diff options
| author | Cameron <cysmith1010@gmail.com> | 2016-10-20 12:58:51 -0600 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2016-10-20 12:58:51 -0600 |
| commit | dff0e16b9104cae053d9891689f656fd6d60de51 (patch) | |
| tree | 9504947e926d2ffc6e29a4029ba62691258a82fc /README.md | |
| parent | 5ce83127e824122765cfdff633b8ca062abfce69 (diff) | |
Changed default style weight to 1e4
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 2 |
1 files changed, 1 insertions, 1 deletions
@@ -245,7 +245,7 @@ python neural_style.py --video \ * `--init_img_type`: Image used to initialize the network. *Choices*: `content`, `random`, `style`. *Default*: `content` * `--max_size`: Maximum width or height of the input images. *Default*: `512` * `--content_weight`: Weight for the content loss function. *Default*: `5e0` -* `--style_weight`: Weight for the style loss function. *Default*: `1e3` +* `--style_weight`: Weight for the style loss function. *Default*: `1e4` * `--tv_weight`: Weight for the total variational loss function. *Default*: `1e-3` * `--temporal_weight`: Weight for the temporal loss function. *Default*: `2e2` * `--content_layers`: *Space-separated* VGG19 layer names used for the content image. *Default*: `conv4_2` |