khushalps/api_internal
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Squashed 'utils_v2/' changes from ef9630d..271426c

Browse Source 
271426c (20241010) Can now cache class methods by accessing a caching object from the class itself!
606b02a Merge commit 'b0e0760fc7bb6336debf621860d1286575a0b8cc'
3d2a723 (20241009) Work in progress.
58266e3 (20241009) 'last decorator' bug-fixed
53e7a39 (20241009) Work in progress.
dbfc17f (20241009) 'last decorator' bug-fixed
11875e6 (20241008) logging decorator and model improved.

git-subtree-dir: utils_v2
git-subtree-split: 271426c19bea8de5edec7ecb79ee04368c47b02f
This commit is contained in:
khushal
2024-10-10 11:44:01 +05:30
parent 8494a2c0c0
commit 0450b2a445
17 changed files with 218 additions and 257 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ai/image_segmentation/async_dichotomous_segmentation.py
+2 -2
View File
@@ -13,12 +13,12 @@
To provide an easy way to get masks from dichotomous image segmentation.
This code uses a very specific model from HuggingFace: "ZhengPeng7/BiRefNet-portrait".
You may experiment with other models too, but make sure that model is made for "dichotomous" behaviour. This
You may experiment with other behaviour_models too, but make sure that model is made for "dichotomous" behaviour. This
means that the model should have only two classes like "foreground", and "background". The specified model was
trained for implementing portrait mode style blurring of backgrounds.
The originally tested model has an MIT license as per their GitHub page. The code in this file may or may not
support drop-in replacement for other models, please be aware about this.
support drop-in replacement for other behaviour_models, please be aware about this.
REFERENCES: