Instantiates the ResNet152 architecture.
View aliases
Main aliases
tf.keras.applications.resnet.ResNet152
See Migration guide for more details.
tf.compat.v1.keras.applications.ResNet152
, tf.compat.v1.keras.applications.resnet.ResNet152
tf.keras.applications.ResNet152(
include_top=True, weights='imagenet', input_tensor=None,
input_shape=None, pooling=None, classes=1000, **kwargs
)
Reference:
- Deep Residual Learning for Image Recognition (CVPR 2015)
Optionally loads weights pre-trained on ImageNet.
Note that the data format convention used by the model is
the one specified in your Keras config at ~/.keras/keras.json
.
Arguments | |
---|---|
include_
|
whether to include the fully-connected layer at the top of the network. |
weights
|
one of None (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
|
input_
|
optional Keras tensor (i.e. output of layers.Input() )
to use as image input for the model.
|
input_
|
optional shape tuple, only to be specified
if include_ is False (otherwise the input shape
has to be (224, (with 'channels_ data format)
or (3, (with 'channels_ data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 32.
E.g. (200, would be one valid value.
|
pooling
|
Optional pooling mode for feature extraction
when include_ is False .
|
classes
|
optional number of classes to classify images
into, only to be specified if include_top is True, and
if no weights argument is specified.
|
Returns | |
---|---|
A Keras model instance. |