fix esmm

models/multitask/esmm/config.yaml

@@ -12,40 +12,55 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-evaluate:
-  reader:
-    batch_size: 1
-    class: "{workspace}/esmm_infer_reader.py"
-    test_data_path: "{workspace}/data/train"
 
-train:
-  trainer:
-    # for cluster training
-    strategy: "async"
+workspace: "paddlerec.models.multitask.esmm"
 
-  epochs: 3
-  workspace: "paddlerec.models.multitask.esmm"
-  device: cpu
+dataset:
+- name: dataset_train
+  batch_size: 1
+  type: QueueDataset
+  data_path: "{workspace}/data/train"
+  data_converter: "{workspace}/esmm_reader.py"
+- name: dataset_infer
+  batch_size: 1
+  type: QueueDataset
+  data_path: "{workspace}/data/test"
+  data_converter: "{workspace}/esmm_reader.py"
 
-  reader:
-    batch_size: 2
-    class: "{workspace}/esmm_reader.py"
-    train_data_path: "{workspace}/data/train"
+hyper_parameters:
+  vocab_size: 10000
+  embed_size: 128
+  optimizer: 
+    class: adam
+    learning_rate: 0.001
+    strategy: async
 
-  model:
-    models: "{workspace}/model.py"
-    hyper_parameters:
-      vocab_size: 10000
-      embed_size: 128
-      learning_rate: 0.001
-      optimizer: adam
+#use infer_runner mode and modify 'phase' below if infer
+mode: train_runner
+#mode: infer_runner
+
+runner:
+- name: train_runner
+  class: single_train
+  device: cpu
+  epochs: 3
+  save_checkpoint_interval: 2
+  save_inference_interval: 4
+  save_checkpoint_path: "increment"
+  save_inference_path: "inference"
+  print_interval: 10
+- name: infer_runner
+  class: single_infer
+  init_model_path: "increment/0"
+  device: cpu
+  epochs: 3
 
-  save:
-    increment:
-      dirname: "increment"
-      epoch_interval: 2
-      save_last: True
-    inference:
-      dirname: "inference"
-      epoch_interval: 4
-      save_last: True
+phase:
+- name: train
+  model: "{workspace}/model.py"
+  dataset_name: dataset_train
+  thread_num: 1
+    #- name: infer
+    #  model: "{workspace}/model.py"
+    #  dataset_name: dataset_infer
+    #  thread_num: 1

models/multitask/esmm/esmm_reader.py

@@ -40,8 +40,6 @@ class TrainReader(Reader):
             This function needs to be implemented by the user, based on data format
             """
             features = line.strip().split(',')
-            # ctr = list(map(int, features[1]))
-            # cvr = list(map(int, features[2]))
             ctr = int(features[1])
             cvr = int(features[2])
 
@@ -54,7 +52,6 @@ class TrainReader(Reader):
                     continue
                 self.all_field_id_dict[field_id][0] = True
                 index = self.all_field_id_dict[field_id][1]
-                # feat_id = list(map(int, feat_id))
                 output[index][1].append(int(feat_id))
 
             for field_id in self.all_field_id_dict:

models/multitask/esmm/model.py

@@ -23,28 +23,11 @@ class Model(ModelBase):
     def __init__(self, config):
         ModelBase.__init__(self, config)
 
-    def fc(self, tag, data, out_dim, active='prelu'):
+    def _init_hyper_parameters(self):
+        self.vocab_size = envs.get_global_env("hyper_parameters.vocab_size")
+        self.embed_size = envs.get_global_env("hyper_parameters.embed_size")
 
-        init_stddev = 1.0
-        scales = 1.0 / np.sqrt(data.shape[1])
-
-        p_attr = fluid.param_attr.ParamAttr(
-            name='%s_weight' % tag,
-            initializer=fluid.initializer.NormalInitializer(
-                loc=0.0, scale=init_stddev * scales))
-
-        b_attr = fluid.ParamAttr(
-            name='%s_bias' % tag, initializer=fluid.initializer.Constant(0.1))
-
-        out = fluid.layers.fc(input=data,
-                              size=out_dim,
-                              act=active,
-                              param_attr=p_attr,
-                              bias_attr=b_attr,
-                              name=tag)
-        return out
-
-    def input_data(self):
+    def input_data(self, is_infer=False, **kwargs):
         sparse_input_ids = [
             fluid.data(
                 name="field_" + str(i),
@@ -55,26 +38,23 @@ class Model(ModelBase):
         label_ctr = fluid.data(name="ctr", shape=[-1, 1], dtype="int64")
         label_cvr = fluid.data(name="cvr", shape=[-1, 1], dtype="int64")
         inputs = sparse_input_ids + [label_ctr] + [label_cvr]
-        self._data_var.extend(inputs)
-
-        return inputs
+        if is_infer:
+            return inputs
+        else:
+            return inputs
 
