Compare commits

...

2 Commits

Author SHA1 Message Date
bd1738dde8
docs: add readme 2023-03-14 23:28:08 +08:00
754c0ee186
docs: update .gitignore 2023-03-14 23:21:22 +08:00
4 changed files with 42 additions and 1 deletions

5
.gitignore vendored
View File

@ -1,2 +1,5 @@
data/*
output/*
output/*
*.pth
__pycache__/*
*.pyc

38
README.md Normal file
View File

@ -0,0 +1,38 @@
# DDPM
A Simple implementation of DDPM model in PyTorch.
![](./images/Screenshot_20230314_225320.png)
![](./images/ezgif.com-gif-maker.gif)
## Traning
Before training, please set up the config.ini file:
```ini
[unet]
batch_size = 256
time_emb_dim = 128
device = cuda
epoch_num = 500
learning_rate = 1e-4
[ddpm]
iteration = 500
```
To start training, run:
```
$ python train.py
```
## Sampling
To generate 16 pictures, run the following command:
The pictures will be output to the `./output` directory.
```
$ python sample 16
```

Binary file not shown.

After

Width:  |  Height:  |  Size: 26 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 251 KiB