Commit 72cda264 authored by narugo1992's avatar narugo1992
Browse files

Merge branch 'main' into dev/operate

parents 2513cef4 f30a29e0

.github/workflows/test.yml

+0 −2
Original line number Diff line number Diff line
@@ -21,8 +21,6 @@ jobs: 
          - '3.9'

          - '3.10'

          - '3.11'

        exclude:

          - python-version: '3.11'



    steps:

      - name: Get system version for Linux

README.md

+7 −3
Original line number Diff line number Diff line
@@ -71,13 +71,17 @@ print(lpips_clustering(images)) # -1 means noises, the same as that in sklearn 


Currently, object detection is supported for anime heads and person, as shown below



* Face Detection



![face detection](https://github.com/deepghs/imgutils/blob/gh-pages/main/_images/face_detect_demo.plot.py.svg)



* Head Detection



![head detection](https://github.com/deepghs/imgutils/blob/gh-pages/main/_images/head_detect.plot.py.svg)

![head detection](https://github.com/deepghs/imgutils/blob/gh-pages/main/_images/head_detect_demo.plot.py.svg)



* Person Detection



![person detection](https://github.com/deepghs/imgutils/blob/gh-pages/main/_images/person_detect.plot.py.svg)

![person detection](https://github.com/deepghs/imgutils/blob/gh-pages/main/_images/person_detect_demo.plot.py.svg)



Based on practical tests, head detection currently has a very stable performance and can be used for automation tasks.

However, person detection is still being further iterated and will focus on enhancing detection capabilities for
@@ -88,7 +92,7 @@ artistic illustrations in the future. 
Anime images can be converted to line drawings using the model provided

by [patrickvonplaten/controlnet_aux](https://github.com/patrickvonplaten/controlnet_aux), as shown below.



![edge example](https://github.com/deepghs/imgutils/blob/gh-pages/main/_images/edge.plot.py.svg)

![edge example](https://github.com/deepghs/imgutils/blob/gh-pages/main/_images/edge_demo.plot.py.svg)



It is worth noting that the `lineart` model may consume more computational resources, while `canny` is the fastest but

has average effect. Therefore, `lineart_anime` may be the most balanced choice in most cases.

docs/source/api_doc/detect/face_detect_benchmark.plot.py

+4 −0
Original line number Diff line number Diff line
@@ -26,6 +26,10 @@ class FaceDetectBenchmark(BaseBenchmark): 
if __name__ == '__main__':

    create_plot_cli(

        [

            ('face v1.4 (yolov8s)', FaceDetectBenchmark('s', 'v1.4')),

            ('face v1.4 (yolov8n)', FaceDetectBenchmark('n', 'v1.4')),

            ('face v1.3 (yolov8s)', FaceDetectBenchmark('s', 'v1.3')),

            ('face v1.3 (yolov8n)', FaceDetectBenchmark('n', 'v1.3')),

            ('face v1 (yolov8s)', FaceDetectBenchmark('s', 'v1')),

            ('face v1 (yolov8n)', FaceDetectBenchmark('n', 'v1')),

            ('face v0 (yolov8s)', FaceDetectBenchmark('s', 'v0')),

docs/source/api_doc/detect/face_detect_benchmark.plot.py.svg

+723 −379

File changed.

Preview size limit exceeded, changes collapsed.

docs/source/api_doc/detect/face_detect_demo.plot.py.svg

+13 −13

File changed.

Preview size limit exceeded, changes collapsed.