最小化 tensorflow.js 中前馈神经网络的损失

•浏览 1

minimizing loss in tensorflow.js for feed forward neural network

我正在尝试在 tensorflow.js 中创建一个示例前馈神经网络，最初使用一个小数据集(仅用于 POC)。有 5 个输入节点和 1 个输出节点。数据与有多个输入的住房相关，我们正在预测价格。

x_train:

[ [ 79545.45857, 5.682861322, 7.009188143, 4.09, 23086.8005 ],

 [ 79248.64245, 6.002899808, 6.730821019, 3.09, 40173.07217 ],

 [ 61287.06718, 5.86588984, 8.51272743, 5.13, 36882.1594 ],

 [ 63345.24005, 7.188236095, 5.586728665, 3.26, 34310.24283 ],

 [ 59982.19723, 5.040554523, 7.839387785, 4.23, 26354.10947 ],

...

] 



y_train

[ [ 1059033.558 ],

 [ 1505890.915 ],

 [ 1058987.988 ],

 [ 1260616.807 ],

 [ 630943.4893 ],

...

]



const model = tf.sequential();

const config_hidden = {

    inputShape: [5],

    activation: 'sigmoid',

    units: 6

  }



const config_output = {

  units: 1,

  activation: 'sigmoid'

}



const hidden = tf.layers.dense(config_hidden);

const output = tf.layers.dense(config_output);



model.add(hidden);

model.add(output);



const optimizer = tf.train.sgd(0.5);



const config = {

  optimizer: optimizer,

  loss: 'meanSquaredError',

  metrics: ['accuracy']

}



model.compile(config);



train_data().then(function () {

  console.log('Training is Complete');

}



async function train_data() {

  const options = {

    shuffle: true,

    epochs: 10,

    batch_size: 100,

    validationSplit: 0.1

  }



  for (let i = 0; i < 10; i++) {

    const res = await model.fit(xs, ys, options);

    console.log(res.history.loss[0]);

  }

}Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

1058ms 235us/step - acc=0.00 loss=1648912629760.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 2 / 10

eta=0.0 ====================================================================>

700ms 156us/step - acc=0.00 loss=1648913285120.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 3 / 10

eta=0.0 ====================================================================>

615ms 137us/step - acc=0.00 loss=1648913022976.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 4 / 10

eta=0.0 ====================================================================>

852ms 189us/step - acc=0.00 loss=1648913285120.00 val_acc=0.00 val_loss=1586459705344.00xs = xs.div(xs.mean(0));



x_train

[[1.1598413, 0.9507535, 1.003062 , 1.0272969, 0.6384002],

  [1.1555134, 1.0042965, 0.9632258, 0.7761241, 1.1108726],

  [0.8936182, 0.9813745, 1.2182286, 1.2885166, 1.0198718],

  ...,Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

841ms 187us/step - acc=0.00 loss=1648912760832.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 2 / 10

eta=0.0 ====================================================================>

613ms 136us/step - acc=0.00 loss=1648913154048.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 3 / 10

eta=0.0 ====================================================================>

646ms 144us/step - acc=0.00 loss=1648913022976.00 val_acc=0.00 val_loss=1586459705344.00ys = ys.div(1000000);



Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

899ms 200us/step - acc=0.00 loss=0.202 val_acc=0.00 val_loss=0.161

Epoch 2 / 10

eta=0.0 ====================================================================>

667ms 148us/step - acc=0.00 loss=0.183 val_acc=0.00 val_loss=0.160

Epoch 3 / 10

eta=0.0 ====================================================================>

609ms 135us/step - acc=0.00 loss=0.182 val_acc=0.00 val_loss=0.159Epoch 8 / 10

eta=0.0 ====================================================================>

502ms 112us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

Epoch 9 / 10

eta=0.0 ====================================================================>

551ms 122us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

Epoch 10 / 10

eta=0.0 ====================================================================>

470ms 104us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

0.18076679110527039

模型编译良好。但是训练模型时的损失是巨大的

x_train:

[ [ 79545.45857, 5.682861322, 7.009188143, 4.09, 23086.8005 ],

 [ 79248.64245, 6.002899808, 6.730821019, 3.09, 40173.07217 ],

 [ 61287.06718, 5.86588984, 8.51272743, 5.13, 36882.1594 ],

 [ 63345.24005, 7.188236095, 5.586728665, 3.26, 34310.24283 ],

 [ 59982.19723, 5.040554523, 7.839387785, 4.23, 26354.10947 ],

...

] 



y_train

[ [ 1059033.558 ],

 [ 1505890.915 ],

 [ 1058987.988 ],

 [ 1260616.807 ],

 [ 630943.4893 ],

...

]



const model = tf.sequential();

const config_hidden = {

    inputShape: [5],

    activation: 'sigmoid',

    units: 6

  }



const config_output = {

  units: 1,

  activation: 'sigmoid'

}



const hidden = tf.layers.dense(config_hidden);

const output = tf.layers.dense(config_output);



model.add(hidden);

model.add(output);



const optimizer = tf.train.sgd(0.5);



const config = {

  optimizer: optimizer,

  loss: 'meanSquaredError',

  metrics: ['accuracy']

}



model.compile(config);



train_data().then(function () {

  console.log('Training is Complete');

}



async function train_data() {

  const options = {

    shuffle: true,

    epochs: 10,

    batch_size: 100,

    validationSplit: 0.1

  }



  for (let i = 0; i < 10; i++) {

    const res = await model.fit(xs, ys, options);

    console.log(res.history.loss[0]);

  }

}Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

1058ms 235us/step - acc=0.00 loss=1648912629760.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 2 / 10

eta=0.0 ====================================================================>

700ms 156us/step - acc=0.00 loss=1648913285120.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 3 / 10

eta=0.0 ====================================================================>

615ms 137us/step - acc=0.00 loss=1648913022976.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 4 / 10

eta=0.0 ====================================================================>

852ms 189us/step - acc=0.00 loss=1648913285120.00 val_acc=0.00 val_loss=1586459705344.00xs = xs.div(xs.mean(0));



x_train

[[1.1598413, 0.9507535, 1.003062 , 1.0272969, 0.6384002],

  [1.1555134, 1.0042965, 0.9632258, 0.7761241, 1.1108726],

  [0.8936182, 0.9813745, 1.2182286, 1.2885166, 1.0198718],

  ...,Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

841ms 187us/step - acc=0.00 loss=1648912760832.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 2 / 10

eta=0.0 ====================================================================>

613ms 136us/step - acc=0.00 loss=1648913154048.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 3 / 10

eta=0.0 ====================================================================>

646ms 144us/step - acc=0.00 loss=1648913022976.00 val_acc=0.00 val_loss=1586459705344.00ys = ys.div(1000000);



Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

899ms 200us/step - acc=0.00 loss=0.202 val_acc=0.00 val_loss=0.161

Epoch 2 / 10

eta=0.0 ====================================================================>

667ms 148us/step - acc=0.00 loss=0.183 val_acc=0.00 val_loss=0.160

Epoch 3 / 10

eta=0.0 ====================================================================>

609ms 135us/step - acc=0.00 loss=0.182 val_acc=0.00 val_loss=0.159Epoch 8 / 10

eta=0.0 ====================================================================>

502ms 112us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

Epoch 9 / 10

eta=0.0 ====================================================================>

551ms 122us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

Epoch 10 / 10

eta=0.0 ====================================================================>

470ms 104us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

0.18076679110527039

我认为这可能是因为训练数据未标准化。所以我取数据的平均值并对其进行划分

x_train:

[ [ 79545.45857, 5.682861322, 7.009188143, 4.09, 23086.8005 ],

 [ 79248.64245, 6.002899808, 6.730821019, 3.09, 40173.07217 ],

 [ 61287.06718, 5.86588984, 8.51272743, 5.13, 36882.1594 ],

 [ 63345.24005, 7.188236095, 5.586728665, 3.26, 34310.24283 ],

 [ 59982.19723, 5.040554523, 7.839387785, 4.23, 26354.10947 ],

...

