A collection of reference Jupyter notebooks and demo AI/ML applications for enterprise use cases: marketing, pricing, supply chain, smart manufacturing, and more.
Introduction to Statistics and Basics of Mathematics for Data Science - The Hacker's Way
关键参数与规格
关键参数与规格
参数
值
语言
Python
类别
Tutorials
子类别
ML/AI fundamentals
关键词
Image production
星标数
1,464
分叉数
304
贡献者
1
创建日期
2022-06-07
更新日期
2026-10-15
1 天星标数
0
7 天星标数
-1
排名
10,254
上次排名
10,262
排名变化
8
7 天星标排名
17,141
上次 7 天星标排名
12,602
7 天星标排名变化
-4,539
总星标排名
8,244
上次总星标排名
8,235
总星标排名变化
-9
国家
Germany
README 摘录
Diffusion Models This is an easy-to-understand implementation of diffusion models within 100 lines of code. Different from other implementations, this code doesn't use the lower-bound formulation for sampling and strictly follows Algorithm 1 from the DDPM paper, which makes it extremely short and easy to follow. Furthermore, the conditional code also implements Classifier-Free-Guidance (CFG) and Exponential-Moving-Average (EMA). Below you can find two explanation videos for the theory behind diffusion models and the implementation
. Train a Diffusion Model on your own data: Unconditional Training 1. (optional) Configure Hyperparameters in 2. (optional) Configure Hyperparameters in 2. Sampling The following examples show how to sample images using the models trained in the video on the Landscape Dataset. You can download the checkpoints for the models here. Unconditional Model Conditional Model This model was trained on CIFAR-10 64x64 with 10 classes A more advanced version of this code can be found here by @tcapelle. It introduces
better logging, faster & more efficient training and other nice features and is also being followed by a nice write-up.
This is an easy-to-understand implementation of diffusion models within 100 lines of code. Different from other implementations, this code doesn't use the lower-bound formulation for sampling and strictly follows Algorithm 1 from the DDPM paper, which makes it extremely short and easy to follow. There are two implementations: conditional and unconditional. Furthermore, the conditional code also implements Classifier-Free-Guidance (CFG) and Exponential-Moving-Average (EMA). Below you can find two explanation videos for the theory behind diffusion models and the implementation.
Train a Diffusion Model on your own data:
Unconditional Training
(optional) Configure Hyperparameters in ddpm.py
Set path to dataset in ddpm.py
python ddpm.py
Conditional Training
(optional) Configure Hyperparameters in ddpm_conditional.py
Set path to dataset in ddpm_conditional.py
python ddpm_conditional.py
Sampling
The following examples show how to sample images using the models trained in the video on the Landscape Dataset. You can download the checkpoints for the models here.
Unconditional Model
device = "cuda"
model = UNet().to(device)
ckpt = torch.load("unconditional_ckpt.pt")
model.load_state_dict(ckpt)
diffusion = Diffusion(img_size=64, device=device)
x = diffusion.sample(model, n=16)
plot_images(x)
Conditional Model
This model was trained on CIFAR-10 64x64 with 10 classes airplane:0, auto:1, bird:2, cat:3, deer:4, dog:5, frog:6, horse:7, ship:8, truck:9
n = 10
device = "cuda"
model = UNet_conditional(num_classes=10).to(device)
ckpt = torch.load("conditional_ema_ckpt.pt")
model.load_state_dict(ckpt)
diffusion = Diffusion(img_size=64, device=device)
y = torch.Tensor([6] * n).long().to(device)
x = diffusion.sample(model, n, y, cfg_scale=3)
plot_images(x)
A more advanced version of this code can be found here by @tcapelle. It introduces better logging, faster & more efficient training and other nice features and is also being followed by a nice write-up.
