ExplainingAI
ExplainingAI
Hello @100daggerz , I see that in your diffusion parameters, you have modified the timesteps, beta start and beta end. I would suggest to use the parameters mentioned in the...
Hello @awais00012 , I would need some more information to help with this. 1. When you say the results are poor, is it the latent image generation or the decoded...
Hello @jpmcarvalho , autoencoder_acc_step is just for gradient accumulation, mimicking training with larger batch size even if your GPU memory is not enough to accommodate the larger batch size. For...
Hello @Nikita-Sherstnev , VAE should work on smaller sizes also. Here's the config which I used for mnist dataset (https://github.com/explainingai-code/StableDiffusion-PyTorch/blob/main/config/mnist.yaml) and the only changes in config were the channels, im_size...
Hello @danielemolino , Yes you are correct. Assume your batch size is 4, so during training for each batch you would do the following: 1. Sample 4 timesteps(from 0 to...
Yes, but in this repo I have only used eps variation. You can take a look at the huggingface library to get better understanding of both variations. Its same as...
Hello, Thanks for the appreciation. I apologize that should have been part of the README , I have updated it now. Can you take a look - https://github.com/explainingai-code/DDPM-Pytorch/blob/main/README.md#training-on-your-own-images and let...
Can you tell me the im_path value you used in the config ? And also the directory structure of your dataset. Is it $REPO_ROOT/ultrasound256CH1/train/*.png ? The error basically means that...
Got it. Create a subfolder 'images' inside train directory and put all training png files in there. So $REPO_ROOT/ultrasound256CH1/train/images/*.png Leave the config as it is to point to "ultrasound256CH1/train" ....
Can you print the directory and path the code is searching at https://github.com/explainingai-code/DDPM-Pytorch/blob/main/dataset/mnist_dataset.py#L40 and share that. `print(d_name, os.path.join(im_path, d_name, '*.{}'.format(self.im_ext))) ` Also comment line https://github.com/explainingai-code/DDPM-Pytorch/blob/main/dataset/mnist_dataset.py#L42