huchenlei/Depth-Anything
1
0
Fork 0
mirror of https://github.com/huchenlei/Depth-Anything.git synced 2026-01-26 15:29:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add gallery

Browse Source
This commit is contained in:
Lihe Yang
2024-02-04 20:32:27 +08:00
committed by GitHub
parent e911178017
commit da155b6cfc
38 changed files with 10 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
semseg/README.md
View File

@@ -37,18 +37,22 @@ Note that our results are obtained *without* Mapillary pre-training.
- [Cityscapes-ViT-L-mIoU-86.4](https://huggingface.co/spaces/LiheYoung/Depth-Anything/blob/main/checkpoints_semseg/cityscapes_vitl_mIoU_86.4.pth)
- [ADE20K-ViT-L-mIoU-59.4](https://huggingface.co/spaces/LiheYoung/Depth-Anything/blob/main/checkpoints_semseg/ade20k_vitl_mIoU_59.4.pth)
**Note:** If you want to reproduce the training process, please 1) download the [Depth Anything pre-trained model](https://huggingface.co/spaces/LiheYoung/Depth-Anything/blob/main/checkpoints/depth_anything_vitl14.pth) (to initialize the encoder) and 2) put it under the ``checkpoints`` folder.
## Installation
Please refer to [MMSegmentation](https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/get_started.md#installation) for instructions.
Please also install mmdet to support Mask2Former:
```bash
pip install "mmdet>=3.0.0rc4"
```
After installation:
- move our [config/depth_anything](./config/depth_anything/) to mmseg's [config](https://github.com/open-mmlab/mmsegmentation/tree/main/configs)
- move our [dinov2.py](./dinov2.py) to mmseg's [backbones](https://github.com/open-mmlab/mmsegmentation/tree/main/mmseg/models/backbones)
- add DINOv2 in mmseg's [models/backbones/\_\_init\_\_.py](https://github.com/open-mmlab/mmsegmentation/blob/main/mmseg/models/backbones/__init__.py)
- download our provided [torchhub](https://github.com/LiheYoung/Depth-Anything/tree/main/torchhub) directory and put it at the root of your working directory
For training or inference with our pre-trained models, please refer to MMSegmentation [instructions](https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/4_train_test.md).
**Note:** If you want to reproduce the **training** process, please 1) download the [Depth Anything pre-trained model](https://huggingface.co/spaces/LiheYoung/Depth-Anything/blob/main/checkpoints/depth_anything_vitl14.pth) (to initialize the encoder) and 2) put it under the ``checkpoints`` folder.
For training or inference with our pre-trained models, please refer to MMSegmentation [instructions](https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/4_train_test.md).