Class NASNet
Neural Architecture Search Network (NASNet) models, with weights pre-trained on ImageNet. The default input size for the NASNetLarge model is 331x331 and for the NASNetMobile model is 224x224.
Implements
Inherited Members
Namespace: Keras.Applications
Assembly: Keras.dll
Syntax
public class NASNet : Base, IDisposable
Methods
| Improve this Doc View SourceDecodePredictions(NDarray, Int32)
Decodes the predictions.
Declaration
public ImageNetPrediction[] DecodePredictions(NDarray preds, int top = 3)
Parameters
Type | Name | Description |
---|---|---|
Numpy.NDarray | preds | The preds. |
System.Int32 | top | The top. |
Returns
Type | Description |
---|---|
ImageNetPrediction[] |
NASNetLarge(Shape, Boolean, String, NDarray, String, Int32)
NASNetLarge
Declaration
public static Model NASNetLarge(Shape input_shape = null, bool include_top = true, string weights = "imagenet", NDarray input_tensor = null, string pooling = "None", int classes = 1000)
Parameters
Type | Name | Description |
---|---|---|
Shape | input_shape | optional shape tuple, only to be specified if include_top is False (otherwise the input shape has to be (224, 224, 3) (with 'channels_last' data format) or (3, 224, 224) (with 'channels_first' data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. (200, 200, 3) would be one valid value. |
System.Boolean | include_top | optional shape tuple, only to be specified if include_top is False (otherwise the input shape has to be (224, 224, 3) (with 'channels_last' data format) or (3, 224, 224) (with 'channels_first' data format) for NASNetMobile or (331, 331, 3) (with 'channels_last' data format) or (3, 331, 331) (with 'channels_first' data format) for NASNetLarge. It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. (200, 200, 3) would be one valid value. |
System.String | weights | one of None (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. |
Numpy.NDarray | input_tensor | optional Keras tensor (i.e. output of layers.Input()) to use as image input for the model. |
System.String | pooling | optional 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. |
System.Int32 | 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
Type | Description |
---|---|
Model | A Keras model instance. |
NASNetMobile(Shape, Boolean, String, NDarray, String, Int32)
NASNetMobile
Declaration
public static Model NASNetMobile(Shape input_shape = null, bool include_top = true, string weights = "imagenet", NDarray input_tensor = null, string pooling = "None", int classes = 1000)
Parameters
Type | Name | Description |
---|---|---|
Shape | input_shape | optional shape tuple, only to be specified if include_top is False (otherwise the input shape has to be (224, 224, 3) (with 'channels_last' data format) or (3, 224, 224) (with 'channels_first' data format). It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. (200, 200, 3) would be one valid value. |
System.Boolean | include_top | optional shape tuple, only to be specified if include_top is False (otherwise the input shape has to be (224, 224, 3) (with 'channels_last' data format) or (3, 224, 224) (with 'channels_first' data format) for NASNetMobile or (331, 331, 3) (with 'channels_last' data format) or (3, 331, 331) (with 'channels_first' data format) for NASNetLarge. It should have exactly 3 inputs channels, and width and height should be no smaller than 32. E.g. (200, 200, 3) would be one valid value. |
System.String | weights | one of None (random initialization), 'imagenet' (pre-training on ImageNet), or the path to the weights file to be loaded. |
Numpy.NDarray | input_tensor | optional Keras tensor (i.e. output of layers.Input()) to use as image input for the model. |
System.String | pooling | optional 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. |
System.Int32 | 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
Type | Description |
---|---|
Model | A Keras model instance. |
PreprocessInput(NDarray)
Preprocesses the input.
Declaration
public NDarray PreprocessInput(NDarray x)
Parameters
Type | Name | Description |
---|---|---|
Numpy.NDarray | x | The input tensor. |
Returns
Type | Description |
---|---|
Numpy.NDarray |