diffusion_models
diffusion_models copied to clipboard
acids-ircam
A series of tutorial notebooks on denoising diffusion probabilistic models in PyTorch
I would like to know if the fourth part of this series is available now. If it is available, can you put it here or share the link with us?
Hi, I think you have an error in:  while it should be q(x_t|x_0).
```python3 def denoising_score_matching(scorenet, samples, key, sigma=0.01): noise = jax.random.normal(key, samples.shape) perturbed_samples = samples + noise * sigma target = -noise / sigma scores = scorenet(perturbed_samples) loss = 1 / 2....
Which one's right? I guess there should be a '-' sign 
File: diffusion_01_score.ipynb. In the section 'Denoising score matching', the $\nabla_{\tilde{\mathbf{x}}} \log q_{\sigma}(\tilde{\mathbf{x}}\mid\mathbf{x})$ should be $= -\frac{\tilde{\mathbf{x}} - \mathbf{x}}{\sigma^{2}}$ instead of $= \frac{\tilde{\mathbf{x}} - \mathbf{x}}{\sigma^{2}}$. Again, thanks for your repository, it...
In notebooks I see updates of EMA model ```def update```, where we change shallow model, but ```def ema``` method was never called. It should be called ones per N epochs...
Why do you shift alphas_prod_p in diffusion_02_model.ipynb? alphas_prod_p = torch.cat([torch.tensor([1]).float(), alphas_prod[:-1]], 0)
Thanks for the very nice tutorial. I found that you may want to use normal distribution for noise term but use "rand" instand of "randn"? In the 6-th block of...
Hello, thank you for your tutorial. It helps me a lot to understand the model. I have got a small question. Since we set the n_steps to 100, the x_seq...
Metadata
Owner
Metadata
A series of tutorial notebooks on denoising diffusion probabilistic models in PyTorch