] 



y_train

[ [ 1059033.558 ],

 [ 1505890.915 ],

 [ 1058987.988 ],

 [ 1260616.807 ],

 [ 630943.4893 ],

...

]



const model = tf.sequential();

const config_hidden = {

    inputShape: [5],

    activation: 'sigmoid',

    units: 6

  }



const config_output = {

  units: 1,

  activation: 'sigmoid'

}



const hidden = tf.layers.dense(config_hidden);

const output = tf.layers.dense(config_output);



model.add(hidden);

model.add(output);



const optimizer = tf.train.sgd(0.5);



const config = {

  optimizer: optimizer,

  loss: 'meanSquaredError',

  metrics: ['accuracy']

}



model.compile(config);



train_data().then(function () {

  console.log('Training is Complete');

}



async function train_data() {

  const options = {

    shuffle: true,

    epochs: 10,

    batch_size: 100,

    validationSplit: 0.1

  }



  for (let i = 0; i < 10; i++) {

    const res = await model.fit(xs, ys, options);

    console.log(res.history.loss[0]);

  }

}Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

1058ms 235us/step - acc=0.00 loss=1648912629760.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 2 / 10

eta=0.0 ====================================================================>

700ms 156us/step - acc=0.00 loss=1648913285120.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 3 / 10

eta=0.0 ====================================================================>

615ms 137us/step - acc=0.00 loss=1648913022976.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 4 / 10

eta=0.0 ====================================================================>

852ms 189us/step - acc=0.00 loss=1648913285120.00 val_acc=0.00 val_loss=1586459705344.00xs = xs.div(xs.mean(0));



x_train

[[1.1598413, 0.9507535, 1.003062 , 1.0272969, 0.6384002],

  [1.1555134, 1.0042965, 0.9632258, 0.7761241, 1.1108726],

  [0.8936182, 0.9813745, 1.2182286, 1.2885166, 1.0198718],

  ...,Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

841ms 187us/step - acc=0.00 loss=1648912760832.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 2 / 10

eta=0.0 ====================================================================>

613ms 136us/step - acc=0.00 loss=1648913154048.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 3 / 10

eta=0.0 ====================================================================>

646ms 144us/step - acc=0.00 loss=1648913022976.00 val_acc=0.00 val_loss=1586459705344.00ys = ys.div(1000000);



Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

899ms 200us/step - acc=0.00 loss=0.202 val_acc=0.00 val_loss=0.161

Epoch 2 / 10

eta=0.0 ====================================================================>

667ms 148us/step - acc=0.00 loss=0.183 val_acc=0.00 val_loss=0.160

Epoch 3 / 10

eta=0.0 ====================================================================>

609ms 135us/step - acc=0.00 loss=0.182 val_acc=0.00 val_loss=0.159Epoch 8 / 10

eta=0.0 ====================================================================>

502ms 112us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

Epoch 9 / 10

eta=0.0 ====================================================================>

551ms 122us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

Epoch 10 / 10

eta=0.0 ====================================================================>

470ms 104us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

0.18076679110527039

损失变化不大

x_train:

[ [ 79545.45857, 5.682861322, 7.009188143, 4.09, 23086.8005 ],

 [ 79248.64245, 6.002899808, 6.730821019, 3.09, 40173.07217 ],

 [ 61287.06718, 5.86588984, 8.51272743, 5.13, 36882.1594 ],

 [ 63345.24005, 7.188236095, 5.586728665, 3.26, 34310.24283 ],

 [ 59982.19723, 5.040554523, 7.839387785, 4.23, 26354.10947 ],

...

