data-efficient-gans

data-efficient-gans copied to clipboard

Deafult augmentation mode error?

3

davidecarnevali

train_set:  generated images:  @click.option('--outdir',default='/work/ai_lab/miner/data-efficient-gans/output', help='Where to save the results', required=True, metavar='DIR') @click.option('--gpus',default=2, help='Number of GPUs to use [default: 1]', type=int, metavar='INT') @click.option('--snap',default=10, help='Snapshot interval [default: 50 ticks]', type=int,...

tdf1995

nvcc fails on windows

10

op.h exists nowhere in my python environment.. where do I get it? (tf115py37) c:\Programming\PythonNotebooks\DataEfficientGans\data-efficient-gans\DiffAugment-stylegan2>python run_low_shot.py --dataset=100-shot-obama --resolution=64 2020-12-20 02:40:10.999131: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_100.dll Local submit - run_dir:...

TashaSkyUp

RuntimeError: No such operator aten::cudnn_convolution_backward_weight

1

I'm trying to create a new model by myself by using the following command: ``` shell python train.py --outdir=training-runs --data=https://data-efficient-gans.mit.edu/datasets/100-shot-obama.zip --gpus=1 ``` And I ran into the Error: return _VF.meshgrid(tensors,...

fancyshirt

How can we use generate.py file to load our own trained models?

1

HashmatShadab

How do you calculate accuracy in paper?

1

For example, in Figure 5 (b), you plot the D's accuracy on T(x), T(G(z)), and G(z), I wonder how this metric was calculated. After each update of discriminator or after...

Luciennnnnnn

Generate images from a grayscale trained pkl file

2

Hello, I have trained using a 100 set of grayscale images, now I am stuck in the generate.py because it is all set for generating RGB images. I get this...

velamini

NOT an issue, but a question :)

7

Hi, I read the paper and it very sounds. I have been trying NVIDIA StyleGanV2-ADA for weeks without success. It simply did not converge and generated images were full of...

thusinh1969

Training set image resolution

4

Hi, is there a way to train using a dataset of images with shape that is not a power of 2? Such as 400x400 or even 420x400? Thank you Davide

davidecarnevali

Questions about nearest neighbors in pixel space

2

Hi, I'd like to generate plots of Nearest neighbors in pixel space like Figure 16 from your paper. Could you guide if this method was included in this repository please?...

aprilycliu