Skip to content

F
ffm-baseline
Commit e5702665 authored by 张彦钊's avatar 张彦钊
Browse files
Options

把训练时里

parent bd61b0a9
Show whitespace changes
Inline Side-by-side
Showing with 6 additions and 6 deletions
eda/esmm/Model_pipline/train.py
View file @ e5702665
...@@ -158,7 +158,7 @@ def model_fn(features, labels, mode, params): ...@@ -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.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) tag2, tag3, tag4, tag5, tag6, tag7,search_tag2,search_tag3], axis=1)
uid = tf.sparse.to_dense(uid,default_value="") uid = tf.sparse.to_dense(uid,default_value="")
...@@ -173,7 +173,7 @@ def model_fn(features, labels, mode, params): ...@@ -173,7 +173,7 @@ def model_fn(features, labels, mode, params):
x_cvr = x_concat x_cvr = x_concat
for i in range(len(layers)): for i in range(len(layers)):
x_cvr = tf.contrib.layers.fully_connected(inputs=x_cvr, num_outputs=layers[i], \ 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: 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 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): ...@@ -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) 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, \ 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]) y_cvr = tf.reshape(y_cvr,shape=[-1])
with tf.name_scope("CTR_Task"): with tf.name_scope("CTR_Task"):
...@@ -193,7 +193,7 @@ def model_fn(features, labels, mode, params): ...@@ -193,7 +193,7 @@ def model_fn(features, labels, mode, params):
x_ctr = x_concat x_ctr = x_concat
for i in range(len(layers)): for i in range(len(layers)):
x_ctr = tf.contrib.layers.fully_connected(inputs=x_ctr, num_outputs=layers[i], \ 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: 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 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): ...@@ -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) 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, \ 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]) y_ctr = tf.reshape(y_ctr,shape=[-1])
with tf.variable_scope("MTL-Layer"): with tf.variable_scope("MTL-Layer"):
...@@ -223,7 +223,7 @@ def model_fn(features, labels, mode, params): ...@@ -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)) 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.nn.sigmoid_cross_entropy_with_logits(logits=y_ctcvr, labels=z))
cvr_loss = tf.reduce_mean(tf.losses.log_loss(predictions=pctcvr, 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('ctr_loss', ctr_loss)
tf.summary.scalar('cvr_loss', cvr_loss) tf.summary.scalar('cvr_loss', cvr_loss)
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment