├── LICENSE ├── README.md ├── outputs ├── 1234461-cat.jpg ├── Hokusai-cat.jpg └── output-small.gif ├── src ├── fromkeras.py ├── model.py └── test.py ├── tests ├── 1234461.jpg └── Hokusai.jpg └── weights └── .gitkeep /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 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # sketchKeras-pytorch 2 | 3 | Unofficial implementation of [sketchKeras](https://github.com/lllyasviel/sketchKeras) in pytorch. sketchKeras is for extracting the sketch from a painting. 4 | I translated the original implementation in keras to the pytorch code and also converted the weight file. 5 | 6 | ## Usage 7 | Place the weight file in `weights` directory. 8 | The weight file can be downloaded [here](https://drive.google.com/file/d/1Zo88NmWoAitO7DnyBrRhKXPcHyMAZS97/view?usp=sharing). 9 | 10 | For processing, run the following command. 11 | ```sh 12 | python src/test.py -i [TEST.JPG] -o [OUTPUT.JPG] 13 | ``` 14 | 15 | If you are interested in the way to convert the weight file of the original implementation to this project, see `src/fromkeras.py` 16 | 17 | ## Examples 18 | First column : original image 19 | Second column : edge image extracted by Sobel filter 20 | Third column : result of sketchKeras 21 | 22 | ![](outputs/1234461-cat.jpg) 23 | (Original image from https://safebooru.org/index.php?page=post&s=view&id=1234461) 24 | ![](outputs/Hokusai-cat.jpg) 25 | (Original image from https://www.metmuseum.org/art/collection/search/45434?searchField=All&sortBy=Relevance&ft=Katsushika+Hokusai&offset=0&rpp=20&pos=1) 26 | ![](outputs/output-small.gif) 27 | (Original image from https://safebooru.org/index.php?page=post&s=view&id=3066528) 28 | 29 | ## (My) Environments 30 | - python (3.7.7) 31 | - numpy 32 | - torch (1.6.0) 33 | - opencv-python (4.4.0.42) -------------------------------------------------------------------------------- /outputs/1234461-cat.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/higumax/sketchKeras-pytorch/820691d8cd41717a0e2ad5fcc6b630260380c5a9/outputs/1234461-cat.jpg -------------------------------------------------------------------------------- /outputs/Hokusai-cat.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/higumax/sketchKeras-pytorch/820691d8cd41717a0e2ad5fcc6b630260380c5a9/outputs/Hokusai-cat.jpg -------------------------------------------------------------------------------- /outputs/output-small.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/higumax/sketchKeras-pytorch/820691d8cd41717a0e2ad5fcc6b630260380c5a9/outputs/output-small.gif -------------------------------------------------------------------------------- /src/fromkeras.py: -------------------------------------------------------------------------------- 1 | from keras.models import load_model 2 | from model import SketchKeras 3 | import torch 4 | 5 | if __name__ == "__main__": 6 | 7 | model = load_model("weights/mod.h5") 8 | 9 | conv_weight = dict() 10 | batch_weight = dict() 11 | conv_idx = 0 12 | batch_idx = 0 13 | for layer in model.layers: 14 | weights = layer.get_weights() 15 | 16 | layer_name = layer.name 17 | 18 | if layer_name.startswith("conv2d"): 19 | w, b = weights 20 | print(layer_name, w.shape, b.shape, w.dtype, b.dtype) 