如何實現卷積神經網絡的L2正則化成本函數

Question

我已經實現了CNN數字分類模型。我的模型過度配合，爲了克服過度配合，我試圖在我的成本函數中使用L2 Regularization。我有一個小混亂 我怎麼能選擇<weights>把成本公式（代碼的最後一行）。

... 

x = tf.placeholder(tf.float32, shape=[None, img_size, img_size, num_channels], name='x') # Input 
y_true = tf.placeholder(tf.float32, shape=[None, num_classes], name='y_true') # Labels 

<Convolution Layer 1> 

<Convolution Layer 2> 

<Convolution Layer 3> 

<Fully Coonected 1> 

<Fully Coonected 2> O/P = layer_fc2 

# Loss Function 
lambda = 0.01 
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=layer_fc2, labels=y_true) 
# cost  = tf.reduce_mean(cross_entropy) # Nornmal Loss 
cost   = tf.reduce_mean(cross_entropy + lambda * tf.nn.l2_loss(<weights>)) # Regularized Loss 

... 

Answer 1

應定義L2損失相對於權重 - 使用該trainable_variables：

C = tf.nn.softmax_cross_entropy_with_logits(logits=layer_fc2, labels=y_true) 
l2_loss = tf.add_n([tf.nn.l2_loss(v) for v in tf.trainable_variables()]) 
C = C + lambda * l2_loss