擅长:python、mysql、java
<pre><code>from sklearn.preprocessing import StandardScaler
n_cols = X_train.shape[1]
ss = StandardScaler()
X_train = ss.fit_transform(X_train)
model = Sequential()
model.add(Dense(128, activation='relu', input_shape=(n_cols,)))
model.add(Dense(64, activation='relu'))
model.add(Dense(16, activation='relu'))
model.add(Dense(1))
model.compile(loss='mean_squared_error',
optimizer='Adam',
metrics=['mean_squared_error'])
model.fit(X_train, y_train,
epochs=50,
validation_split=0.2,
batch_size=20)
</code></pre>
<ul>
<li>规范化数据</li>
<li>为您的人际网络添加更多深度</li>
<li>使最后一层线性化</li>
</ul>
<p><strong>准确度</strong>不是回归的好指标。让我们看一个例子</p>
<pre><code>predictions: [0.9999999, 2.0000001, 3.000001]
ground Truth: [1, 2, 3]
Accuracy = No:of Correct / Total => 0 /3 = 0
</code></pre>
<p>准确度是<code>0</code>,但是预测非常接近实际情况。另一方面,均方误差将非常低,即预测值与地面真实值的偏差非常小。你知道吗</p>