21 | conv_weight[f"conv_{conv_idx}_weight"] = w 22 | conv_weight[f"conv_{conv_idx}_bias"] = b 23 | conv_idx += 1 24 | 25 | if layer_name.startswith("batch"): 26 | print( 27 | layer_name, 28 | weights[0].shape, 29 | weights[1].shape, 30 | weights[2].shape, 31 | weights[3].shape, 32 | ) 33 | batch_weight[f"batch_{batch_idx}_weight"] = weights[0] 34 | batch_weight[f"batch_{batch_idx}_bias"] = weights[1] 35 | batch_weight[f"batch_{batch_idx}_running_mean"] = weights[2] 36 | batch_weight[f"batch_{batch_idx}_running_var"] = weights[3] 37 | batch_idx += 1 38 | 39 | print("-" * 20) 40 | 41 | conv_idx = 0 42 | batch_idx = 0 43 | torchmodel = SketchKeras() 44 | for name, module in torchmodel.named_children(): 45 | 46 | for submodule in module.modules(): 47 | submodule_name = submodule._get_name() 48 | 49 | if submodule_name.startswith("Conv2d"): 50 | w = conv_weight[f"conv_{conv_idx}_weight"].transpose(3, 2, 0, 1) 51 | b = conv_weight[f"conv_{conv_idx}_bias"] 52 | submodule.state_dict()["weight"].copy_(torch.tensor(w)) 53 | submodule.state_dict()["bias"].copy_(torch.tensor(b)) 54 | 55 | print( 56 | submodule_name, 57 | submodule.state_dict()["weight"].shape, 58 | submodule.state_dict()["bias"].shape, 59 | ) 60 | conv_idx += 1 61 | 62 | if submodule_name.startswith("BatchNorm2d"): 63 | a = batch_weight[f"batch_{batch_idx}_weight"] 64 | b = batch_weight[f"batch_{batch_idx}_bias"] 65 | c = batch_weight[f"batch_{batch_idx}_running_mean"] 66 | d = batch_weight[f"batch_{batch_idx}_running_var"] 67 | submodule.state_dict()["weight"].copy_(torch.tensor(a)) 68 | submodule.state_dict()["bias"].copy_(torch.tensor(b)) 69 | submodule.state_dict()["running_mean"].copy_(torch.tensor(c)) 70 | submodule.state_dict()["running_var"].copy_(torch.tensor(d)) 71 | 72 | print( 73 | submodule_name, 74 | submodule.state_dict()["weight"].shape, 75 | submodule.state_dict()["bias"].shape, 76 | submodule.state_dict()["running_mean"].shape, 77 | submodule.state_dict()["running_var"].shape, 78 | submodule.state_dict()["num_batches_tracked"].shape, 79 | ) 80 | 81 | batch_idx += 1 82 | 83 | torch.save(torchmodel.state_dict(), "weights/model.pth") 84 | -------------------------------------------------------------------------------- /src/model.py: -------------------------------------------------------------------------------- 1 | import torch 2 | import torch.nn as nn 3 | 4 | 5 | class SketchKeras(nn.Module): 6 | def __init__(self): 7 | super(SketchKeras, self).__init__() 8 | 9 | self.downblock_1 = nn.Sequential( 10 | nn.ReflectionPad2d((1, 1, 1, 1)), 11 | nn.Conv2d(1, 32, kernel_size=3, stride=1), 12 | nn.BatchNorm2d(32, eps=1e-3, momentum=0), 13 | nn.ReLU(), 14 | ) 15 | self.downblock_2 = nn.Sequential( 16 | nn.ReflectionPad2d((1, 1, 1, 1)), 17 | nn.Conv2d(32, 64, kernel_size=4, stride=2), 18 | nn.BatchNorm2d(64, eps=1e-3, momentum=0), 19 | nn.ReLU(), 20 | nn.ReflectionPad2d((1, 1, 1, 1)), 21 | nn.Conv2d(64, 64, kernel_size=3, stride=1), 22 | nn.BatchNorm2d(64, eps=1e-3, momentum=0), 23 | nn.ReLU(), 24 | ) 25 | self.downblock_3 = nn.Sequential( 26 | nn.ReflectionPad2d((1, 1, 1, 1)), 27 | nn.Conv2d(64, 128, kernel_size=4, stride=2), 28 | nn.BatchNorm2d(128, eps=1e-3, momentum=0), 29 | nn.ReLU(), 30 | nn.ReflectionPad2d((1, 1, 1, 1)), 31 | nn.Conv2d(128, 128, kernel_size=3, stride=1), 32 | nn.BatchNorm2d(128, eps=1e-3, momentum=0), 33 | nn.ReLU(), 34 | ) 35 | self.downblock_4 = nn.Sequential( 36 | nn.ReflectionPad2d((1, 1, 1, 1)), 37 | nn.Conv2d(128, 256, kernel_size=4, stride=2), 38 | nn.BatchNorm2d(256, eps=1e-3, momentum=0), 39 | nn.ReLU(), 40 | nn.ReflectionPad2d((1, 1, 1, 1)), 41 | nn.Conv2d(256, 256, kernel_size=3, stride=1), 42 | nn.BatchNorm2d(256, eps=1e-3, momentum=0), 43 | nn.ReLU(), 44 | ) 45 | self.downblock_5 = nn.Sequential( 46 | nn.ReflectionPad2d((1, 1, 1, 1)), 47 | nn.Conv2d(256, 512, kernel_size=4, stride=2), 48 | nn.BatchNorm2d(512, eps=1e-3, momentum=0), 49 | nn.ReLU(), 50 | ) 51 | self.downblock_6 = nn.Sequential( 52 | nn.ReflectionPad2d((1, 1, 1, 1)), 53 | nn.Conv2d(512, 512, kernel_size=3, stride=1), 54 | nn.BatchNorm2d(512, eps=1e-3, momentum=0), 55 | nn.ReLU(), 56 | ) 57 | 58 | self.upblock_1 = nn.Sequential( 59 | nn.Upsample((64, 64)), 60 | nn.ReflectionPad2d((1, 2, 1, 2)), 61 | nn.Conv2d(1024, 512, kernel_size=4, stride=1), 62 | nn.BatchNorm2d(512, eps=1e-3, momentum=0), 63 | nn.ReLU(), 64 | nn.ReflectionPad2d((1, 1, 1, 1)), 65 | nn.Conv2d(512, 256, kernel_size=3, stride=1), 66 | nn.BatchNorm2d(256, eps=1e-3, momentum=0), 67 | nn.ReLU(), 68 | ) 69 | 70 | self.upblock_2 = nn.Sequential( 71 | nn.Upsample((128, 128)), 72 | nn.ReflectionPad2d((1, 2, 1, 2)), 73 | nn.Conv2d(512, 256, kernel_size=4, stride=1), 74 | nn.BatchNorm2d(256, eps=1e-3, momentum=0), 75 | nn.ReLU(), 76 | nn.ReflectionPad2d((1, 1, 1, 1)), 77 | nn.Conv2d(256, 128, kernel_size=3, stride=1), 78 | nn.BatchNorm2d(128, eps=1e-3, momentum=0), 79 | nn.ReLU(), 80 | ) 81 | 82 | self.upblock_3 = nn.Sequential( 83 | nn.Upsample((256, 256)), 84 | nn.ReflectionPad2d((1, 2, 1, 2)), 85 | nn.Conv2d(256, 128, kernel_size=4, stride=1), 86 | nn.BatchNorm2d(128, eps=1e-3, momentum=0), 87 | nn.ReLU(), 88 | nn.ReflectionPad2d((1, 1, 1, 1)), 89 | nn.Conv2d(128, 64, kernel_size=3, stride=1), 90 | nn.BatchNorm2d(64, eps=1e-3, momentum=0), 91 | nn.ReLU(), 92 | ) 93 | 94 | self.upblock_4 = nn.Sequential( 95 | nn.Upsample((512, 512)), 96 | nn.ReflectionPad2d((1, 2, 1, 2)), 97 | nn.Conv2d(128, 64, kernel_size=4, stride=1), 98 | nn.BatchNorm2d(64, eps=1e-3, momentum=0), 99 | nn.ReLU(), 100 | nn.ReflectionPad2d((1, 1, 1, 1)), 101 | nn.Conv2d(64, 32, kernel_size=3, stride=1), 102 | nn.BatchNorm2d(32, eps=1e-3, momentum=0), 103 | nn.ReLU(), 104 | ) 105 | 106 | self.last_pad = nn.ReflectionPad2d((1, 1, 1, 1)) 107 | self.last_conv = nn.Conv2d(64, 1, kernel_size=3, stride=1) 108 | 109 | def forward(self, x): 110 | d1 = self.downblock_1(x) 111 | d2 = self.downblock_2(d1) 112 | d3 = self.downblock_3(d2) 113 | d4 = self.downblock_4(d3) 114 | d5 = self.downblock_5(d4) 115 | d6 = self.downblock_6(d5) 116 | 117 | u1 = torch.cat((d5, d6), dim=1) 118 | u1 = self.upblock_1(u1) 119 | u2 = torch.cat((d4, u1), dim=1) 120 | u2 = self.upblock_2(u2) 121 | u3 = torch.cat((d3, u2), dim=1) 122 | u3 = self.upblock_3(u3) 123 | u4 = torch.cat((d2, u3), dim=1) 124 | u4 = self.upblock_4(u4) 125 | u5 = torch.cat((d1, u4), dim=1) 126 | 127 | out = self.last_conv(self.last_pad(u5)) 128 | 129 | return out 130 | -------------------------------------------------------------------------------- /src/test.py: -------------------------------------------------------------------------------- 1 | import argparse 2 | import numpy as np 3 | import torch 4 | import cv2 5 | from model import SketchKeras 6 | 7 | device = "cuda" if torch.cuda.is_available() else "cpu" 8 | 9 | def parse_args(): 10 | parser = argparse.ArgumentParser() 11 | parser.add_argument("--input", "-i", type=str, default="", help="input image file") 12 | parser.add_argument( 13 | "--output", "-o", type=str, default="output.jpg", help="output image file" 14 | ) 15 | parser.add_argument( 16 | "--weight", "-w", type=str, default="weights/model.pth", help="weight file" 17 | ) 18 | return parser.parse_args() 19 | 20 | 21 | def preprocess(img): 22 | h, w, c = img.shape 23 | blurred = cv2.GaussianBlur(img, (0, 0), 3) 24 | highpass = img.astype(int) - blurred.astype(int) 25 | highpass = highpass.astype(np.float) / 128.0 26 | highpass /= np.max(highpass) 27 | 28 | ret = np.zeros((512, 512, 3), dtype=np.float) 29 | ret[0:h,0:w,0:c] = highpass 30 | return ret 31 | 32 | 33 | def postprocess(pred, thresh=0.18, smooth=False): 34 | assert thresh <= 1.0 and thresh >= 0.0 35 | 36 | pred = np.amax(pred, 0) 37 | pred[pred < thresh] = 0 38 | pred = 1 - pred 39 | pred *= 255 40 | pred = np.clip(pred, 0, 255).astype(np.uint8) 41 | if smooth: 42 | pred = cv2.medianBlur(pred, 3) 43 | return pred 44 | 45 | 46 | if __name__ == "__main__": 47 | args = parse_args() 48 | 49 | model = SketchKeras().to(device) 50 | 51 | if len(args.weight) > 0: 52 | model.load_state_dict(torch.load(args.weight)) 53 | print(f"{args.weight} loaded..") 54 | 55 | img = cv2.imread(args.input) 56 | 57 | # resize 58 | height, width = float(img.shape[0]), float(img.shape[1]) 59 | if width > height: 60 | new_width, new_height = (512, int(512 / width * height)) 61 | else: 62 | new_width, new_height = (int(512 / height * width), 512) 63 | img = cv2.resize(img, (new_width, new_height)) 64 | 65 | # preprocess 66 | img = preprocess(img) 67 | x = img.reshape(1, *img.shape).transpose(3, 0, 1, 2) 68 | x = torch.tensor(x).float() 69 | 70 | # feed into the network 71 | with torch.no_grad(): 72 | pred = model(x.to(device)) 73 | pred = pred.squeeze() 74 | 75 | # postprocess 76 | output = pred.cpu().detach().numpy() 77 | output = postprocess(output, thresh=0.1, smooth=False) 78 | output = output[:new_height, :new_width] 79 | 80 | cv2.imwrite(args.output, output) 81 | -------------------------------------------------------------------------------- /tests/1234461.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/higumax/sketchKeras-pytorch/820691d8cd41717a0e2ad5fcc6b630260380c5a9/tests/1234461.jpg -------------------------------------------------------------------------------- /tests/Hokusai.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/higumax/sketchKeras-pytorch/820691d8cd41717a0e2ad5fcc6b630260380c5a9/tests/Hokusai.jpg -------------------------------------------------------------------------------- /weights/.gitkeep: -------------------------------------------------------------------------------- 1 | 2 | --------------------------------------------------------------------------------