├── .gitattributes ├── .gitignore ├── requirements.txt ├── README.md ├── demo.ipynb ├── dctransformer └── transforms.py └── LICENSE /.gitattributes: -------------------------------------------------------------------------------- 1 | *.ipynb linguist-documentation -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | __pycache__ 2 | venv 3 | .ipynb_checkpoints -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | # --find-links https://download.pytorch.org/whl/torch_stable.html 2 | --find-links https://download.pytorch.org/whl/cu111/torch_stable.html 3 | 4 | pillow-simd 5 | requests 6 | torch>=1.8 7 | torchvision>=0.9 -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Unofficial pytorch implementation of the paper "Generating images with sparse representations" 2 | 3 | ## Get started 4 | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/benjs/DCTransformer-PyTorch/blob/main/demo.ipynb) 5 | 6 | ``` 7 | git clone https://github.com/benjs/DCTransformer-PyTorch.git 8 | cd DCTransformer-PyTorch 9 | pip install -r requirements.txt 10 | ``` 11 | -------------------------------------------------------------------------------- /demo.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "metadata": { 3 | "language_info": { 4 | "codemirror_mode": { 5 | "name": "ipython", 6 | "version": 3 7 | }, 8 | "file_extension": ".py", 9 | "mimetype": "text/x-python", 10 | "name": "python", 11 | "nbconvert_exporter": "python", 12 | "pygments_lexer": "ipython3", 13 | "version": "3.9.1-final" 14 | }, 15 | "orig_nbformat": 2, 16 | "kernelspec": { 17 | "name": "python39164bitvenvvenvf2c9b4834eef47e697adcf97600cf570", 18 | "display_name": "Python 3.9.1 64-bit ('venv': venv)", 19 | "language": "python" 20 | } 21 | }, 22 | "nbformat": 4, 23 | "nbformat_minor": 2, 24 | "cells": [ 25 | { 26 | "cell_type": "code", 27 | "execution_count": null, 28 | "metadata": {}, 29 | "outputs": [], 30 | "source": [ 31 | "!git clone https://github.com/benjs/DCTransformer-PyTorch.git dctransformer_demo\n", 32 | "%cd dctransformer_demo" 33 | ] 34 | }, 35 | { 36 | "cell_type": "code", 37 | "execution_count": null, 38 | "metadata": {}, 39 | "outputs": [], 40 | "source": [ 41 | "!pip install -r requirements.txt matplotlib" 42 | ] 43 | }, 44 | { 45 | "cell_type": "code", 46 | "execution_count": null, 47 | "metadata": {}, 48 | "outputs": [], 49 | "source": [ 50 | "from dctransformer.transforms import DCTCompression\n", 51 | "dct = DCTCompression()" 52 | ] 53 | }, 54 | { 55 | "cell_type": "code", 56 | "execution_count": null, 57 | "metadata": {}, 58 | "outputs": [], 59 | "source": [ 60 | "import matplotlib.pyplot as plt\n", 61 | "import torch\n", 62 | "import torchvision\n", 63 | "\n", 64 | "weights = (dct.weight+1)/2 # from (-1,1) to (0,1)\n", 65 | "im_grid = torchvision.utils.make_grid(weights, nrow=8, padding=1)\n", 66 | "plt.imshow(im_grid.permute(1,2,0))\n", 67 | "plt.show()" 68 | ] 69 | }, 70 | { 71 | "cell_type": "code", 72 | "execution_count": null, 73 | "metadata": {}, 74 | "outputs": [], 75 | "source": [ 76 | "# DCT transform should yield high values at position 1 and 2 \n", 77 | "# (not 1 and 8 because of zigzag ordering)\n", 78 | "img = (weights[1] + weights[8])/2\n", 79 | "img = (img+1)/2 * 255\n", 80 | "\n", 81 | "plt.imshow(img.permute(1,2,0), cmap='gray')\n", 82 | "plt.show()" 83 | ] 84 | }, 85 | { 86 | "cell_type": "code", 87 | "execution_count": null, 88 | "metadata": {}, 89 | "outputs": [], 90 | "source": [ 91 | "img3 = img.unsqueeze(0).repeat(1,3,1,1) # Need batched and 3 channels\n", 92 | "img3 = (img3+1)/2 * 255\n", 93 | "torch.round(dct(img3)).view(192)" 94 | ] 95 | }, 96 | { 97 | "cell_type": "code", 98 | "execution_count": null, 99 | "metadata": {}, 100 | "outputs": [], 101 | "source": [] 102 | } 103 | ] 104 | } -------------------------------------------------------------------------------- /dctransformer/transforms.py: -------------------------------------------------------------------------------- 1 | import torch 2 | import torch.nn as nn 3 | import torch.nn.functional as F 4 | 5 | rgb_to_ycbcr = torch.tensor([ 6 | [ 0.299000, 0.587000, 0.114000], 7 | [-0.168736, -0.331264, 0.500000], 8 | [ 0.500000, -0.418688, -0.081312] 9 | ]) 10 | 11 | rgb_to_ycbcr_bias = torch.tensor([0, 0.5, 0.5]) 12 | 13 | class RGBToYCbCr(nn.Module): 14 | """Converts a tensor from RGB to YCbCr color space. 15 | Using transform from https://github.com/libjpeg-turbo/libjpeg-turbo/blob/master/jccolor.c 16 | """ 17 | def __init__(self): 18 | super().__init__() 19 | 20 | self.register_buffer('transform', rgb_to_ycbcr[:, :, None, None], persistent=False) 21 | self.register_buffer('transform_bias', rgb_to_ycbcr_bias, persistent=False) 22 | 23 | @torch.no_grad() 24 | def forward(self, x:torch.Tensor): 25 | return F.conv2d(x, self.transform, self.transform_bias) 26 | 27 | # Base matrix for luma quantization 28 | T_luma = torch.tensor([ 29 | [16, 11, 10, 16, 24, 40, 51, 61], 30 | [12, 12, 14, 19, 26, 58, 60, 55], 31 | [14, 13, 16, 24, 40, 57, 69, 56], 32 | [14, 17, 22, 29, 51, 87, 80, 62], 33 | [18, 22, 37, 56, 68, 109, 103, 77], 34 | [24, 35, 55, 64, 81, 104, 113, 92], 35 | [49, 64, 78, 87, 103, 121, 120, 101], 36 | [72, 92, 95, 98, 112, 100, 103, 99] 37 | ]) 38 | 39 | # Chroma quantization matrix 40 | Q_chroma = torch.tensor([ 41 | [17, 18, 24, 47, 99, 99, 99, 99], 42 | [18, 21, 26, 66, 99, 99, 99, 99], 43 | [24, 26, 56, 99, 99, 99, 99, 99], 44 | [47, 66, 99, 99, 99, 99, 99, 99], 45 | [99, 99, 99, 99, 99, 99, 99, 99], 46 | [99, 99, 99, 99, 99, 99, 99, 99], 47 | [99, 99, 99, 99, 99, 99, 99, 99], 48 | [99, 99, 99, 99, 99, 99, 99, 99] 49 | ]) 50 | 51 | def Q_luma(q:float) -> torch.Tensor: 52 | """Generate the luma quantization matrix 53 | 54 | Args: 55 | q (float): Quality parameter (1-100) 56 | """ 57 | s = 5000./q if q < 50 else 200 - 2*q 58 | return torch.floor((s*T_luma + 50)/100) 59 | 60 | def zigzag(n:int) -> torch.Tensor: 61 | """Generates a zigzag position encoding tensor. 