Skip to content

Added Style Scale #5

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

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Added Style Scale #5

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
63de829
added style scale feature
ryletko Jan 17, 2021
6361aa6
removed parentheses
ryletko Jan 17, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion neural_style_transfer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,7 @@ def neural_style_transfer(config):
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

content_img = utils.prepare_img(content_img_path, config['height'], device)
style_img = utils.prepare_img(style_img_path, config['height'], device)
style_img = utils.prepare_img(style_img_path, int(config['height'] * config['style_scale']), device)

if config['init_method'] == 'random':
# white_noise_img = np.random.uniform(-90., 90., content_img.shape).astype(np.float32)
Expand Down Expand Up @@ -152,6 +152,8 @@ def closure():
parser.add_argument("--model", type=str, choices=['vgg16', 'vgg19'], default='vgg19')
parser.add_argument("--init_method", type=str, choices=['random', 'content', 'style'], default='content')
parser.add_argument("--saving_freq", type=int, help="saving frequency for intermediate images (-1 means only final)", default=-1)
parser.add_argument("--style_scale", type=float, help="style scale (1 means no scale)", default=1)

args = parser.parse_args()

# some values of weights that worked for figures.jpg, vg_starry_night.jpg (starting point for finding good images)
Expand Down