當前位置: 首頁>>編程示例 >>用法及示例精選 >>正文


Tensorflow.js tf.layers getWeights()用法及代碼示例

Tensorflow.js是Google開發的開源庫,用於在瀏覽器或節點環境中運行機器學習模型和深度學習神經網絡。它還可以幫助開發人員使用JavaScript語言開發ML模型,並可以直接在瀏覽器或Node.js中使用ML。

tf.layers.Layer.getWeights() 函數用於獲取張量的權重值。

用法:

getWeights( trainableOnly? )

參數:

  • trainableOnly(boolean):如果為 true,該函數將僅返回可訓練的權重值。

返回值:它返回一個 tf.Tensor



範例1:

Javascript


// Creating a model
const model = tf.sequential();
  
// Adding layers
model.add(tf.layers.dense({units:2, inputShape:[5]}));
model.add(tf.layers.dense({units:3}));
  
model.compile({loss:'categoricalCrossentropy', optimizer:'sgd'});
  
// Printing the weights of the layers
model.layers[0].getWeights()[0].print()
model.layers[0].getWeights()[1].print()

輸出:

Tensor
    [[-0.4756567, 0.2925433 ],
     [0.3505997 , -0.5043278],
     [0.5344347 , 0.2662918 ],
     [-0.1357223, 0.2435055 ],
     [-0.6059403, 0.1990891 ]]
Tensor
    [0, 0]

範例2:

Javascript


const tf = require("@tensorflow/tfjs")
  
// Creating a model
const model = tf.sequential();
  
// Adding layers
model.add(tf.layers.dense({units:1, inputShape:[10]}));
model.add(tf.layers.dense({units:3}));
  
// Setting new weights
model.layers[0].setWeights([tf.zeros([10, 1]), tf.ones([1])]);
  
model.compile({loss:'categoricalCrossentropy', optimizer:'sgd'});
  
// Printing the weights of the layers
model.layers[0].getWeights()[0].print()
model.layers[0].getWeights()[1].print()

輸出:

Tensor
    [[0],
     [0],
     [0],
     [0],
     [0],
     [0],
     [0],
     [0],
     [0],
     [0]]
Tensor
    [1]

參考:https://js.tensorflow.org/api/latest/#tf.layers.Layer.getWeights




相關用法


注:本文由純淨天空篩選整理自parasmadan15大神的英文原創作品 Tensorflow.js tf.layers getWeights() Method。非經特殊聲明,原始代碼版權歸原作者所有,本譯文未經允許或授權,請勿轉載或複製。