tamarott / SinGAN

Official pytorch implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"

https://tamarott.github.io/SinGAN.htm

tamarott/SinGAN Issues

How to input image name
Updated 6 months ago
draw_concat
Updated 6 months ago
SIFID: nan
Updated a year ago
RuntimeError: Cannot initialize CUDA without ATen_cuda library.
Updated a year ago4
No such file or directory: 'TrainedModels/balloons/scale_factor=0.793701,alpha=100/Gs.pth'
Updated a year ago2
Black Image for fake_sample.png at scale 8 and 9
Updated a year ago2
ValueRrror of SIFID
Updated a year ago
About Pretrained Model (Harmonize and Super Resolution)
Updated a year ago
RuntimeError: CUDA out of memory.
Updated a year ago6
version another pytorch intead of 1.4.0
Updated a year ago
mask result image
Updated a year ago
Lack of imsave in random_samples.py
Closed a year ago
Lack of package versions in requirements.txt file.
Closed a year ago
Can I train model from multiple images?
Updated a year ago
Getting black images as output of harmonization
Updated a year ago2
Possible one-line solution for Runtime error (variables modified in-place)
Updated 2 years ago8
process of inject scale for image manip (supplemental material figure 3)
Updated 2 years ago
Does everyone know how to fix this runtime error？
Updated 2 years ago3
torch version issue, please suggest
Closed 3 years ago2
How to use SinGAN to perform image translation just as CycleGAN.
Updated 2 years ago
how to generate larger gifs
Updated 2 years ago2
Why the training always stop at scale 8 ?
Updated 2 years ago
ValueError: the input array must have size 3 along `channel_axis`, got (197, 250)
Closed 2 years ago2
Error: Providing a bool or integral fill value without setting the optional `dtype` or `out` arguments is currently unsupported
Updated 2 years ago
Is there someone know how many variants of SinGAN since 2019? Could you please send me some variants for me, thanks!
Updated 3 years ago
I guess there is Error at SIFID code
Updated 3 years ago
How to calculate "diversity" ?
Updated 3 years ago1
Training stops without an error
Updated 3 years ago5
Runtime Error: A100 is out of memory
Closed 3 years ago2
single channel error (ValueError : the input array must be have a shape == (.., .., [..,] 3)), got (614, 989, 1))
Updated 3 years ago4
How to deal with a single channel image
Updated 3 years ago5
About use TraindeModel
Updated 3 years ago
RuntimeError when attempting to use main_train.py out-of-the-box
Updated 3 years ago2
Codes are hard too understand, could you provide more annotation?
Updated 3 years ago
Reproduce paint to image task
Closed 3 years ago1
Cuda Out of Memory in gradients_penalty.backward()
Closed 3 years ago2
RunTimeError: Providing a bool or integral fill value without setting the optional 'dtype' or 'out' arguments is currently unsupported.
Closed 3 years ago1
FileNotFoundError
Closed 3 years ago2
Training loop for generator uses fake output from generator pre-update
Closed 3 years ago1
error=11 : invalid argument
Updated 3 years ago1
Question about calculating how the number of scales is calculated
Updated 3 years ago2
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.FloatTensor [3, 32, 3, 3]] is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).
Closed 3 years ago2
Changing the type of noise used during training
Closed 3 years ago1
The indicators in the paper cannot be obtained
Updated 3 years ago2
[Super Resolution] opt.mode = 'SR_train'
Closed 3 years ago2
Equine zebra
Updated 4 years ago
Why the image format have so much impact of SIFID, could you give some explanation?
Updated 4 years ago2
No results are shown in the folder "stone_edit_mask_out" when I run the editing.py?
Updated 4 years ago
Superresolution training and inference
Updated 4 years ago1
i want to know the usage of the mask
Updated 4 years ago2