epochs = 100 13 | batch_size = 100 14 | learning_rate = 1e-3 15 | shape = [batch_size, 28, 28, 1] 16 | 17 | # Basic tensorflow setting 18 | sess = tf.Session() 19 | ae = ConvWTA(sess) 20 | x = tf.placeholder(tf.float32, shape) 21 | loss = ae.loss(x, lifetime_sparsity=0.05) 22 | 23 | optim = tf.train.AdamOptimizer(learning_rate=learning_rate) 24 | train = optim.minimize(loss, var_list=ae.t_vars) 25 | 26 | sess.run(tf.global_variables_initializer()) 27 | 28 | # Data read & train 29 | from tensorflow.examples.tutorials.mnist import input_data 30 | mnist = input_data.read_data_sets("mnist/", one_hot=True) 31 | 32 | import time 33 | start_time = time.time() 34 | for epoch in range(epochs): 35 | total_batch = int(mnist.train.num_examples / batch_size) 36 | avg_loss = 0 37 | for i in range(total_batch): 38 | batch_x, _ = mnist.train.next_batch(batch_size) 39 | 40 | batch_x = batch_x.reshape(shape) 41 | l, _ = sess.run([loss, train], {x:batch_x}) 42 | avg_loss += l / total_batch 43 | 44 | print("Epoch : {:04d}, Loss : {:.9f}".format(epoch+1, avg_loss)) 45 | print("Training time : {}".format(time.time() - start_time)) 46 | 47 | ae.save(ckpt_path) 48 | -------------------------------------------------------------------------------- /model.py: -------------------------------------------------------------------------------- 1 | import tensorflow as tf 2 | 3 | """ 4 | Convolutioanl Winner-Take-All Autoencoder TensorFlow implementation. 5 | Usage : 6 | ae = ConvWTA(sess) 7 | 8 | # 1. to train an Autoencoder 9 | loss = ae.loss(x) 10 | train = optimizer.minimize(loss) 11 | sess.run(train, feed_dict={...}) 12 | 13 | # 2. to get the sparse codes 14 | h = ae.encoder(x) 15 | sess.run(h, feed_dict={...}) 16 | 17 | # 3. to get the reconstructed results 18 | y = ae.reconstruct(x) 19 | sess.run(y, feed_dict={...}) 20 | 21 | # 4. to get the learned features 22 | f = ae.features() # np.float32 array with shape [11, 11, 1, 16] 23 | # 4-1. to train a different number of features 24 | ae = ConvWTA(sess, num_features=32) 25 | 26 | # 5. to save & restore the variables 27 | ae.save(save_path) 28 | ae.restore(save_path) 29 | 30 | Reference: 31 | [1] https://arxiv.org/pdf/1409.2752.pdf 32 | """ 33 | 34 | class ConvWTA(object): 35 | """ 36 | Args : 37 | sess : TensorFlow session. 38 | x : Input tensor. 39 | """ 40 | def __init__(self, sess, num_features=16, name="ConvWTA"): 41 | self.sess = sess 42 | self.name = name 43 | self.size = [1, 128, 128, num_features] # ref [1] 44 | 45 | self._set_variables() 46 | self.t_vars = tf.get_collection( 47 | tf.GraphKeys.TRAINABLE_VARIABLES, scope=self.name) 48 | self.sess.run(tf.variables_initializer(self.t_vars)) 49 | self.saver = tf.train.Saver(self.t_vars) 50 | 51 | def encoder(self, x): 52 | with tf.variable_scope(self.name) as vs: 53 | h = self._conv(x, self.size[1], 5, 5, 1, 1, "conv_1") 54 | h = self._conv(h, self.size[2], 5, 5, 1, 1, "conv_2") 55 | h = self._conv(h, self.size[3], 5, 5, 1, 1, "conv_3") 56 | return h 57 | 58 | def _decoder(self, h): 59 | shape = tf.shape(h) 60 | out_shape = tf.stack([shape[0], shape[1], shape[2], 1]) 61 | with tf.variable_scope(self.name) as vs: 62 | y = self._deconv(h, out_shape, self.size[0], 63 | 11, 11, 1, 1, "deconv", end=True) 64 | return y 65 | 66 | def loss(self, x, lifetime_sparsity=0.20): 67 | h = self.encoder(x) 68 | h, winner = self._spatial_sparsity(h) 69 | h = self._lifetime_sparsity(h, winner, lifetime_sparsity) 70 | y = self._decoder(h) 