├── CONTRIBUTING.md ├── LICENSE └── README.md /CONTRIBUTING.md: -------------------------------------------------------------------------------- 1 | # How to Contribute 2 | 3 | We'd love to accept your patches and contributions to this project. There are 4 | just a few small guidelines you need to follow. 5 | 6 | ## Contributor License Agreement 7 | 8 | Contributions to this project must be accompanied by a Contributor License 9 | Agreement. You (or your employer) retain the copyright to your contribution; 10 | this simply gives us permission to use and redistribute your contributions as 11 | part of the project. Head over to to see 12 | your current agreements on file or to sign a new one. 13 | 14 | You generally only need to submit a CLA once, so if you've already submitted one 15 | (even if it was for a different project), you probably don't need to do it 16 | again. 17 | 18 | ## Code reviews 19 | 20 | All submissions, including submissions by project members, require review. We 21 | use GitHub pull requests for this purpose. Consult 22 | [GitHub Help](https://help.github.com/articles/about-pull-requests/) for more 23 | information on using pull requests. 24 | 25 | ## Community Guidelines 26 | 27 | This project follows [Google's Open Source Community 28 | Guidelines](https://opensource.google.com/conduct/). 29 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | 2 | Apache License 3 | Version 2.0, January 2004 4 | http://www.apache.org/licenses/ 5 | 6 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 7 | 8 | 1. Definitions. 9 | 10 | "License" shall mean the terms and conditions for use, reproduction, 11 | and distribution as defined by Sections 1 through 9 of this document. 12 | 13 | "Licensor" shall mean the copyright owner or entity authorized by 14 | the copyright owner that is granting the License. 15 | 16 | "Legal Entity" shall mean the union of the acting entity and all 17 | other entities that control, are controlled by, or are under common 18 | control with that entity. For the purposes of this definition, 19 | "control" means (i) the power, direct or indirect, to cause the 20 | direction or management of such entity, whether by contract or 21 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 22 | outstanding shares, or (iii) beneficial ownership of such entity. 23 | 24 | "You" (or "Your") shall mean an individual or Legal Entity 25 | exercising permissions granted by this License. 26 | 27 | "Source" form shall mean the preferred form for making modifications, 28 | including but not limited to software source code, documentation 29 | source, and configuration files. 30 | 31 | "Object" form shall mean any form resulting from mechanical 32 | transformation or translation of a Source form, including but 33 | not limited to compiled object code, generated documentation, 34 | and conversions to other media types. 35 | 36 | "Work" shall mean the work of authorship, whether in Source or 37 | Object form, made available under the License, as indicated by a 38 | copyright notice that is included in or attached to the work 39 | (an example is provided in the Appendix below). 40 | 41 | "Derivative Works" shall mean any work, whether in Source or Object 42 | form, that is based on (or derived from) the Work and for which the 43 | editorial revisions, annotations, elaborations, or other modifications 44 | represent, as a whole, an original work of authorship. For the purposes 45 | of this License, Derivative Works shall not include works that remain 46 | separable from, or merely link (or bind by name) to the interfaces of, 47 | the Work and Derivative Works thereof. 48 | 49 | "Contribution" shall mean any work of authorship, including 50 | the original version of the Work and any modifications or additions 51 | to that Work or Derivative Works thereof, that is intentionally 52 | submitted to Licensor for inclusion in the Work by the copyright owner 53 | or by an individual or Legal Entity authorized to submit on behalf of 54 | the copyright owner. For the purposes of this definition, "submitted" 55 | means any form of electronic, verbal, or written communication sent 56 | to the Licensor or its representatives, including but not limited to 57 | communication on electronic mailing lists, source code control systems, 58 | and issue tracking systems that are managed by, or on behalf of, the 59 | Licensor for the purpose of discussing and improving the Work, but 60 | excluding communication that is conspicuously marked or otherwise 61 | designated in writing by the copyright owner as "Not a Contribution." 