LinWeiJeff

> The training progress depends on the number of images seen during training, which is `batch_size x iteration`. For faster convergence at high resolution, I recommend reweighting the training objective...

hello, I have the same problem in image inpainting based on this repository, did you have any idea or code for inpainting based on this repository?

hello, I have the same problem, did you solve it?

> I have the same problems: `(AGE) D:\model\AGE-main>python tools/inference.py File "D:\model\AGE-main\.\models\stylegan2\op\fused_act.py", line 9, in fused = load( File "D:\SourceCode\anaconda3\envs\AGE\lib\site-packages\torch\utils\cpp_extension.py", line 1124, in load return _jit_compile( File "D:\SourceCode\anaconda3\envs\AGE\lib\site-packages\torch\utils\cpp_extension.py", line 1362, in...

> > > I have the same problems: `(AGE) D:\model\AGE-main>python tools/inference.py File "D:\model\AGE-main\.\models\stylegan2\op\fused_act.py", line 9, in fused = load( File "D:\SourceCode\anaconda3\envs\AGE\lib\site-packages\torch\utils\cpp_extension.py", line 1124, in load return _jit_compile( File "D:\SourceCode\anaconda3\envs\AGE\lib\site-packages\torch\utils\cpp_extension.py", line...

@ATUI-TING I have tried to set environment variable `CUDA_HOME` to **C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.2** (as shown as the first picture below, I installed my cuda in C:\Program Files\NVIDIA GPU...

@HarperHao @jychoi118 I have the same question, why does the lambda_t equal to 1? Do you find out the reason?

> Is there any particular reason that the cosine scheduler is removed and this repository only supports linear schedulers, is it safe to just add back the cosine scheduler as...

> I used my own dataset and then inferred using the test.py code, the result of the reconstruction is clearer, but another issue that arose is that the generated result...

> @jbnjvc10000 did you tried? when I set `num_channels` to 256, i often have NaN in the loss which skip the training step. And it does not go away @MaugrimEP...