Skip to content

Commit

Permalink
refine
Browse files Browse the repository at this point in the history
  • Loading branch information
CoinCheung committed Aug 2, 2022
1 parent 4d63a55 commit 6a2afc7
Showing 1 changed file with 2 additions and 2 deletions.
4 changes: 2 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -108,7 +108,7 @@ $ cd /path/to/BiSeNet
$ python tools/gen_dataset_annos.py --dataset coco
```

3. ade20k
3.ade20k

Download `ADEChallengeData2016.zip` from this [website](http://sceneparsing.csail.mit.edu/) and unzip it. Then we can move the uncompressed folders to `datasets/ade20k`, and generate the txt files with the script I prepared for you:
```
Expand All @@ -119,7 +119,7 @@ $ python tools/gen_dataset_annos.py --ade20k
```


4. custom dataset
4.custom dataset

If you want to train on your own dataset, you should generate annotation files first with the format like this:
```
Expand Down

0 comments on commit 6a2afc7

Please sign in to comment.