62 | 63 | "Contributor" shall mean Licensor and any individual or Legal Entity 64 | on behalf of whom a Contribution has been received by Licensor and 65 | subsequently incorporated within the Work. 66 | 67 | 2. Grant of Copyright License. Subject to the terms and conditions of 68 | this License, each Contributor hereby grants to You a perpetual, 69 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 70 | copyright license to reproduce, prepare Derivative Works of, 71 | publicly display, publicly perform, sublicense, and distribute the 72 | Work and such Derivative Works in Source or Object form. 73 | 74 | 3. Grant of Patent License. Subject to the terms and conditions of 75 | this License, each Contributor hereby grants to You a perpetual, 76 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 77 | (except as stated in this section) patent license to make, have made, 78 | use, offer to sell, sell, import, and otherwise transfer the Work, 79 | where such license applies only to those patent claims licensable 80 | by such Contributor that are necessarily infringed by their 81 | Contribution(s) alone or by combination of their Contribution(s) 82 | with the Work to which such Contribution(s) was submitted. If You 83 | institute patent litigation against any entity (including a 84 | cross-claim or counterclaim in a lawsuit) alleging that the Work 85 | or a Contribution incorporated within the Work constitutes direct 86 | or contributory patent infringement, then any patent licenses 87 | granted to You under this License for that Work shall terminate 88 | as of the date such litigation is filed. 89 | 90 | 4. Redistribution. You may reproduce and distribute copies of the 91 | Work or Derivative Works thereof in any medium, with or without 92 | modifications, and in Source or Object form, provided that You 93 | meet the following conditions: 94 | 95 | (a) You must give any other recipients of the Work or 96 | Derivative Works a copy of this License; and 97 | 98 | (b) You must cause any modified files to carry prominent notices 99 | stating that You changed the files; and 100 | 101 | (c) You must retain, in the Source form of any Derivative Works 102 | that You distribute, all copyright, patent, trademark, and 103 | attribution notices from the Source form of the Work, 104 | excluding those notices that do not pertain to any part of 105 | the Derivative Works; and 106 | 107 | (d) If the Work includes a "NOTICE" text file as part of its 108 | distribution, then any Derivative Works that You distribute must 109 | include a readable copy of the attribution notices contained 110 | within such NOTICE file, excluding those notices that do not 111 | pertain to any part of the Derivative Works, in at least one 112 | of the following places: within a NOTICE text file distributed 113 | as part of the Derivative Works; within the Source form or 114 | documentation, if provided along with the Derivative Works; or, 115 | within a display generated by the Derivative Works, if and 116 | wherever such third-party notices normally appear. The contents 117 | of the NOTICE file are for informational purposes only and 118 | do not modify the License. You may add Your own attribution 119 | notices within Derivative Works that You distribute, alongside 120 | or as an addendum to the NOTICE text from the Work, provided 121 | that such additional attribution notices cannot be construed 122 | as modifying the License. 123 | 124 | You may add Your own copyright statement to Your modifications and 125 | may provide additional or different license terms and conditions 126 | for use, reproduction, or distribution of Your modifications, or 127 | for any such Derivative Works as a whole, provided Your use, 128 | reproduction, and distribution of the Work otherwise complies with 129 | the conditions stated in this License. 130 | 131 | 5. Submission of Contributions. Unless You explicitly state otherwise, 132 | any Contribution intentionally submitted for inclusion in the Work 133 | by You to the Licensor shall be under the terms and conditions of 134 | this License, without any additional terms or conditions. 135 | Notwithstanding the above, nothing herein shall supersede or modify 136 | the terms of any separate license agreement you may have executed 137 | with Licensor regarding such Contributions. 138 | 139 | 6. Trademarks. This License does not grant permission to use the trade 140 | names, trademarks, service marks, or product names of the Licensor, 141 | except as required for reasonable and customary use in describing the 142 | origin of the Work and reproducing the content of the NOTICE file. 143 | 144 | 7. Disclaimer of Warranty. Unless required by applicable law or 145 | agreed to in writing, Licensor provides the Work (and each 146 | Contributor provides its Contributions) on an "AS IS" BASIS, 147 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 148 | implied, including, without limitation, any warranties or conditions 149 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 150 | PARTICULAR PURPOSE. You are solely responsible for determining the 151 | appropriateness of using or redistributing the Work and assume any 152 | risks associated with Your exercise of permissions under this License. 