] 



y_train

[ [ 1059033.558 ],

 [ 1505890.915 ],

 [ 1058987.988 ],

 [ 1260616.807 ],

 [ 630943.4893 ],

...

]



const model = tf.sequential();

const config_hidden = {

    inputShape: [5],

    activation: 'sigmoid',

    units: 6

  }



const config_output = {

  units: 1,

  activation: 'sigmoid'

}



const hidden = tf.layers.dense(config_hidden);

const output = tf.layers.dense(config_output);



model.add(hidden);

model.add(output);



const optimizer = tf.train.sgd(0.5);



const config = {

  optimizer: optimizer,

  loss: 'meanSquaredError',

  metrics: ['accuracy']

}



model.compile(config);



train_data().then(function () {

  console.log('Training is Complete');

}



async function train_data() {

  const options = {

    shuffle: true,

    epochs: 10,

    batch_size: 100,

    validationSplit: 0.1

  }



  for (let i = 0; i < 10; i++) {

    const res = await model.fit(xs, ys, options);

    console.log(res.history.loss[0]);

  }

}Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

1058ms 235us/step - acc=0.00 loss=1648912629760.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 2 / 10

eta=0.0 ====================================================================>

700ms 156us/step - acc=0.00 loss=1648913285120.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 3 / 10

eta=0.0 ====================================================================>

615ms 137us/step - acc=0.00 loss=1648913022976.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 4 / 10

eta=0.0 ====================================================================>

852ms 189us/step - acc=0.00 loss=1648913285120.00 val_acc=0.00 val_loss=1586459705344.00xs = xs.div(xs.mean(0));



x_train

[[1.1598413, 0.9507535, 1.003062 , 1.0272969, 0.6384002],

  [1.1555134, 1.0042965, 0.9632258, 0.7761241, 1.1108726],

  [0.8936182, 0.9813745, 1.2182286, 1.2885166, 1.0198718],

  ...,Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

841ms 187us/step - acc=0.00 loss=1648912760832.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 2 / 10

eta=0.0 ====================================================================>

613ms 136us/step - acc=0.00 loss=1648913154048.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 3 / 10

eta=0.0 ====================================================================>

646ms 144us/step - acc=0.00 loss=1648913022976.00 val_acc=0.00 val_loss=1586459705344.00ys = ys.div(1000000);



Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

899ms 200us/step - acc=0.00 loss=0.202 val_acc=0.00 val_loss=0.161

Epoch 2 / 10

eta=0.0 ====================================================================>

667ms 148us/step - acc=0.00 loss=0.183 val_acc=0.00 val_loss=0.160

Epoch 3 / 10

eta=0.0 ====================================================================>

609ms 135us/step - acc=0.00 loss=0.182 val_acc=0.00 val_loss=0.159Epoch 8 / 10

eta=0.0 ====================================================================>

502ms 112us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

Epoch 9 / 10

eta=0.0 ====================================================================>

551ms 122us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

Epoch 10 / 10

eta=0.0 ====================================================================>

470ms 104us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

0.18076679110527039

然后我也将输出标准化，

x_train:

[ [ 79545.45857, 5.682861322, 7.009188143, 4.09, 23086.8005 ],

 [ 79248.64245, 6.002899808, 6.730821019, 3.09, 40173.07217 ],

 [ 61287.06718, 5.86588984, 8.51272743, 5.13, 36882.1594 ],

 [ 63345.24005, 7.188236095, 5.586728665, 3.26, 34310.24283 ],

 [ 59982.19723, 5.040554523, 7.839387785, 4.23, 26354.10947 ],

...

] 



y_train

[ [ 1059033.558 ],

 [ 1505890.915 ],

 [ 1058987.988 ],

 [ 1260616.807 ],

 [ 630943.4893 ],

...

