Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ base_model:
|
|
| 15 |
|
| 16 |
In this repo you can find:
|
| 17 |
* The notebook which was used to convert [depth-anything/Depth-Anything-V2-Small](https://huggingface.co/depth-anything/Depth-Anything-V2-Small) into a CoreML package.
|
| 18 |
-
* Both mlpackage files which can be opened in Xcode and used for Preview and development of macOS and iOS Apps
|
| 19 |
* Performence and compute unit mapping report for these models as meassured on an iPhone 16 Pro Max
|
| 20 |
* One model uses internal resolution of 518x518 ("Box") and the other 518x392 ("Landscape").
|
| 21 |
* The "Landscape" is much faster than "Box" but will also give more "juggy" edges, due to the patch I applied to avoid bicubing upsampling (.diff file is also present in this repo)
|
|
|
|
| 15 |
|
| 16 |
In this repo you can find:
|
| 17 |
* The notebook which was used to convert [depth-anything/Depth-Anything-V2-Small](https://huggingface.co/depth-anything/Depth-Anything-V2-Small) into a CoreML package.
|
| 18 |
+
* Both mlpackage files which can be opened in Xcode and used for Preview (of both images and videos) and development of macOS and iOS Apps
|
| 19 |
* Performence and compute unit mapping report for these models as meassured on an iPhone 16 Pro Max
|
| 20 |
* One model uses internal resolution of 518x518 ("Box") and the other 518x392 ("Landscape").
|
| 21 |
* The "Landscape" is much faster than "Box" but will also give more "juggy" edges, due to the patch I applied to avoid bicubing upsampling (.diff file is also present in this repo)
|