153 | 154 | 8. Limitation of Liability. In no event and under no legal theory, 155 | whether in tort (including negligence), contract, or otherwise, 156 | unless required by applicable law (such as deliberate and grossly 157 | negligent acts) or agreed to in writing, shall any Contributor be 158 | liable to You for damages, including any direct, indirect, special, 159 | incidental, or consequential damages of any character arising as a 160 | result of this License or out of the use or inability to use the 161 | Work (including but not limited to damages for loss of goodwill, 162 | work stoppage, computer failure or malfunction, or any and all 163 | other commercial damages or losses), even if such Contributor 164 | has been advised of the possibility of such damages. 165 | 166 | 9. Accepting Warranty or Additional Liability. While redistributing 167 | the Work or Derivative Works thereof, You may choose to offer, 168 | and charge a fee for, acceptance of support, warranty, indemnity, 169 | or other liability obligations and/or rights consistent with this 170 | License. However, in accepting such obligations, You may act only 171 | on Your own behalf and on Your sole responsibility, not on behalf 172 | of any other Contributor, and only if You agree to indemnify, 173 | defend, and hold each Contributor harmless for any liability 174 | incurred by, or claims asserted against, such Contributor by reason 175 | of your accepting any such warranty or additional liability. 176 | 177 | END OF TERMS AND CONDITIONS 178 | 179 | APPENDIX: How to apply the Apache License to your work. 180 | 181 | To apply the Apache License to your work, attach the following 182 | boilerplate notice, with the fields enclosed by brackets "[]" 183 | replaced with your own identifying information. (Don't include 184 | the brackets!) The text should be enclosed in the appropriate 185 | comment syntax for the file format. We also recommend that a 186 | file or class name and description of purpose be included on the 187 | same "printed page" as the copyright notice for easier 188 | identification within third-party archives. 189 | 190 | Copyright [yyyy] [name of copyright owner] 191 | 192 | Licensed under the Apache License, Version 2.0 (the "License"); 193 | you may not use this file except in compliance with the License. 194 | You may obtain a copy of the License at 195 | 196 | http://www.apache.org/licenses/LICENSE-2.0 197 | 198 | Unless required by applicable law or agreed to in writing, software 199 | distributed under the License is distributed on an "AS IS" BASIS, 200 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 201 | See the License for the specific language governing permissions and 202 | limitations under the License. 203 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | ### This repo points to data from the papers [Measuring Abstract Reasoning in Neural Networks](https://arxiv.org/abs/1807.04225); Barrett, Hill, Santoro et al. (2018) and [Learning to Make Analogies by Contrasting Abstract Relational Structures](https://openreview.net/pdf?id=SylLYsCcFm); Hill, Santoro et al. (2019). The data can be found [here](https://console.cloud.google.com/storage/browser/ravens-matrices) 2 | 3 | This data is made available for the purposes of non-commercial research only and is not to be used for any other purpose. 4 | 5 | # Procedurally Generated Matrices (PGM) data 6 | From the paper [Measuring Abstract Reasoning in Neural Networks](https://arxiv.org/abs/1807.04225), Barrett, Hill, Santoro et al. 2018. 7 | 8 | ### UPDATE -- fix re: array shape and readability of the data 9 | 10 | Users have noted issues with readability of the data. This is caused by a mis-shaped numpy array upon loading. As noted below, images are of size 160x160x16. When loading the .npz, please reshape the array: 11 | 12 | ~~~~ 13 | data = np.load("name.npz") 14 | image = data["image"].reshape(16, 160, 160) 15 | ~~~~ 16 | 17 | The first dimension of image now indexes the array into the correct panels, as is intended. This array should now depict readable images when plotted. 18 | 19 | ## Directory and file organisation 20 | The parent data folder contains 8 archived directories, corresponding to a particular generalisation regime: 21 | - neutral.tar.gz 22 | - interpolation.tar.gz 23 | - extrapolation.tar.gz 24 | - attr.rel.pairs.tar.gz 25 | - attr.rels.tar.gz 26 | - attrs.pairs.tar.gz 27 | - attrs.shape.color.tar.gz 28 | - attrs.line.type.tar.gz 29 | 30 | Within each folder are 1.42M .npz files encoding the samples. The naming convention is: PGM_{split_type}_{train/test/val}_{id}.npz, where split_type is one of the 8 indicated above, train/test/val is the train, test, or validation set, and id is a numerical identifier for a particular matrix. 31 | 32 | A saved array has the following structure: 33 | 34 | **image**: a 160x160x16 integer array with values from 0 to 255. The last dimension denotes the panel number for the matrix, with the first 8 panels being the "context", and the last 8 being the "choices". 35 | 36 | **meta_matrix**: A 4x12 binary array encoding the structure of the matrix (i.e., the triples $[r, o, a]$ contained in the matrix). The rows index a tuple, and the columns have the following syntax: 37 | 38 | 'shape' : 0 39 | 'line' : 1 40 | 'color' : 2 41 | 'number' : 3 42 | 'position' : 4 43 | 'size' : 5 44 | 'type' : 6 45 | 'progression' : 7 46 | 'XOR' : 8 47 | 'OR' : 9 48 | 'AND' : 10 49 | 'consistent_union' : 11 50 | 51 | **meta_target**: an OR operation applied across all binary-encoded triples [r, o, a] (i.e., the rows of the meta_matrix). 52 | 53 | **target**: integer value denoting the target for the particular matrix (i.e., the index of the correct answer among the "choice" panels). 54 | 55 | ## Notation 56 | $R$ denotes the set of relation types (progression, XOR, OR, AND, consistent union), $O$ denotes the object types (shape, line), and $A$ denotes the attribute types (size, colour, position, number). The structure of a matrix, $S$, is the set of triples $S=\{[r, o, a]\}$ that determine the challenge posed by a particular matrix. 57 | 58 | ## Generalisation split details 59 | The generalisation splits are as follows: 60 | 61 | - **neutral**: The structures encoding the matrices in both the training and testing sets contain any triples $[r, o, a]$ for $r \in R$, $o \in O$, and $a \in A$. Training and testing sets are disjoint, with separation occurring at the level of the input variables (i.e. pixel manifestations). 62 | 63 | - **interpolation**: As in the neutral split, $S$ consisted of any triples $[r, o, a]$. For interpolation, in the training set, when the attribute was "colour" or "size" (i.e., the ordered attributes), the values of the attributes were restricted to even-indexed members of a discrete set, whereas in the test set only odd-indexed values were permitted. Note that all $S$ contained some triple $[r, o, a]$ with the colour or size attribute . Thus, generalisation is required for every question in the test set. 64 | 65 | - **extrapolation**: Same as in interpolation, but the values of the attributes were restricted to the lower half of the discrete set during training, whereas in the test set they took values in the upper half. 66 | 67 | - **attr.rel.pairs**: All $S$ contained at least two triples, $([r_1,o_1,a_1],[r_2,o_2,a_2]) = (t_1, t_2)$, of which 400 are viable. We randomly allocated 360 to the training set and 40 to the test set. Members $(t_1, t_2)$ of the 40 held-out pairs did not occur together in structures $S$ in the training set, and all structures $S$ had at least one such pair $(t_1, t_2)$ as a subset. 68 | 69 | - **attr.rels**: In our dataset, there are 29 possible unique triples $[r,o,a]$. We allocated seven of these for the test set, at random, but such that each of the attributes was represented exactly once in this set. These held-out triples never occurred in questions in the training set, and every $S$ in the test set contained at least one of them. 70 | 71 | - **attrs.pairs**: $S$ contained at least two triples. There are 20 (unordered) viable pairs of attributes $(a_1, a_2)$ such that for some $r_i, o_i, ([r_1,o_1,a_1],[r_2,o_2,a_2])$ is a viable triple pair $([r_1,o_1,a_1],[r_2,o_2,a_2]) = (t_1, t_2)$. We allocated 16 of these pairs for training and four for testing. For a pair $(a_1, a_2)$ in the test set, $S$ in the training set contained triples with $a_1$ or $a_2$. In the test set, all $S$ contained triples with $a_1$ and $a_2$. 72 | 73 | - **attrs.shape.color**, **attrs.line.type**: Held-out attribute shape-colour or line-type. $S$ in the training set contained no triples with $o$=shape and $a$=colour. All structures governing puzzles in the test set contained at least one triple with $o$=shape and $a$=colour. For comparison, we included a similar split in which triples were held-out if $o$=line and $a$=type. 74 | 75 | # Visual Analogy data 76 | 77 | From the paper [Learning to Make Analogies by Contrasting Abstract Relational Structures(https://openreview.net/pdf?id=SylLYsCcFm); Hill, Santoro et al (2019). 78 | 79 | This data can be found in the {analogies} subdirectory, which contains archived directories corresponding to the visual analogy problems described in the paper. 80 | 81 | novel.domain.transfer.tar.gz 82 | novel.target.domain.line.type.tar.gz 83 | novel.target.domain.shape.color.tar.gz 84 | interpolation.tar.gz 85 | extrapolation.tar.gz 86 | 87 | Within each of these directories is a large number of .npz files. The filenames are of the form analogy_{split_type}_{train/test/val}_{lbc/normal}_{id}.npz, where split_type is the name of one of the corresponding directory, lbc/normal determines the nature of the incorrect answer candidates and id is a unique identifier for the file. 88 | 89 | 90 | 91 | 92 | --------------------------------------------------------------------------------