|
25 | 25 | "source": [
|
26 | 26 | "# 🦙 **LaMa: Resolution-robust Large Mask Inpainting with Fourier Convolutions**\n",
|
27 | 27 | "\n",
|
28 |
| - "[[Project page](https://saic-mdal.github.io/lama-project/)] [[arXiv](https://arxiv.org/abs/2109.07161)] [[Supplementary](https://ashukha.com/projects/lama_21/lama_supmat_2021.pdf)] [[BibTeX](https://senya-ashukha.github.io/projects/lama_21/paper.txt)]\n", |
| 28 | + "[[Project page](https://saic-mdal.github.io/lama-project/)] [[GitHub](https://github.com/saic-mdal/lama)] [[arXiv](https://arxiv.org/abs/2109.07161)] [[Supplementary](https://ashukha.com/projects/lama_21/lama_supmat_2021.pdf)] [[BibTeX](https://senya-ashukha.github.io/projects/lama_21/paper.txt)]\n", |
29 | 29 | "\n",
|
30 | 30 | "<p align=\"center\" \"font-size:30px;\">\n",
|
31 | 31 | "Our model generalizes surprisingly well to much higher resolutions (~2k❗️) than it saw during training (256x256), and achieves the excellent performance even in challenging scenarios, e.g. completion of periodic structures.\n",
|
32 | 32 | "</p>\n",
|
33 | 33 | "\n",
|
34 |
| - "# Try it yorself!👇\n" |
| 34 | + "# Try it yourself!👇\n" |
35 | 35 | ]
|
36 | 36 | },
|
37 | 37 | {
|
38 | 38 | "cell_type": "code",
|
39 | 39 | "metadata": {
|
40 | 40 | "id": "RwXRMaNHW4r5",
|
41 |
| - "colab": { |
42 |
| - "base_uri": "https://localhost:8080/" |
43 |
| - }, |
44 |
| - "cellView": "form", |
45 |
| - "outputId": "9570e776-baea-4157-acfb-a35ec1f00e92" |
| 41 | + "cellView": "form" |
46 | 42 | },
|
47 | 43 | "source": [
|
48 | 44 | "#@title Run this sell to set everything up\n",
|
|
150 | 146 | " with open(filename, 'wb') as f:\n",
|
151 | 147 | " f.write(binary)"
|
152 | 148 | ],
|
153 |
| - "execution_count": 1, |
154 |
| - "outputs": [ |
155 |
| - { |
156 |
| - "output_type": "stream", |
157 |
| - "name": "stdout", |
158 |
| - "text": [ |
159 |
| - "\n", |
160 |
| - "> Cloning the repo\n", |
161 |
| - "Cloning into 'lama'...\n", |
162 |
| - "remote: Enumerating objects: 406, done.\u001b[K\n", |
163 |
| - "remote: Counting objects: 100% (406/406), done.\u001b[K\n", |
164 |
| - "remote: Compressing objects: 100% (341/341), done.\u001b[K\n", |
165 |
| - "remote: Total 406 (delta 127), reused 261 (delta 45), pack-reused 0\u001b[K\n", |
166 |
| - "Receiving objects: 100% (406/406), 11.76 MiB | 17.75 MiB/s, done.\n", |
167 |
| - "Resolving deltas: 100% (127/127), done.\n", |
168 |
| - "\n", |
169 |
| - "> Install dependencies\n", |
170 |
| - "\u001b[K |████████████████████████████████| 12.5 MB 17 kB/s \n", |
171 |
| - "\u001b[K |████████████████████████████████| 22.3 MB 1.3 MB/s \n", |
172 |
| - "\u001b[K |████████████████████████████████| 72 kB 669 kB/s \n", |
173 |
| - "\u001b[K |████████████████████████████████| 144 kB 48.1 MB/s \n", |
174 |
| - "\u001b[K |████████████████████████████████| 841 kB 39.7 MB/s \n", |
175 |
| - "\u001b[K |████████████████████████████████| 271 kB 41.7 MB/s \n", |
176 |
| - "\u001b[K |████████████████████████████████| 45 kB 3.5 MB/s \n", |
177 |
| - "\u001b[K |████████████████████████████████| 37.1 MB 40 kB/s \n", |
178 |
| - "\u001b[K |████████████████████████████████| 948 kB 33.8 MB/s \n", |
179 |
| - "\u001b[K |████████████████████████████████| 112 kB 48.9 MB/s \n", |
180 |
| - "\u001b[K |████████████████████████████████| 74 kB 3.0 MB/s \n", |
181 |
| - "\u001b[K |████████████████████████████████| 176 kB 40.7 MB/s \n", |
182 |
| - "\u001b[K |████████████████████████████████| 829 kB 40.1 MB/s \n", |
183 |
| - "\u001b[K |████████████████████████████████| 125 kB 32.2 MB/s \n", |
184 |
| - "\u001b[K |████████████████████████████████| 269 kB 43.1 MB/s \n", |
185 |
| - "\u001b[K |████████████████████████████████| 1.3 MB 31.6 MB/s \n", |
186 |
| - "\u001b[K |████████████████████████████████| 160 kB 47.9 MB/s \n", |
187 |
| - "\u001b[K |████████████████████████████████| 271 kB 40.5 MB/s \n", |
188 |
| - "\u001b[?25h Building wheel for antlr4-python3-runtime (setup.py) ... \u001b[?25l\u001b[?25hdone\n", |
189 |
| - " Building wheel for pyyaml (setup.py) ... \u001b[?25l\u001b[?25hdone\n", |
190 |
| - " Building wheel for future (setup.py) ... \u001b[?25l\u001b[?25hdone\n", |
191 |
| - " Building wheel for wget (setup.py) ... \u001b[?25l\u001b[?25hdone\n", |
192 |
| - "\n", |
193 |
| - "> Changing the dir to:\n", |
194 |
| - "/content/lama\n", |
195 |
| - "\n", |
196 |
| - "> Download the model\n", |
197 |
| - " % Total % Received % Xferd Average Speed Time Time Time Current\n", |
198 |
| - " Dload Upload Total Spent Left Speed\n", |
199 |
| - " 0 0 0 0 0 0 0 0 --:--:-- 0:00:01 --:--:-- 0\n", |
200 |
| - "100 363M 0 363M 0 0 9852k 0 --:--:-- 0:00:37 --:--:-- 9975k\n", |
201 |
| - "Archive: big-lama.zip\n", |
202 |
| - " inflating: big-lama/config.yaml \n", |
203 |
| - " inflating: big-lama/models/best.ckpt \n", |
204 |
| - "\n", |
205 |
| - "> Init mask-drawing code\n" |
206 |
| - ] |
207 |
| - } |
208 |
| - ] |
| 149 | + "execution_count": null, |
| 150 | + "outputs": [] |
209 | 151 | },
|
210 | 152 | {
|
211 | 153 | "cell_type": "markdown",
|
|
0 commit comments