]



const model = tf.sequential();

const config_hidden = {

    inputShape: [5],

    activation: 'sigmoid',

    units: 6

  }



const config_output = {

  units: 1,

  activation: 'sigmoid'

}



const hidden = tf.layers.dense(config_hidden);

const output = tf.layers.dense(config_output);



model.add(hidden);

model.add(output);



const optimizer = tf.train.sgd(0.5);



const config = {

  optimizer: optimizer,

  loss: 'meanSquaredError',

  metrics: ['accuracy']

}



model.compile(config);



train_data().then(function () {

  console.log('Training is Complete');

}



async function train_data() {

  const options = {

    shuffle: true,

    epochs: 10,

    batch_size: 100,

    validationSplit: 0.1

  }



  for (let i = 0; i < 10; i++) {

    const res = await model.fit(xs, ys, options);

    console.log(res.history.loss[0]);

  }

}Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

1058ms 235us/step - acc=0.00 loss=1648912629760.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 2 / 10

eta=0.0 ====================================================================>

700ms 156us/step - acc=0.00 loss=1648913285120.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 3 / 10

eta=0.0 ====================================================================>

615ms 137us/step - acc=0.00 loss=1648913022976.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 4 / 10

eta=0.0 ====================================================================>

852ms 189us/step - acc=0.00 loss=1648913285120.00 val_acc=0.00 val_loss=1586459705344.00xs = xs.div(xs.mean(0));



x_train

[[1.1598413, 0.9507535, 1.003062 , 1.0272969, 0.6384002],

  [1.1555134, 1.0042965, 0.9632258, 0.7761241, 1.1108726],

  [0.8936182, 0.9813745, 1.2182286, 1.2885166, 1.0198718],

  ...,Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

841ms 187us/step - acc=0.00 loss=1648912760832.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 2 / 10

eta=0.0 ====================================================================>

613ms 136us/step - acc=0.00 loss=1648913154048.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 3 / 10

eta=0.0 ====================================================================>

646ms 144us/step - acc=0.00 loss=1648913022976.00 val_acc=0.00 val_loss=1586459705344.00ys = ys.div(1000000);



Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

899ms 200us/step - acc=0.00 loss=0.202 val_acc=0.00 val_loss=0.161

Epoch 2 / 10

eta=0.0 ====================================================================>

667ms 148us/step - acc=0.00 loss=0.183 val_acc=0.00 val_loss=0.160

Epoch 3 / 10

eta=0.0 ====================================================================>

609ms 135us/step - acc=0.00 loss=0.182 val_acc=0.00 val_loss=0.159Epoch 8 / 10

eta=0.0 ====================================================================>

502ms 112us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

Epoch 9 / 10

eta=0.0 ====================================================================>

551ms 122us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

Epoch 10 / 10

eta=0.0 ====================================================================>

470ms 104us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

0.18076679110527039

这将损失降至十进制数字。然而可以看出，即使在训练数据上运行 10000 次迭代也不会显着减少损失。例如

x_train:

[ [ 79545.45857, 5.682861322, 7.009188143, 4.09, 23086.8005 ],

 [ 79248.64245, 6.002899808, 6.730821019, 3.09, 40173.07217 ],

 [ 61287.06718, 5.86588984, 8.51272743, 5.13, 36882.1594 ],

 [ 63345.24005, 7.188236095, 5.586728665, 3.26, 34310.24283 ],

 [ 59982.19723, 5.040554523, 7.839387785, 4.23, 26354.10947 ],

...

] 



y_train

[ [ 1059033.558 ],

 [ 1505890.915 ],

 [ 1058987.988 ],

 [ 1260616.807 ],

 [ 630943.4893 ],

...

