denoising-diffusion-pytorch

denoising-diffusion-pytorch copied to clipboard

RuntimeError: Trying to resize storage that is not resizable

3

I want to use Multi-Task Facial Landmark (MTFL) dataset to train DDPM. I use the code bellow. ``` python from denoising_diffusion_pytorch import Unet, GaussianDiffusion, Trainer model = Unet( dim =...

song-wensong

How can I deal with images that height is not equal to weight?

2

Hi Lucidrains, I noticed that `height and width of image must be {img_size}`, but what if my image's weight and height are different? Does it mean that I have to...

Mystere271

Dimension issue with conditioning

1

I am trying to run the 1D diffusion model with conditioning but getting the following error. `x = self.init_conv(x)` in line https://github.com/lucidrains/denoising-diffusion-pytorch/blob/5ff2393c72a2a678535ac1c31779684552f18189/denoising_diffusion_pytorch/denoising_diffusion_pytorch_1d.py#L352 The input is `torch.Size([64, 705])` i.e batch size...

anshumansinha16

Hi, I am confused about why do we scale the value of the x0 sample from x1 to [-1, 1]. I understand why when x is between (-1, 1), the...

janelawrence

Hi I had trained on my custom dataset and when the model trained , it produced the checkpoint and sample image file which contains a grid of images. My questions...

lchunleo

How to generate new images?

15

Hi, I've trained a model and only got the pictures of the training process. The name of the model is 'model-10.pt'. I want to know how to use it to...

NinePeAkSword

How to generate images after training. Hope it could help you guys.

1

` from denoising_diffusion_pytorch import Unet, GaussianDiffusion, Trainer model = Unet( dim = 64, dim_mults = (1, 2, 4, 8), flash_attn = True ) diffusion = GaussianDiffusion( model, image_size = 128,...

CooperLuo32

Error of dimmensions while upsampling in class Unet1D

2

I am getting the following error in the upsampling of class Unet1D : `x = torch.cat((x, h.pop()), dim = 1)` . Is it related to conditional generation? If yes, then...

anshumansinha16

Could diffusion model work for n channels (n>3)?

1

Hello, My question is as the title. Why I have n > 3 is because I use DCT signals to represent an image. I tried to modify your Dataset class...

random-var-x

local gpu can't run full in small sample cases

5

My data is a 32*320 matrix with 32 samples and 320 dimensions. But locally using 4090, each iteration takes 20s and the cpu usage is 99% and gpu is 1%....

leiqianstat