Semantic Image Synthesis with SPADE (GauGAN) - Tensorflow
Simple Tensorflow implementation of "Semantic Image Synthesis with Spatially-Adaptive Normalization" (CVPR 2019 Oral)
Requirements
- scipy == 1.2.0
- The latest version is not available.
imsave
is deprecated.
- tqdm
- numpy
- pillow
- opencv-python
- tensorflow-gpu
- keras
Preparation
- YOUR DATASET
- Image
- Segmentation map
- Don't worry. I do one-hot encoding of segmentation map automatically (whether color or gray)
- CelebAMask-HQ
Pretrained model
- Download checkpoint
- CelebAMask-HQ, hinge loss
- It is a better performance than the results in the
READEME
segmap_label.txt
for CelebAMask-HQ
- {(0, 0, 0): 0, (0, 0, 255): 1, (255, 0, 0): 2, (150, 30, 150): 3, (255, 65, 255): 4, (150, 80, 0): 5, (170, 120, 65): 6, (125, 125, 125): 7, (255, 255, 0): 8, (0, 255, 255): 9, (255, 150, 0): 10, (255, 225, 120): 11, (255, 125, 125): 12, (200, 100, 100): 13, (0, 255, 0): 14, (0, 150, 80): 15, (215, 175, 125): 16, (220, 180, 210): 17, (125, 125, 255): 18}
Usage
โโโ dataset
ย ย โโโ YOUR_DATASET_NAME
ย ย โโโ image
ย ย ย ย ย โโโ 000001.jpg
โโโ 000002.png
โโโ ...
โโโ segmap
โโโ 000001.jpg
โโโ 000002.png
โโโ ...
โโโ segmap_test
โโโ a.jpg
โโโ b.png
โโโ ...
โโโ segmap_label.txt (Automatically created)
โโโ guide.jpg (example for guided image translation task)
Train
> python main.py --dataset spade_celebA --img_ch 3 --segmap_ch 3 --phase train
Random test
> python main.py --dataset spade_celebA --segmap_ch 3 --phase random
Guide test
> python main.py --dataset spade_celebA --img_ch 3 --segmap_ch 3 --phase guide --guide_img ./guide_img.png
Our Results
Loss grpah
CityScape
CelebA-HQ (Style Manipulation)
CelebA-HQ (Random Manipulation)
How about the Least-Square loss ?
CelebA-HQ (Style Manipulation)
CelebA-HQ (Random Manipulation)
Architecture
Generator |
Image Encoder |
Discriminator |
All-in-one |
|
|
|
|
SPADE architecture
SPADE |
SPADE Residual Block |
|
|
Author
Junho Kim