Skip to content
This repository has been archived by the owner on Dec 18, 2024. It is now read-only.

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
@ranftlr
ranftlr authored Mar 26, 2021
1 parent 2be666e commit 0e27bcb
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion README.md
View file
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
## Vision Transformers for Dense Prediction

This repository contains code and models for our [paper](https://github.com/intel-isl/DPT/releases/download/1_0/dpt.pdf):
This repository contains code and models for our [paper](https://arxiv.org/abs/2103.13413):

> Vision Transformers for Dense Prediction
> René Ranftl, Alexey Bochkovskiy, Vladlen Koltun
Expand Down

4 comments on commit 0e27bcb

@Wu-ZJ
Copy link

@Wu-ZJ Wu-ZJ commented on 0e27bcb Mar 27, 2021

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'm sorry. Is this project not finished yet? The semantic segmentation code doesn't seem to be complete.

@r90941022
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

hi where can I find MIDAS weights "midas_v21-f6b98070.pt" when I run '-t midas_v21'. thanks a lot

@AlexeyAB
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@r90941022 You can download https://github.com/intel-isl/MiDaS/releases/download/v2_1/model-f6b98070.pt rename it to midas_v21-f6b98070.pt and put in the directory /weights/

@AlexeyAB
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@manguoooneil Semantic code works well.

  1. Download https://github.com/intel-isl/DPT/releases/download/1_0/dpt_hybrid-ade20k-53898607.pt to the directory /weights/
  2. Put your images (with a context similar to the ADE20k dataset) to the directory /input/
  3. Run python run_segmentation.py --model_type dpt_hybrid
  4. See results in the directory /output_semseg/

Please sign in to comment.