change predict and sort process

eda/esmm/Model_pipline/train.py

@@ -59,14 +59,10 @@ def input_fn(filenames, batch_size=32, num_epochs=1, perform_shuffle=False):
             "tag6_list": tf.VarLenFeature(tf.int64),
             "tag7_list": tf.VarLenFeature(tf.int64),
             "search_tag2_list": tf.VarLenFeature(tf.int64),
-<<<<<<< HEAD
             "search_tag3_list": tf.VarLenFeature(tf.int64),
             "uid": tf.VarLenFeature(tf.string),
             "city": tf.VarLenFeature(tf.string),
             "cid_id": tf.VarLenFeature(tf.string)
-=======
-            "search_tag3_list": tf.VarLenFeature(tf.int64)
->>>>>>> 6219b3d856f8bfae4b542ea25d6ffb4209e193ad
         }
         parsed = tf.parse_single_example(record, features)
         y = parsed.pop('y')
@@ -135,13 +131,10 @@ def model_fn(features, labels, mode, params):
     tag7_list = features['tag7_list']
     search_tag2_list = features['search_tag2_list']
     search_tag3_list = features['search_tag3_list']
-<<<<<<< HEAD
     uid = features['uid']
     city = features['city']
     cid_id = features['cid_id']
 
-=======
->>>>>>> 6219b3d856f8bfae4b542ea25d6ffb4209e193ad
 
     if FLAGS.task_type != "infer":
         y = labels['y']
@@ -167,13 +160,10 @@ 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,
                               tag2, tag3, tag4, tag5, tag6, tag7,search_tag2,search_tag3], axis=1)
-<<<<<<< HEAD
 
         uid = tf.sparse.to_dense(uid,default_value="")
         city = tf.sparse.to_dense(city,default_value="")
         cid_id = tf.sparse.to_dense(cid_id,default_value="")
-=======
->>>>>>> 6219b3d856f8bfae4b542ea25d6ffb4209e193ad
 
     with tf.name_scope("CVR_Task"):
         if mode == tf.estimator.ModeKeys.TRAIN: