0.27.12

Merge pull request #102 from npielawski/main
Added gradient clipping.
2026-09-10 12:01:08 +08:00 · 2022-10-05 13:50:54 -07:00 · 2022-10-05 13:50:39 -07:00 · 2022-10-05 11:29:49 -07:00 · 2022-09-27 11:21:23 -07:00
3 changed files with 4 additions and 1 deletions
@@ -8,6 +8,8 @@ This implementation was transcribed from the official Tensorflow version <a href

 Youtube AI Educators - <a href="https://www.youtube.com/watch?v=W-O7AZNzbzQ">Yannic Kilcher</a> | <a href="https://www.youtube.com/watch?v=344w5h24-h8">AI Coffeebreak with Letitia</a> | <a href="https://www.youtube.com/watch?v=HoKDTa5jHvg">Outlier</a>

+<a href="https://github.com/yiyixuxu/denoising-diffusion-flax">Flax implementation</a> from <a href="https://github.com/yiyixuxu">YiYi Xu</a>
+
 <a href="https://huggingface.co/blog/annotated-diffusion">Annotated code</a> by Research Scientists / Engineers from <a href="https://huggingface.co/">🤗 Huggingface</a>

 Update: Turns out none of the technicalities really matters at all | <a href="https://arxiv.org/abs/2208.09392">"Cold Diffusion" paper</a>
@@ -845,6 +845,7 @@ class Trainer(object):

                    self.accelerator.backward(loss)

+                accelerator.clip_grad_norm_(self.model.parameters(), 1.0)
                pbar.set_description(f'loss: {total_loss:.4f}')

                accelerator.wait_for_everyone()
@@ -3,7 +3,7 @@ from setuptools import setup, find_packages
 setup(
  name = 'denoising-diffusion-pytorch',
  packages = find_packages(),
-  version = '0.27.11',
+  version = '0.27.12',
  license='MIT',
  description = 'Denoising Diffusion Probabilistic Models - Pytorch',
  author = 'Phil Wang',
Author	SHA1	Message	Date
Phil Wang	dfbafee555	0.27.12	2022-10-05 13:50:54 -07:00
Phil Wang	40dd8ba1de	Merge pull request #102 from npielawski/main Added gradient clipping.	2022-10-05 13:50:39 -07:00
Nicolas Pielawski	2ac3f94a80	Added gradient clipping.	2022-10-05 11:29:49 -07:00
Phil Wang	98f2eeac35	link to flax implementation from @yiyixuxu	2022-09-27 11:21:23 -07:00