]



const model = tf.sequential();

const config_hidden = {

    inputShape: [5],

    activation: 'sigmoid',

    units: 6

  }



const config_output = {

  units: 1,

  activation: 'sigmoid'

}



const hidden = tf.layers.dense(config_hidden);

const output = tf.layers.dense(config_output);



model.add(hidden);

model.add(output);



const optimizer = tf.train.sgd(0.5);



const config = {

  optimizer: optimizer,

  loss: 'meanSquaredError',

  metrics: ['accuracy']

}



model.compile(config);



train_data().then(function () {

  console.log('Training is Complete');

}



async function train_data() {

  const options = {

    shuffle: true,

    epochs: 10,

    batch_size: 100,

    validationSplit: 0.1

  }



  for (let i = 0; i < 10; i++) {

    const res = await model.fit(xs, ys, options);

    console.log(res.history.loss[0]);

  }

}Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

1058ms 235us/step - acc=0.00 loss=1648912629760.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 2 / 10

eta=0.0 ====================================================================>

700ms 156us/step - acc=0.00 loss=1648913285120.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 3 / 10

eta=0.0 ====================================================================>

615ms 137us/step - acc=0.00 loss=1648913022976.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 4 / 10

eta=0.0 ====================================================================>

852ms 189us/step - acc=0.00 loss=1648913285120.00 val_acc=0.00 val_loss=1586459705344.00xs = xs.div(xs.mean(0));



x_train

[[1.1598413, 0.9507535, 1.003062 , 1.0272969, 0.6384002],

  [1.1555134, 1.0042965, 0.9632258, 0.7761241, 1.1108726],

  [0.8936182, 0.9813745, 1.2182286, 1.2885166, 1.0198718],

  ...,Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

841ms 187us/step - acc=0.00 loss=1648912760832.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 2 / 10

eta=0.0 ====================================================================>

613ms 136us/step - acc=0.00 loss=1648913154048.00 val_acc=0.00 val_loss=1586459705344.00

Epoch 3 / 10

eta=0.0 ====================================================================>

646ms 144us/step - acc=0.00 loss=1648913022976.00 val_acc=0.00 val_loss=1586459705344.00ys = ys.div(1000000);



Model Successfully Compiled

Epoch 1 / 10

eta=0.0 ====================================================================>

899ms 200us/step - acc=0.00 loss=0.202 val_acc=0.00 val_loss=0.161

Epoch 2 / 10

eta=0.0 ====================================================================>

667ms 148us/step - acc=0.00 loss=0.183 val_acc=0.00 val_loss=0.160

Epoch 3 / 10

eta=0.0 ====================================================================>

609ms 135us/step - acc=0.00 loss=0.182 val_acc=0.00 val_loss=0.159Epoch 8 / 10

eta=0.0 ====================================================================>

502ms 112us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

Epoch 9 / 10

eta=0.0 ====================================================================>

551ms 122us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

Epoch 10 / 10

eta=0.0 ====================================================================>

470ms 104us/step - acc=0.00 loss=0.181 val_acc=0.00 val_loss=0.158

0.18076679110527039

最终损失从 0.202 左右开始下降到 0.180 左右。这会导致错误的预测。

这是一种非常常见的情况。具有不同范围值的多个输入(例如，上面使用的住房数据)。多个输入传递给前馈神经网络。预计只有一个输出(在这种情况下为价格)。

问题：

1.我在上面的代码中做错了什么？

2. 我是否以正确的方式规范化数据？

3. 我是否使用了正确的损失函数/优化器/学习率/激活等？

4.我如何知道模型是否表现良好

5. tensorflow.js 中有没有其他方法可以做到这一点？

我将假设您没有尝试线性回归，因为 Sigmoidal 激活。如果您正在尝试线性回归，请删除所有地方的 sigmoidal 激活。将尝试解决我能看到的所有错误：

  • 从输出中删除 sigmoid 激活。 sigmoid 函数将输入压缩到 0 到 1 之间，因此它不用于回归。您的最后一层不需要激活。

  • 你的学习率太高了，所以我怀疑学习算法能否收敛。从大约 0.001 - 0.01 等值开始，并根据需要进行调整。

  • 不，你没有正确规范化。通常，数据被归一化为均值为零和标准差为 1。这是针对每个特征列完成的，仅使用该列的平均值和标准差，而不是所有数据。例如特征列x中的i的公式如下：(x_i - x.mean()) / x.std()。 (我不懂 javascript)

