├── README.md ├── decode_beam.py └── LICENSE /README.md: -------------------------------------------------------------------------------- 1 | # PyTorch-Beam-Search 2 | PyTorch implementation of beam search decoding for seq2seq models based on https://github.com/shawnwun/NNDIAL. 3 | Decoding goes seperately for each sentence and stores the nodes in prioritized queue. 4 | 5 | Usage: 6 | You can specify additional reward for decoding through BeamSearchNode.eval. Works for model with and without attention. 7 | -------------------------------------------------------------------------------- /decode_beam.py: -------------------------------------------------------------------------------- 1 | import operator 2 | import torch 3 | import torch.nn as nn 4 | import torch.nn.functional as F 5 | from Queue import PriorityQueue 6 | device = torch.device("cuda" if torch.cuda.is_available() else "cpu") 7 | 8 | SOS_token = 0 9 | EOS_token = 1 10 | MAX_LENGTH = 50 11 | 12 | 13 | class DecoderRNN(nn.Module): 14 | def __init__(self, embedding_size, hidden_size, output_size, cell_type, dropout=0.1): 15 | ''' 16 | Illustrative decoder 17 | ''' 18 | super(DecoderRNN, self).__init__() 19 | self.hidden_size = hidden_size 20 | self.cell_type = cell_type 21 | self.embedding = nn.Embedding(num_embeddings=output_size, 22 | embedding_dim=embedding_size, 23 | ) 24 | 25 | self.rnn = nn.GRU(embedding_size, hidden_size, bidirectional=True, dropout=dropout, batch_first=False) 26 | self.dropout_rate = dropout 27 | self.out = nn.Linear(hidden_size, output_size) 28 | 29 | def forward(self, input, hidden, not_used): 30 | embedded = self.embedding(input).transpose(0, 1) # [B,1] -> [ 1, B, D] 31 | embedded = F.dropout(embedded, self.dropout_rate) 32 | 33 | output = embedded 34 | 35 | output, hidden = self.rnn(output, hidden) 36 | 37 | out = self.out(output.squeeze(0)) 38 | output = F.log_softmax(out, dim=1) 39 | return output, hidden 40 | 41 | 42 | class BeamSearchNode(object): 43 | def __init__(self, hiddenstate, previousNode, wordId, logProb, length): 44 | ''' 45 | :param hiddenstate: 46 | :param previousNode: 47 | :param wordId: 48 | :param logProb: 49 | :param length: 50 | ''' 51 | self.h = hiddenstate 52 | self.prevNode = previousNode 53 | self.wordid = wordId 54 | self.logp = logProb 55 | self.leng = length 56 | 57 | def eval(self, alpha=1.0): 58 | reward = 0 59 | # Add here a function for shaping a reward 60 | 61 | return self.logp / float(self.leng - 1 + 1e-6) + alpha * reward 62 | 63 | 64 | decoder = DecoderRNN() 65 | 66 | 67 | def beam_decode(target_tensor, decoder_hiddens, encoder_outputs=None): 68 | ''' 69 | :param target_tensor: target indexes tensor of shape [B, T] where B is the batch size and T is the maximum length of the output sentence 70 | :param decoder_hidden: input tensor of shape [1, B, H] for start of the decoding 71 | :param encoder_outputs: if you are using attention mechanism you can pass encoder outputs, [T, B, H] where T is the maximum length of input sentence 72 | :return: decoded_batch 73 | ''' 74 | 75 | beam_width = 10 76 | topk = 1 # how many sentence do you want to generate 77 | decoded_batch = [] 78 | 79 | # decoding goes sentence by sentence 80 | for idx in range(target_tensor.size(0)): 81 | if isinstance(decoder_hiddens, tuple): # LSTM case 82 | decoder_hidden = (decoder_hiddens[0][:,idx, :].unsqueeze(0),decoder_hiddens[1][:,idx, :].unsqueeze(0)) 83 | else: 84 | decoder_hidden = decoder_hiddens[:, idx, :].unsqueeze(0) 85 | encoder_output = encoder_outputs[:,idx, :].unsqueeze(1) 86 | 87 | # Start with