Skip to content

Latest commit

 

History

History
14 lines (10 loc) · 774 Bytes

File metadata and controls

14 lines (10 loc) · 774 Bytes

Anime character segmentation with UNet

rr

Classes : [ background, hair, eye, mouth, face, skin, clothes ]

Model

1_Xp3R17gR8PL0SA0inUplcg

In: 3x512x512 -> Out: 7x512x512

It uses pretrained mobilenet_v2 as encoder

References

[1] Deep Learning Project — Drawing Anime Face with Simple Segmentation Mask link

[2] pit-ray/Anime-Semantic-Segmentation-GAN link