├── README.md ├── CRNN.py └── license.txt /README.md: -------------------------------------------------------------------------------- 1 | TensorFlow (v1.0) code for the paper "Convolutional RNN: an Enhanced Model for Extracting Features from Sequential Data" (https://arxiv.org/abs/1602.05875) by Gil Keren and Björn Schuller. 2 | 3 | For any questions feel free to contact: cruvadom@gmail.com 4 | -------------------------------------------------------------------------------- /CRNN.py: -------------------------------------------------------------------------------- 1 | import tensorflow as tf 2 | 3 | r"""Performs the 1-D Convolutional RNN Operation, according to the paper: 4 | Convolutional RNN: an Enhanced Model for Extracting Features from Sequential Data (https://arxiv.org/abs/1602.05875) 5 | Gil Keren and Bjoern Schuller. 6 | 7 | Calling the below function is equivalnet to applying one CRNN layer. For a deep model with a few 8 | CRNN layers, the function should be invoked multiple times. 9 | 10 | Given a tensor, the function extracts patches of `kernel_size` time-steps, and processed each 11 | with one or more recurrent layers. The hidden state of the recurrent neural network is then 12 | returned as the feature vector representing the path. 13 | 14 | Args: 15 | tensor: The tensor to perform the operation on, shape `[batch, time-steps, features]` 16 | or `[batch, time-steps, features, 1]`. 17 | kernel_size: The number of time-steps to include in every patch/window (same as in standard 1-D convolution). 18 | stride: the number of time-steps between two consecutive patches/windows (same as in standard 1-D convolution). 19 | out_channels: The number of extracted features from each patch/window (in standard 1-D convolution 20 | known as the number of feature maps), which is the hidden dimension of the recurrent 21 | layers that processes each patch/window. 22 | rnn_n_layers: The number of recurrent layers to process the patches/windows. 23 | (in the original paper was always =1). 24 | rnn_type: Type of recurrent layers to use: `simple`/`lstm`/`gru` 25 | bidirectional: Whether to use a bidirectional recurrent layers (such as BLSTM, when the rnn_type is 'lstm'). 26 | If True, The actual number of extracted features from each patch/window is `2 * out_channels`. 27 | w_std: Weights in the recurrent layers will be initialized randomly using a Gaussaian distribution with 28 | zero mean and a standard deviation of `w_std`. Biases are initialized with zero. 29 | padding: `SAME` or `VALID` (same as in standard 1-D convolution). 30 | scope_name: For variable naming, the name prefix for variables names. 31 | 32 | Returns: 33 | A 3-D `Tensor` with shape `[batch, time-steps, features]`, similarly to the output of a standard 1-D convolution. 34 | """ 35 | def crnn(tensor, kernel_size, stride, out_channels, rnn_n_layers, rnn_type, bidirectional, w_std, padding, scope_name): 36 | with tf.variable_scope(scope_name, initializer=tf.truncated_normal_initializer(stddev=w_std)): 37 | # Expand to have 4 dimensions if needed 38 | if len(tensor.shape) == 3: 39 | tensor = tf.expand_dims(tensor, 3) 40 | 41 | # Extract the patches (returns [batch, time-steps, 1, patch content flattened]) 42 | batch_size = tensor.shape[0].value 43 | n_in_features = tensor.shape[2].value 44 | patches = tf.extract_image_patches(images=tensor, 45 | ksizes=[1, kernel_size, n_in_features, 1], 46 | strides=[1, stride, n_in_features, 1], 47 | rates=[1, 1, 1, 1], 48 | padding=padding) 49 | patches = patches[:, :, 0, :] 50 | 51 | # Reshape to do: 52 | # 1) reshape the flattened patches back to [kernel_size, n_in_features] 53 | # 2) combine the batch and time-steps dimensions (which will be the new 'batch' size, for the RNN) 54 | # now shape will be [batch * time-steps, kernel_size, n_features] 55 | time_steps_after_stride = patches.shape[1].value 56 | patches = tf.reshape(patches, [batch_size * time_steps_after_stride, kernel_size, n_in_features]) 57 | 58 | # Transpose and convert to a list, to fit the tf.contrib.rnn.static_rnn requirements 59 | # Now will be a list of length kernel_size, each element of shape [batch * time-steps, n_features] 60 | patches = tf.unstack(tf.transpose(patches, [1, 0, 2])) 61 | 62 | # Create the RNN Cell 63 | if rnn_type == 'simple': 64 | rnn_cell_func = tf.contrib.rnn.BasicRNNCell 65 | elif rnn_type == 'lstm': 66 | rnn_cell_func = tf.contrib.rnn.LSTMBlockCell 67 | elif rnn_type == 'gru': 68 | rnn_cell_func = tf.contrib.rnn.GRUBlockCell 69 | if not bidirectional: 70 | rnn_cell = rnn_cell_func(out_channels) 71 | else: 72 | rnn_cell_f = rnn_cell_func(out_channels) 73 | rnn_cell_b = rnn_cell_func(out_channels) 74 | 75 | # Multilayer RNN? (does not appear in the original paper) 76 | if rnn_n_layers > 1: 77 | if not bidirectional: 78 | rnn_cell = tf.contrib.rnn.MultiRNNCell([rnn_cell] * rnn_n_layers) 79 | else: 80 | rnn_cell_f = tf.contrib.rnn.MultiRNNCell([rnn_cell_f] * rnn_n_layers) 81 | rnn_cell_b = tf.contrib.rnn.MultiRNNCell([rnn_cell_b] * rnn_n_layers) 82 | 83 | # The RNN itself 84 | if not bidirectional: 85 | outputs, state = tf.contrib.rnn.static_rnn(rnn_cell, patches, dtype=tf.float32) 86 | else: 87 | outputs, output_state_fw, output_state_bw = tf.contrib.rnn.static_bidirectional_rnn(rnn_cell_f, rnn_cell_b, patches, dtype=tf.float32) 88 | 89 | # Use only the output of the last time-step (shape will be [batch * time-steps, out_channels]). 90 | # In the case of a bidirectional RNN, we want to take the last time-step of the forward RNN, 91 | # and the first time-step of the backward RNN. 92 | if not bidirectional: 93 | outputs = outputs[-1] 94 | else: 95 | half = int(outputs[0].shape.as_list()[-1] / 2) 96 | outputs = tf.concat([outputs[-1][:,:half], 97 | outputs[0][:,half:]], 98 | axis=1) 99 | 100 | # Expand the batch * time-steps back (shape will be [batch_size, time_steps, out_channels] 101 | if bidirectional: 102 | out_channels = 2 * out_channels 103 | outputs = tf.reshape(outputs, [batch_size, time_steps_after_stride, out_channels]) 104 | 105 | return outputs 106 | 107 | -------------------------------------------------------------------------------- /license.txt: -------------------------------------------------------------------------------- 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 | --------------------------------------------------------------------------------