[英]Are the weights of a pre-trained Tensorflow model that has been ported to TensorFlow.js accessible at runtime through the model object?
如何在调试期间访问模型的权重？
当我在调试器中执行期间检查model.model.weights['dense_3/bias'][0]时，实际权重不存在。 但是，当我console.log ，会打印出权重的表达式。 似乎正在进行某种延迟执行？
我在下面创建了一个基于有毒分类器媒体文章的片段，该文章展示了如何访问特定层的权重对象。
const threshold = 0.9; // Which toxicity labels to return. const labelsToInclude = ['identity_attack', 'insult', 'threat']; toxicity.load(threshold, labelsToInclude).then(model => { // Now you can use the `model` object to label sentences. model.classify(['you suck']).then(predictions => { console.log("Specific weights: "+ model.model.weights['dense_3/bias'][0]) document.getElementById("predictions").innerHTML = JSON.stringify(predictions, null, 2); }); });
<!DOCTYPE html> <html lang="en-us"> <head> <meta charset="UTF-8"> <title>Activity 1: Basic HTML Bio</title> <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs@1.0"></script> <script src="https://cdn.jsdelivr.net/npm/@tensorflow-models/toxicity"></script> </head> <body> <div id="predictions"> Will be populated by prebuilt toxicity model </div> </body> </html>
张量数组中的每一层。 可以通过迭代数组来访问层的权重。
const t = model.model.weights['dense_3/bias'][0] // t is a tensor
t.print() // will display the tensor in the console
// to add value to the weight
t.add(tf.scalar(0.5))
console.log(model.model.weights['dense_3/bias'][0]) 将显示一个对象而不是张量的值。 原因是张量是 TypeScript 中的一个类，它在 js 中被转译为Function类型的对象。 这就是为什么console.log(model.model.weights['dense_3/bias'][0])将打印一个对象，其键是类张量的属性。 需要调用print方法来查看张量的底层值
const threshold = 0.9; // Which toxicity labels to return. const labelsToInclude = ['identity_attack', 'insult', 'threat']; toxicity.load(threshold, labelsToInclude).then(model => { // print weights model.model.weights['dense_3/bias'][0].print() // continue processing });
<!DOCTYPE html> <html lang="en-us"> <head> <meta charset="UTF-8"> <title>Activity 1: Basic HTML Bio</title> <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs@1.0"></script> <script src="https://cdn.jsdelivr.net/npm/@tensorflow-models/toxicity"></script> </head> <body> </body> </html>
从另一篇文章中，我能够推导出如何访问权重。
对于每一层，都有一个data承诺可以访问权重。
const threshold = 0.9; // Which toxicity labels to return. const labelsToInclude = ['identity_attack', 'insult', 'threat']; toxicity.load(threshold, labelsToInclude).then(model => { // Now you can use the `model` object to label sentences. model.classify(['you suck']).then(predictions => { model.model.weights['dense_3/bias'][0].data().then( function(value) { document.getElementById("specific_weights").innerHTML = JSON.stringify(value); }); document.getElementById("predictions").innerHTML = JSON.stringify(predictions, null, 2); }); });
<!DOCTYPE html> <html lang="en-us"> <head> <meta charset="UTF-8"> <title>Activity 1: Basic HTML Bio</title> <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs@1.0"></script> <script src="https://cdn.jsdelivr.net/npm/@tensorflow-models/toxicity"></script> </head> <body> <div id="predictions"> Will be populated by prebuilt toxicity model </div> <div id="specific_weights"> Will contain weights for specific layer </div> </body> </html>
如何在 Tensorflow.js 中保护（混淆/DRM）训练模型权重？
[英]How to protect (obfuscate/DRM) trained model weights in Tensorflow.js?
无法通过在tensorflow.js中加载预训练的模型（loadLayersModel）进行预测
[英]Unable to predict by loading pre-trained models(loadLayersModel) in tensorflow.js
如何将 tensorflow.js model 权重转换为 pytorch 张量，然后返回？
[英]How to convert tensorflow.js model weights to pytorch tensors, and back?
尝试将TensorFlow保存模型转换为TensorFlow.js模型时出错
[英]Error Trying to Convert TensorFlow Saved Model to TensorFlow.js Model
声明:本站的技术帖子网页，遵循CC BY-SA 4.0协议，如果您需要转载，请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.