Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Caochenjie #10

Merged
merged 2 commits into from
Dec 13, 2018
Merged

Caochenjie #10

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
682f29d
update for readme
ewrfcas Dec 13, 2018
9a92040
update for readme
ewrfcas Dec 13, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
12 changes: 6 additions & 6 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,22 +14,22 @@ The SAGAN was trained in batchsize=64 and cost only 3GB GPU memory. It needs abo

https://arxiv.org/abs/1809.11096?context=cs.LG

The BIGGAN was trained in batchsize=64 and cost 16GB GPU memory. It needs only 10000 steps for training.
The BIGGAN was trained in batchsize=64 and cost 16GB GPU memory (batchsize=32 cost 10GB GPU memory for 1080Ti). It needs only 10000 steps for training.

### results

SAGAN 61600 steps

![61600 steps](pictures/fake_steps_61600.jpg)

BIGGAN 12600 steps
state-of-art BIGGAN 12600 steps

![12600 steps](pictures/fake_steps_12600.jpg)

GIF

![gif](pictures/GanGIF.gif)

SAGAN 61600 steps (without the residual structure)

![61600 steps](pictures/fake_steps_61600.jpg)

### Open sourced dataset
We decide to opensource our used datasets.

Expand Down