Skip to content
Projects

chaiyujin/glow-pytorch has 514 GitHub stars and 81 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-19 06:07 UTC. Last push 2019-04-25.

How these counts are measured

Measured star growth

in 24h
0
in 7 days
Collecting history
in 15 days
Collecting history
in 1 month
Collecting history

Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.

About

pytorch implementation of openai paper "Glow: Generative Flow with Invertible 1×1 Convolutions"

Machine Learning

README.md

Original

Glow

This is pytorch implementation of paper "Glow: Generative Flow with Invertible 1x1 Convolutions". Most modules are adapted from the offical TensorFlow version openai/glow.

TODO

  • Glow model. The model is coded as described in original paper, some functions are adapted from offical TF version. Most modules are tested.
  • Trainer, builder and hparams loaded from json.
  • Infer after training
  • Test LU_decomposed 1x1 conv2d

Scripts

  • Train a model with
    train.py <hparams> <dataset> <dataset_root>
    
  • Generate z_delta and manipulate attributes with
    infer_celeba.py <hparams> <dataset_root> <z_dir>
    

Training result

Currently, I trained model for 45,000 batches with hparams/celeba.json using CelebA dataset. In short, I trained with follwing parameters

HParam Value
image_shape (64, 64, 3)
hidden_channels 512
K 32
L 3
flow_permutation invertible 1x1 conv
flow_coupling affine
batch_size 12 on each GPU, with 4 GPUs
learn_top false
y_condition false
  • Download pre-trained model from Dropbox

Reconstruction

Following are some samples at training phase. Row 1: reconstructed, Row 2: original.

Manipulate attribute

Use the method decribed in paper to calculate z_pos and z_neg for a given attribute. And z_delta = z_pos - z_neg is the direction to manipulate the original image.

  • manipulate Smiling (from negative to positive):

  • manipulate Young (from negative to positive):

  • manipulate Pale_Skin (from negative to positive):

  • manipulate Male (from negative to positive):

Issues

There might be some errors in my codes. Please help me to figure out.