the start of the sentence token 88 | decoder_input = torch.LongTensor([[SOS_token]], device=device) 89 | 90 | # Number of sentence to generate 91 | endnodes = [] 92 | number_required = min((topk + 1), topk - len(endnodes)) 93 | 94 | # starting node - hidden vector, previous node, word id, logp, length 95 | node = BeamSearchNode(decoder_hidden, None, decoder_input, 0, 1) 96 | nodes = PriorityQueue() 97 | 98 | # start the queue 99 | nodes.put((-node.eval(), node)) 100 | qsize = 1 101 | 102 | # start beam search 103 | while True: 104 | # give up when decoding takes too long 105 | if qsize > 2000: break 106 | 107 | # fetch the best node 108 | score, n = nodes.get() 109 | decoder_input = n.wordid 110 | decoder_hidden = n.h 111 | 112 | if n.wordid.item() == EOS_token and n.prevNode != None: 113 | endnodes.append((score, n)) 114 | # if we reached maximum # of sentences required 115 | if len(endnodes) >= number_required: 116 | break 117 | else: 118 | continue 119 | 120 | # decode for one step using decoder 121 | decoder_output, decoder_hidden = decoder(decoder_input, decoder_hidden, encoder_output) 122 | 123 | # PUT HERE REAL BEAM SEARCH OF TOP 124 | log_prob, indexes = torch.topk(decoder_output, beam_width) 125 | nextnodes = [] 126 | 127 | for new_k in range(beam_width): 128 | decoded_t = indexes[0][new_k].view(1, -1) 129 | log_p = log_prob[0][new_k].item() 130 | 131 | node = BeamSearchNode(decoder_hidden, n, decoded_t, n.logp + log_p, n.leng + 1) 132 | score = -node.eval() 133 | nextnodes.append((score, node)) 134 | 135 | # put them into queue 136 | for i in range(len(nextnodes)): 137 | score, nn = nextnodes[i] 138 | nodes.put((score, nn)) 139 | # increase qsize 140 | qsize += len(nextnodes) - 1 141 | 142 | # choose nbest paths, back trace them 143 | if len(endnodes) == 0: 144 | endnodes = [nodes.get() for _ in range(topk)] 145 | 146 | utterances = [] 147 | for score, n in sorted(endnodes, key=operator.itemgetter(0)): 148 | utterance = [] 149 | utterance.append(n.wordid) 150 | # back trace 151 | while n.prevNode != None: 152 | n = n.prevNode 153 | utterance.append(n.wordid) 154 | 155 | utterance = utterance[::-1] 156 | utterances.append(utterance) 157 | 158 | decoded_batch.append(utterances) 159 | 160 | return decoded_batch 161 | 162 | 163 | def greedy_decode(decoder_hidden, encoder_outputs, target_tensor): 164 | ''' 165 | :param target_tensor: target indexes tensor of shape [B, T] where B is the batch size and T is the maximum length of the output sentence 166 | :param decoder_hidden: input tensor of shape [1, B, H] for start of the decoding 167 | :param encoder_outputs: if you are using attention mechanism you can pass encoder outputs, [T, B, H] where T is the maximum length of input sentence 168 | :return: decoded_batch 169 | ''' 170 | 171 | batch_size, seq_len = target_tensor.size() 172 | decoded_batch = torch.zeros((batch_size, MAX_LENGTH)) 173 | decoder_input = torch.LongTensor([[SOS_token] for _ in range(batch_size)], device=device) 174 | 175 | for t in range(MAX_LENGTH): 176 | decoder_output, decoder_hidden = decoder(decoder_input, decoder_hidden, encoder_outputs) 177 | 178 | topv, topi = decoder_output.data.topk(1) # get candidates 179 | topi = topi.view(-1) 180 | decoded_batch[:, t] = topi 181 | 182 | decoder_input = topi.detach().view(-1, 1) 183 | 184 | return decoded_batch 185 | -------------------------------------------------------------------------------- /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 | --------------------------------------------------------------------------------