tf.keras.applications.NASNetLarge

Instantiates a NASNet model in ImageNet mode.

tf.keras.applications.NASNetLarge(
    input_shape=None,
    include_top=True,
    weights='imagenet',
    input_tensor=None,
    pooling=None,
    classes=1000,
    classifier_activation='softmax'
)

Reference:

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.

input_shapeOptional shape tuple, only to be specified if include_top is False (otherwise the input shape has to be (331, 331, 3) for NASNetLarge. It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. (224, 224, 3) would be one valid value.
include_topWhether to include the fully-connected layer at the top of the network.
weightsNone (random initialization) or imagenet (ImageNet weights). For loading imagenet weights, input_shape should be (331, 331, 3)
input_tensorOptional Keras tensor (i.e. output of layers.Input()) to use as image input for the model.
poolingOptional pooling mode for feature extraction when include_top is False.

  • None means that the output of the model will be the 4D tensor output of the last convolutional layer.
  • avg means that global average pooling will be applied to the output of the last convolutional layer, and thus the output of the model will be a 2D tensor.
  • max means that global max pooling will be applied.
classesOptional number of classes to classify images into, only to be specified if include_top is True, and if no weights argument is specified.
classifier_activationA str or callable. The activation function to use on the "top" layer. Ignored unless include_top=True. Set classifier_activation=None to return the logits of the "top" layer. When loading pretrained weights, classifier_activation can only be None or "softmax".

A Keras model instance.