|
9 | 9 | }, |
10 | 10 | "source": [ |
11 | 11 | "# Clustering Images with DINOv2\n", |
12 | | - "This notebook shows how to extract feature vectors efficiency using [DINOv2](https://github.com/facebookresearch/dinov2) by Meta AI Research - No GPU needed!\n", |
| 12 | + "This notebook shows how to extract feature vectors efficiently using [DINOv2](https://github.com/facebookresearch/dinov2) by Meta AI Research - No GPU needed!\n", |
13 | 13 | "\n", |
14 | | - "This file includes artifacts from the DINOv2 repository, which is licensed under the\n", |
| 14 | + "This notebook includes artifacts from the DINOv2 repository, which is licensed under the\n", |
15 | 15 | "Creative Commons Attribution-NonCommercial 4.0 International License.\n", |
16 | 16 | "You are free to use this code as long as you provide attribution to the original author and use it in accordance with the terms of the license.\n", |
17 | 17 | "\n", |
|
39 | 39 | "source": [ |
40 | 40 | "## Download Oxford Pets Dataset\n", |
41 | 41 | "\n", |
42 | | - "For demonstration, we will use a widely available and well curated dataset. For that reason we might not find a lot of issues here. Feel free to swap this dataset with your own." |
| 42 | + "For demonstration, we will use a widely available and well curated dataset. For that reason we might not find a lot of issues here. \n", |
| 43 | + "\n", |
| 44 | + "Feel free to swap this dataset with your own." |
43 | 45 | ] |
44 | 46 | }, |
45 | 47 | { |
|
62 | 64 | }, |
63 | 65 | "source": [ |
64 | 66 | "## Import and Run fastdup to create embedding\n", |
65 | | - "Note: runtime on a 2 core colab node may be slow, it is recommended to run on 32 core machine to get x16 speedup. " |
| 67 | + "> **Note** - Runtime on a 2-core Google Colab node may be slow, it is recommended to run on 32-core machine to get x16 speedup. " |
66 | 68 | ] |
67 | 69 | }, |
68 | 70 | { |
|
138 | 140 | "source": [ |
139 | 141 | "## Image Clusters\n", |
140 | 142 | "\n", |
141 | | - "Let's debug embedding quality by clustering group of similar images and visualizing them." |
| 143 | + "Let's debug the embedding quality by clustering group of similar images and visualizing them." |
142 | 144 | ] |
143 | 145 | }, |
144 | 146 | { |
|
0 commit comments