Skip to content

Commit 15acafb

Browse files
authored
Merge pull request titu1994#34 from lininglouis/lininglouis
update examples of using denseNet in readme.md
2 parents da91065 + fff64d5 commit 15acafb

File tree

1 file changed

+2
-2
lines changed

1 file changed

+2
-2
lines changed

‎README.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -46,7 +46,7 @@ import densenet
4646
# 'th' dim-ordering or 'tf' dim-ordering
4747
image_dim = (3, 32, 32) or image_dim = (32, 32, 3)
4848
49-
model = densenet.DenseNet(nb_classes=10, img_dim=image_dim, depth=40, growth_rate=12,
49+
model = densenet.DenseNet(classes=10, input_shape=image_dim, depth=40, growth_rate=12,
5050
bottleneck=True, reduction=0.5)
5151
```
5252

@@ -59,7 +59,7 @@ import densenet
5959
# 'th' dim-ordering or 'tf' dim-ordering
6060
image_dim = (3, 224, 224) or image_dim = (224, 224, 3)
6161
62-
model = densenet.DenseNetImageNet121(image_dim)
62+
model = densenet.DenseNetImageNet121(input_shape=image_dim)
6363
```
6464

6565
Weights for the DenseNetImageNet121, DenseNetImageNet161 and DenseNetImageNet169 models are provided ([in the release tab](https://github.com/titu1994/DenseNet/releases)) and will be automatically downloaded when first called. They have been trained on ImageNet. The weights were ported from the repository https://github.com/flyyufelix/DenseNet-Keras.

0 commit comments

Comments
 (0)