71 | 72 | return tf.reduce_sum(tf.square(y - x)) 73 | 74 | def reconstruct(self, x): 75 | h = self.encoder(x) 76 | h, _ = self._spatial_sparsity(h) 77 | y = self._decoder(h) 78 | return y 79 | 80 | def _set_variables(self): 81 | with tf.variable_scope(self.name) as vs: 82 | self._conv_var(self.size[0], self.size[1], 5, 5, "conv_1") 83 | self._conv_var(self.size[1], self.size[2], 5, 5, "conv_2") 84 | self._conv_var(self.size[2], self.size[3], 5, 5, "conv_3") 85 | self.f, _ = self._deconv_var( 86 | self.size[-1], self.size[0], 11, 11, "deconv") 87 | 88 | def _conv_var(self, in_dim, out_dim, k_h, k_w, name, stddev=0.1): 89 | with tf.variable_scope(name) as vs: 90 | k = tf.get_variable('filter', 91 | [k_h, k_w, in_dim, out_dim], 92 | initializer=tf.truncated_normal_initializer(stddev=stddev)) 93 | b = tf.get_variable('biases', [out_dim], 94 | initializer=tf.constant_initializer(0.0001)) 95 | return k, b 96 | 97 | def _deconv_var(self, in_dim, out_dim, k_h, k_w, name, stddev=0.1): 98 | with tf.variable_scope(name) as vs: 99 | k = tf.get_variable('filter', 100 | [k_h, k_w, out_dim, in_dim], 101 | initializer=tf.truncated_normal_initializer(stddev=stddev)) 102 | b = tf.get_variable('biases', [out_dim], 103 | initializer=tf.constant_initializer(0.0001)) 104 | return k, b 105 | 106 | def _conv(self, x, out_dim, 107 | k_h, k_w, s_h, s_w, name, end=False): 108 | with tf.variable_scope(name, reuse=True) as vs: 109 | k = tf.get_variable('filter') 110 | b = tf.get_variable('biases') 111 | conv = tf.nn.conv2d(x, k, [1, s_h, s_w, 1], "SAME") + b 112 | return conv if end else tf.nn.relu(conv) 113 | 114 | def _deconv(self, x, out_shape, out_dim, 115 | k_h, k_w, s_h, s_w, name, end=False): 116 | with tf.variable_scope(name, reuse=True) as vs: 117 | k = tf.get_variable('filter') 118 | b = tf.get_variable('biases') 119 | deconv = tf.nn.conv2d_transpose( 120 | x, k, out_shape, [1, s_h, s_w, 1], "SAME") + b 121 | return deconv if end else tf.nn.relu(deconv) 122 | 123 | def _spatial_sparsity(self, h): 124 | shape = tf.shape(h) 125 | n = shape[0] 126 | c = shape[3] 127 | 128 | h_t = tf.transpose(h, [0, 3, 1, 2]) # n, c, h, w 129 | h_r = tf.reshape(h_t, tf.stack([n, c, -1])) # n, c, h*w 130 | 131 | th, _ = tf.nn.top_k(h_r, 1) # n, c, 1 132 | th_r = tf.reshape(th, tf.stack([n, 1, 1, c])) # n, 1, 1, c 133 | drop = tf.where(h < th_r, 134 | tf.zeros(shape, tf.float32), tf.ones(shape, tf.float32)) 135 | 136 | # spatially dropped & winner 137 | return h*drop, tf.reshape(th, tf.stack([n, c])) # n, c 138 | 139 | def _lifetime_sparsity(self, h, winner, rate): 140 | shape = tf.shape(winner) 141 | n = shape[0] 142 | c = shape[1] 143 | k = tf.cast(rate * tf.cast(n, tf.float32), tf.int32) 144 | 145 | winner = tf.transpose(winner) # c, n 146 | th_k, _ = tf.nn.top_k(winner, k) # c, k 147 | 148 | shape_t = tf.stack([c, n]) 149 | drop = tf.where(winner < th_k[:,k-1:k], # c, n 150 | tf.zeros(shape_t, tf.float32), tf.ones(shape_t, tf.float32)) 151 | drop = tf.transpose(drop) # n, c 152 | return h * tf.reshape(drop, tf.stack([n, 1, 1, c])) 153 | 154 | def features(self): 155 | return self.sess.run(self.f) 156 | 157 | def save(self, ckpt_path): 158 | self.saver.save(self.sess, ckpt_path) 159 | 160 | def restore(self, ckpt_path): 161 | self.saver.restore(self.sess, ckpt_path) 162 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright {yyyy} {name of copyright owner} 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------