SPADE-Tensorflow
SPADE-Tensorflow copied to clipboard
taki0112
Simple Tensorflow implementation of "Semantic Image Synthesis with Spatially-Adaptive Normalization" a.k.a. GauGAN, SPADE (CVPR 2019 Oral)
any pretrained models on ade20k or cityscapes?
HI, the provided color label map can generate reasonable result, but the gray label map can not. Anybody knows about this?
These are some quick changes to the code that make it work with my current version of tensorflow 2. Not ready to be merged because it would overrule people using...
I run python main.py --dataset spade_celebA --segmap_ch 3 --phase, but the sved image is dark. something is wrong.
Hi, I am unable to reproduce prediction or training using existing celebA hinge checkpoint. Here is the stack trace of calling random test with pretrained checkpoint: `python main.py --dataset spade_celebA...
For example, if the image size is 632, the following error will occur. ValueError: Dimensions must be equal, but are 38 and 39 for 'generator/spade_resblock_0/spade_1/mul' (op: 'Mul') with input shapes:...
It seems that when merging CelebA-Mask-HQ masks the order of masks matters. In particular one should first render "skin" and only then "ear". Compare: https://github.com/taki0112/SPADE-Tensorflow/blob/master/dataset/spade_celebA/segmap/7.jpg https://github.com/olegmyrk/SPADE-Tensorflow/blob/develop/dataset/spade_celebA/segmap/7.png Could you share the...
Thank you for providing the version of TensorFlow. I would like to ask if the label image and the real image should be consistent during training. When I was training,...
Hi, I tested the model with the segmap_label.txt in the README and the segmap images in ./dataset/spade_celebA/segmap_test: ``` segmap_label.txt for CelebAMask-HQ {(0, 0, 0): 0, (0, 0, 255): 1, (255,...
