search

menyifang / ADGAN

The Implementation of paper "Controllable Person Image Synthesis with Attribute-Decomposed GAN" CVPR 2020 (Oral); Pose and Appearance Attributes Transfer;
475 stars 90 forks source link

What is the mapping of the semantic map of person image to the merged K=8 attribute? #10

Closed nitthilan closed 4 years ago

nitthilan commented 4 years ago

I am trying to map the segmentation mask output with the merged (K=8) indexes. The current indexes I have are

np.array(('Background', # always index 0 'Hat', 'Hair', 'Glove', 'Sunglasses', 'UpperClothes', 'Dress', 'Coat', 'Socks', 'Pants', 'Jumpsuits', 'Scarf', 'Skirt', 'Face', 'Left-arm', 'Right-arm', 'Left-leg', 'Right-leg', 'Left-shoe', 'Right-shoe',)) is the input

and the merged index is : background, hair, face, upper clothes, pants, skirt, arm and leg

Is there a code you could share where this operation is performed? I am trying to reuse the pre-trained model

menyifang commented 4 years ago

Hi @nitthilan, our segmentation files 'semantic_merge3' is obtained with the following merge manner: 0(Background): Background 1(Pants): Pants 2(Hair): Hat, Hair 3(Skirt): Skirt 4(Face): Face, Sunglasses, Jumpsuits 5(UpperClothes): UpperClothes, Dress, Coat, Scarf 6(Arm): Glove, Left-arm, Right-arm 7(Leg): Socks, Left-leg, Right-leg, Left-shoe, Right-shoe

genghisun commented 4 years ago

Hi @nitthilan, our segmentation files 'semantic_merge3' is obtained with the following merge manner: 0(Background): Background 1(Pants): Pants 2(Hair): Hat, Hair 3(Skirt): Skirt 4(Face): Face, Sunglasses, Jumpsuits 5(UpperClothes): UpperClothes, Dress, Coat, Scarf 6(Arm): Glove, Left-arm, Right-arm 7(Leg): Socks, Left-leg, Right-leg, Left-shoe, Right-shoe

Hi, Can you explain why Jumpsuits are merged in the Face class?