DDPM_Mnist/README.md
2023-03-14 23:28:08 +08:00

540 B

DDPM

A Simple implementation of DDPM model in PyTorch.

Traning

Before training, please set up the config.ini file:

[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