  • 您提供的性能指标"准确度"用于分类，而不是回归，并且毫无意义(如果提供的话)。最小化均方误差或绝对平方误差是量化模型性能的最佳方法。

赞 (0)
« 上一篇
下一篇 »

相关推荐

  • Spring部署设置openshift

    Springdeploymentsettingsopenshift我有一个问题让我抓狂了三天。我根据OpenShift帐户上的教程部署了spring-eap6-quickstart代码。我已配置调试选项，并且已将Eclipse工作区与OpehShift服务器同步-服务器上的一切工作正常，但在Eclipse中出现无法消除的错误。我有这个错误：cvc-complex-type.2.4.a:Invali…
    2025-04-161

  • 检查Java中正则表达式中模式的第n次出现

    CheckfornthoccurrenceofpatterninregularexpressioninJava本问题已经有最佳答案，请猛点这里访问。我想使用Java正则表达式检查输入字符串中特定模式的第n次出现。你能建议怎么做吗？这应该可以工作：MatchResultfindNthOccurance(intn,Patternp,CharSequencesrc){Matcherm=p.matcher…
    2025-04-161

  • 如何让 JTable 停留在已编辑的单元格上

    HowtohaveJTablestayingontheeditedcell如果有人编辑JTable的单元格内容并按Enter，则内容会被修改并且表格选择会移动到下一行。是否可以禁止JTable在单元格编辑后转到下一行？原因是我的程序使用ListSelectionListener在单元格选择上同步了其他一些小部件，并且我不想在编辑当前单元格后选择下一行。Enter的默认绑定是名为selectNext…
    2025-04-161

  • Weblogic 12c 部署

    Weblogic12cdeploy我正在尝试将我的应用程序从Tomcat迁移到Weblogic12.2.1.3.0。我能够毫无错误地部署应用程序，但我遇到了与持久性提供程序相关的运行时错误。这是堆栈跟踪：javax.validation.ValidationException:CalltoTraversableResolver.isReachable()threwanexceptionatorg.…
    2025-04-161

  • Resteasy Content-Type 默认值

    ResteasyContent-Typedefaults我正在使用Resteasy编写一个可以返回JSON和XML的应用程序，但可以选择默认为XML。这是我的方法：@GET@Path("/content")@Produces({MediaType.APPLICATION_XML,MediaType.APPLICATION_JSON})publicStringcontentListRequestXm…
    2025-04-161

  • 代码不会停止运行，在 Java 中

    thecodedoesn'tstoprunning,inJava我正在用Java解决项目Euler中的问题10，即"Thesumoftheprimesbelow10is2+3+5+7=17.Findthesumofalltheprimesbelowtwomillion."我的代码是packageprojecteuler_1;importjava.math.BigInteger;importjava…
    2025-04-161

  • Out of memory java heap space

    Outofmemoryjavaheapspace我正在尝试将大量文件从服务器发送到多个客户端。当我尝试发送大小为700mb的文件时，它显示了"OutOfMemoryjavaheapspace"错误。我正在使用Netbeans7.1.2版本。我还在属性中尝试了VMoption。但仍然发生同样的错误。我认为阅读整个文件存在一些问题。下面的代码最多可用于300mb。请给我一些建议。提前致谢publicc…
    2025-04-161

  • Log4j 记录到共享日志文件

    Log4jLoggingtoaSharedLogFile有没有办法将log4j日志记录事件写入也被其他应用程序写入的日志文件。其他应用程序可以是非Java应用程序。有什么缺点？锁定问题？格式化？Log4j有一个SocketAppender，它将向服务发送事件，您可以自己实现或使用与Log4j捆绑的简单实现。它还支持syslogd和Windows事件日志，这对于尝试将日志输出与来自非Java应用程序…
    2025-04-161
手机版技术脚本