62 | Source: https://stackoverflow.com/questions/15201395/zig-zag-scan-an-n-x-n-array 63 | """ 64 | 65 | pattern = torch.zeros(n, n) 66 | triangle = lambda x: (x*(x+1))/2 67 | 68 | # even index sums 69 | for y in range(0, n): 70 | for x in range(y%2, n-y, 2): 71 | pattern[y, x] = triangle(x + y + 1) - x - 1 72 | 73 | # odd index sums 74 | for y in range(0, n): 75 | for x in range((y+1)%2, n-y, 2): 76 | pattern[y, x] = triangle(x + y + 1) - y - 1 77 | 78 | # bottom right triangle 79 | for y in range(n-1, -1, -1): 80 | for x in range(n-1, -1+(n-y), -1): 81 | pattern[y, x] = n*n-1 - pattern[n-y-1, n-x-1] 82 | 83 | return pattern.t().contiguous() 84 | 85 | class DCTCompression(nn.Module): 86 | def __init__(self, N=8, q=50): 87 | super().__init__() 88 | 89 | self.N = N 90 | 91 | # Create all N² frequency squares 92 | # The DCT's result is a linear combination of those squares. 93 | 94 | # us: 95 | # [[0, 1, 2, ...], 96 | # [0, 1, 2, ...], 97 | # [0, 1, 2, ...], 98 | # ... ]) 99 | us = torch.arange(N).repeat(N, 1)/N # N×N 100 | vs = us.t().contiguous() # N×N 101 | 102 | xy = torch.arange(N,dtype=torch.float) # N 103 | 104 | # freqs: (2x + 1)uπ/(2B) or (2y + 1)vπ/(2B) 105 | freqs = ((xy + 0.5)*3.1415)[:, None, None] # N×1×1 106 | 107 | # cosine values, these are const no matter the image. 108 | cus = torch.cos(us * freqs) # N×N×N 109 | cvs = torch.cos(vs * freqs) # N×N×N 110 | 111 | # calculate the 64 (if N=8) frequency squares 112 | freq_sqs = cus.repeat(N, 1, 1, 1) * cvs[:, None] # N×N × N×N 113 | 114 | # Put freq squares in format N²×1×N×N (same as kernel size of convolution) 115 | # Use plt.imshow(torchvision.utils.make_grid(BlockDCT.weight, nrow = BlockDCT.N)) to visualize 116 | self.register_buffer('weight', freq_sqs.view(N*N, 1, N, N)) 117 | 118 | zigzag_vector = zigzag(self.N).view(self.N**2).to(torch.long) # N² 119 | self.register_buffer('zigzag_weight', F.one_hot(zigzag_vector).to(torch.float).inverse()[:,:,None,None]) 120 | 121 | # matrix with sqrt(2)/2 at u=y=0 122 | norm_matrix = torch.ones(N, N) 123 | norm_matrix[:,0] = torch.sqrt(torch.tensor(2.)).repeat(8)/2 124 | norm_matrix[0,:] = norm_matrix[:,0] 125 | norm_matrix /= 4 126 | 127 | norm_weight = norm_matrix.view(N*N,1).repeat(1,N*N)*torch.eye(N*N) # N²×N² 128 | self.register_buffer('norm_weight', norm_weight[:,:,None,None]) 129 | 130 | quant_vals = 1/torch.cat((Q_luma(q).view(64), Q_chroma.view(64), Q_chroma.view(64)), dim=0) 131 | quant_weight = quant_vals.repeat(3*N*N,1)*torch.eye(3*N*N) 132 | self.register_buffer('quant_weight', quant_weight[:,:,None,None]) 133 | 134 | @torch.no_grad() 135 | def forward(self, x:torch.Tensor): 136 | B, C, H, W = x.size() 137 | assert H % self.N == 0 or W % self.N == 0, "Images size must be multiple of N (TBD)" 138 | 139 | out = x.view(-1, 1, H, W) # Increase batch size by channels, reduce channels to 1 140 | out = F.conv2d(out, weight=self.weight, stride=self.N) 141 | out = F.conv2d(out, self.norm_weight) 142 | out = F.conv2d(out, self.zigzag_weight) 143 | out = out.view(B, C*self.N*self.N, H//self.N, W//self.N) 144 | out = F.conv2d(out, self.quant_weight) 145 | return out 146 | 147 | -------------------------------------------------------------------------------- /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 | --------------------------------------------------------------------------------