Optional
properties: TensorScriptPropertiesOptional
featureOptional
featureOptional
tf?: anyOptional
window_Optional
PAD?: stringOptional
initialOptional
initialRest
...args: any[]Optional
getOptional
idOptional
importedOptional
layersOptional
lossOptional
numberRest
...args: any[]Optional
xOptional
yPredicts new dependent variables
returns tensorflow prediction
Optional
layers?: DenseLayer[]Uses either cosineProximity or Eucledian distance to rank similarity
//weights = [ [1,2,3,], [1,2,2], [0,-1,3] ]
//labeledWeights = [ {car:[1,2,3,],tesla:[1,2,2],boat:[0,-1,3]}]
FeatureEmbeddingInstance.findSimilarFeatures(weights,{features:['car'], limit:2,}) //=>
{
car:[
{
comparedFeature: 'tesla',
proximity: -0.5087087154388428,
distance: 0.03015853278338909
},
{
comparedFeature: 'boat',
proximity: -0.3032159209251404,
distance: 0.036241017282009125
},
]
}
Adds dense layers to tensorflow classification model
independent variables
dependent variables
Optional
layers: TensorScriptLayersmodel dense layer parameters
Optional
addOptional
featureOptional
featureOptional
fixOptional
idOptional
inputOptional
numberConverts matrix of layer weights into labeled features
const weights = [
[1.5,1,4,1.6,3.5],
[4.3,3.2,5.5,6.5]
]
FeatureEmbeddingInstance.labelWeights(weights) //=>
weights = {
car:[1.5,1,4,1.6,3.5],
boat:[4.3,3.2,5.5,6.5]
}
Loads a saved tensoflow / keras model, this is an alias for
tensorflow model
https://www.tensorflow.org/js/guide/save_load#loading_a_tfmodel
tensorflow load model options
Returns prediction values from tensorflow model
predicted model values
new test independent variables
Uses tSNE to reduce dimensionality of features
const weights = [
[1.5,1,4,1.6,3.5],
[4.3,3.2,5.5,6.5]
]
FeatureEmbeddingInstance.reduceWeights(weights) //=>
[
[1,2],
[2,3],
]
Optional
options: anysaves a tensorflow model, this is an alias for
tensorflow model
https://www.tensorflow.org/js/guide/save_load#save_a_tfmodel
tensorflow save model options
Asynchronously trains tensorflow model
returns trained tensorflow model
independent variables
dependent variables
Optional
layers: DenseLayer[]array of model dense layer parameters
Optional
inputOptional
inputStatic
getOptional
tf?: anyOptional
window_Static
getOptional
PAD?: stringOptional
initialOptional
initialStatic
getReturns the shape of an input matrix
const input = [
[ 0, 1, ],
[ 1, 0, ],
];
TensorScriptModelInterface.getInputShape(input) // => [2,2]
returns the shape of a matrix (e.g. [2,2])
input matrix
Static
getStatic
reshapeReshapes an array
const array = [ 0, 1, 1, 0, ];
const shape = [2,2];
TensorScriptModelInterface.reshape(array,shape) // =>
[
[ 0, 1, ],
[ 1, 0, ],
];
returns a matrix with the defined shape
input array
shape array
use a corpus to generate features from an embedding layer with Tensorflow
Implements