把训练时里

eda/esmm/Model_pipline/train.py

@@ -158,7 +158,7 @@ def model_fn(features, labels, mode, params):
 
 
         # x_concat = tf.reshape(embedding_id,shape=[-1, common_dims])  # None * (F * K)
-        x_concat = tf.concat([tf.reshape(embedding_id, shape=[-1, common_dims]), app_id, level2, level3, tag1,
+        x_concat = tf.concat([tf.reshape(embedding_id, shape=[-1, common_dims]), app_id, levetf.nn.l1, level3, tag1,
                               tag2, tag3, tag4, tag5, tag6, tag7,search_tag2,search_tag3], axis=1)
 
         uid = tf.sparse.to_dense(uid,default_value="")
@@ -173,7 +173,7 @@ def model_fn(features, labels, mode, params):
         x_cvr = x_concat
         for i in range(len(layers)):
             x_cvr = tf.contrib.layers.fully_connected(inputs=x_cvr, num_outputs=layers[i], \
-                weights_regularizer=tf.contrib.layers.l2_regularizer(l2_reg), scope='cvr_mlp%d' % i)
+                weights_regularizer=tf.contrib.layers.l1_regularizer(l2_reg), scope='cvr_mlp%d' % i)
 
             if FLAGS.batch_norm:
                 x_cvr = batch_norm_layer(x_cvr, train_phase=train_phase, scope_bn='cvr_bn_%d' %i)       #放在RELU之后 https://github.com/ducha-aiki/caffenet-benchmark/blob/master/batchnorm.md#bn----before-or-after-relu
@@ -181,7 +181,7 @@ def model_fn(features, labels, mode, params):
                 x_cvr = tf.nn.dropout(x_cvr, keep_prob=dropout[i])                                  #Apply Dropout after all BN layers and set dropout=0.8(drop_ratio=0.2)
 
         y_cvr = tf.contrib.layers.fully_connected(inputs=x_cvr, num_outputs=1, activation_fn=tf.identity, \
-            weights_regularizer=tf.contrib.layers.l2_regularizer(l2_reg), scope='cvr_out')
+            weights_regularizer=tf.contrib.layers.l1_regularizer(l2_reg), scope='cvr_out')
         y_cvr = tf.reshape(y_cvr,shape=[-1])
 
     with tf.name_scope("CTR_Task"):
@@ -193,7 +193,7 @@ def model_fn(features, labels, mode, params):
         x_ctr = x_concat
         for i in range(len(layers)):
             x_ctr = tf.contrib.layers.fully_connected(inputs=x_ctr, num_outputs=layers[i], \
-                weights_regularizer=tf.contrib.layers.l2_regularizer(l2_reg), scope='ctr_mlp%d' % i)
+                weights_regularizer=tf.contrib.layers.l1_regularizer(l2_reg), scope='ctr_mlp%d' % i)
 
             if FLAGS.batch_norm:
                 x_ctr = batch_norm_layer(x_ctr, train_phase=train_phase, scope_bn='ctr_bn_%d' %i)       #放在RELU之后 https://github.com/ducha-aiki/caffenet-benchmark/blob/master/batchnorm.md#bn----before-or-after-relu
@@ -201,7 +201,7 @@ def model_fn(features, labels, mode, params):
                 x_ctr = tf.nn.dropout(x_ctr, keep_prob=dropout[i])                                  #Apply Dropout after all BN layers and set dropout=0.8(drop_ratio=0.2)
 
         y_ctr = tf.contrib.layers.fully_connected(inputs=x_ctr, num_outputs=1, activation_fn=tf.identity, \
-            weights_regularizer=tf.contrib.layers.l2_regularizer(l2_reg), scope='ctr_out')
+            weights_regularizer=tf.contrib.layers.l1_regularizer(l2_reg), scope='ctr_out')
         y_ctr = tf.reshape(y_ctr,shape=[-1])
 
     with tf.variable_scope("MTL-Layer"):
@@ -223,7 +223,7 @@ def model_fn(features, labels, mode, params):
         ctr_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=y_ctr, labels=y))
         #cvr_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=y_ctcvr, labels=z))
         cvr_loss = tf.reduce_mean(tf.losses.log_loss(predictions=pctcvr, labels=z))
-        loss = ctr_task_wgt * ctr_loss + (1  -ctr_task_wgt) * cvr_loss + l2_reg * tf.nn.l2_loss(Feat_Emb)
+        loss = ctr_task_wgt * ctr_loss + (1  -ctr_task_wgt) * cvr_loss + l2_reg * tf.nn.l1_loss(Feat_Emb)
 
         tf.summary.scalar('ctr_loss', ctr_loss)
         tf.summary.scalar('cvr_loss', cvr_loss)