     def net(self, inputs, is_infer=False):
 
-        vocab_size = envs.get_global_env("hyper_parameters.vocab_size", None,
-                                         self._namespace)
-        embed_size = envs.get_global_env("hyper_parameters.embed_size", None,
-                                         self._namespace)
         emb = []
         for data in inputs[0:-2]:
             feat_emb = fluid.embedding(
                 input=data,
-                size=[vocab_size, embed_size],
+                size=[self.vocab_size, self.embed_size],
                 param_attr=fluid.ParamAttr(
                     name='dis_emb',
                     learning_rate=5,
                     initializer=fluid.initializer.Xavier(
-                        fan_in=embed_size, fan_out=embed_size)),
+                        fan_in=self.embed_size, fan_out=self.embed_size)),
                 is_sparse=True)
             field_emb = fluid.layers.sequence_pool(
                 input=feat_emb, pool_type='sum')
@@ -83,14 +63,14 @@ class Model(ModelBase):
 
         # ctr
         active = 'relu'
-        ctr_fc1 = self.fc('ctr_fc1', concat_emb, 200, active)
-        ctr_fc2 = self.fc('ctr_fc2', ctr_fc1, 80, active)
-        ctr_out = self.fc('ctr_out', ctr_fc2, 2, 'softmax')
+        ctr_fc1 = self._fc('ctr_fc1', concat_emb, 200, active)
+        ctr_fc2 = self._fc('ctr_fc2', ctr_fc1, 80, active)
+        ctr_out = self._fc('ctr_out', ctr_fc2, 2, 'softmax')
 
         # cvr
-        cvr_fc1 = self.fc('cvr_fc1', concat_emb, 200, active)
-        cvr_fc2 = self.fc('cvr_fc2', cvr_fc1, 80, active)
-        cvr_out = self.fc('cvr_out', cvr_fc2, 2, 'softmax')
+        cvr_fc1 = self._fc('cvr_fc1', concat_emb, 200, active)
+        cvr_fc2 = self._fc('cvr_fc2', cvr_fc1, 80, active)
+        cvr_out = self._fc('cvr_out', cvr_fc2, 2, 'softmax')
 
         ctr_clk = inputs[-2]
         ctcvr_buy = inputs[-1]
@@ -127,15 +107,23 @@ class Model(ModelBase):
         self._metrics["AUC_ctcvr"] = auc_ctcvr
         self._metrics["BATCH_AUC_ctcvr"] = batch_auc_ctcvr
 
-    def train_net(self):
-        input_data = self.input_data()
-        self.net(input_data)
-
-    def infer_net(self):
-        self._infer_data_var = self.input_data()
-        self._infer_data_loader = fluid.io.DataLoader.from_generator(
-            feed_list=self._infer_data_var,
-            capacity=64,
-            use_double_buffer=False,
-            iterable=False)
-        self.net(self._infer_data_var, is_infer=True)
+    def _fc(self, tag, data, out_dim, active='prelu'):
+
+        init_stddev = 1.0
+        scales = 1.0 / np.sqrt(data.shape[1])
+
+        p_attr = fluid.param_attr.ParamAttr(
+            name='%s_weight' % tag,
+            initializer=fluid.initializer.NormalInitializer(
+                loc=0.0, scale=init_stddev * scales))
+
+        b_attr = fluid.ParamAttr(
+            name='%s_bias' % tag, initializer=fluid.initializer.Constant(0.1))
+
+        out = fluid.layers.fc(input=data,
+                              size=out_dim,
+                              act=active,
+                              param_attr=p_attr,
+                              bias_attr=b_attr,
+                              name=tag)
+        return out