fix ncf

models/recall/ncf/config.yaml

@@ -12,42 +12,56 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-evaluate:
-  reader:
-    batch_size: 1
-    class: "{workspace}/movielens_infer_reader.py"
-    test_data_path: "{workspace}/data/test"
+workspace: "paddlerec.models.recall.ncf"
 
-train:
-  trainer:
-    # for cluster training
-    strategy: "async"
+dataset:
+- name: dataset_train
+  batch_size: 5
+  type: QueueDataset
+  data_path: "{workspace}/data/train"
+  data_converter: "{workspace}/movielens_reader.py"
+- name: dataset_infer
+  batch_size: 5
+  type: QueueDataset
+  data_path: "{workspace}/data/test"
+  data_converter: "{workspace}/movielens_infer_reader.py"
 
-  epochs: 3
-  workspace: "paddlerec.models.recall.ncf"
-  device: cpu
-
-  reader:
-    batch_size: 2
-    class: "{workspace}/movielens_reader.py"
-    train_data_path: "{workspace}/data/train"
-
-  model:
-    models: "{workspace}/model.py"
-    hyper_parameters:
+hyper_parameters:
   num_users: 6040
   num_items: 3706
   latent_dim: 8
   layers: [64, 32, 16, 8]
+  optimizer: 
+    class: adam
     learning_rate: 0.001
-      optimizer: adam
+    strategy: async
+
+#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/recall/ncf/model.py

@@ -24,7 +24,13 @@ class Model(ModelBase):
     def __init__(self, config):
         ModelBase.__init__(self, config)
 
-    def input_data(self, is_infer=False):
+    def _init_hyper_parameters(self):
+        self.num_users = envs.get_global_env("hyper_parameters.num_users")
+        self.num_items = envs.get_global_env("hyper_parameters.num_items")
+        self.latent_dim = envs.get_global_env("hyper_parameters.latent_dim")
+        self.layers = envs.get_global_env("hyper_parameters.layers")
+
+    def input_data(self, is_infer=False, **kwargs):
         user_input = fluid.data(
             name="user_input", shape=[-1, 1], dtype="int64", lod_level=0)
         item_input = fluid.data(
@@ -35,45 +41,35 @@ class Model(ModelBase):
             inputs = [user_input] + [item_input]
         else:
             inputs = [user_input] + [item_input] + [label]
-            self._data_var = inputs
 
         return inputs
 
     def net(self, inputs, is_infer=False):
 
-        num_users = envs.get_global_env("hyper_parameters.num_users", None,
-                                        self._namespace)
-        num_items = envs.get_global_env("hyper_parameters.num_items", None,
-                                        self._namespace)
-        latent_dim = envs.get_global_env("hyper_parameters.latent_dim", None,
-                                         self._namespace)
-        layers = envs.get_global_env("hyper_parameters.layers", None,
-                                     self._namespace)
-
-        num_layer = len(layers)  #Number of layers in the MLP
+        num_layer = len(self.layers)  #Number of layers in the MLP
 
         MF_Embedding_User = fluid.embedding(
             input=inputs[0],
-            size=[num_users, latent_dim],
+            size=[self.num_users, self.latent_dim],
             param_attr=fluid.initializer.Normal(
                 loc=0.0, scale=0.01),
             is_sparse=True)
         MF_Embedding_Item = fluid.embedding(
             input=inputs[1],
-            size=[num_items, latent_dim],
+            size=[self.num_items, self.latent_dim],
             param_attr=fluid.initializer.Normal(
                 loc=0.0, scale=0.01),
             is_sparse=True)
 
         MLP_Embedding_User = fluid.embedding(
             input=inputs[0],
-            size=[num_users, int(layers[0] / 2)],
+            size=[self.num_users, int(self.layers[0] / 2)],
             param_attr=fluid.initializer.Normal(
                 loc=0.0, scale=0.01),
             is_sparse=True)
         MLP_Embedding_Item = fluid.embedding(
             input=inputs[1],
-            size=[num_items, int(layers[0] / 2)],
+            size=[self.num_items, int(self.layers[0] / 2)],
             param_attr=fluid.initializer.Normal(
                 loc=0.0, scale=0.01),
             is_sparse=True)
@@ -94,7 +90,7 @@ class Model(ModelBase):
         for i in range(1, num_layer):
             mlp_vector = fluid.layers.fc(
                 input=mlp_vector,
-                size=layers[i],
+                size=self.layers[i],
                 act='relu',
                 param_attr=fluid.ParamAttr(
                     initializer=fluid.initializer.TruncatedNormal(
@@ -126,16 +122,3 @@ class Model(ModelBase):
 
         self._cost = avg_cost
         self._metrics["cost"] = avg_cost
-
-    def train_net(self):
-        input_data = self.input_data()
-        self.net(input_data)
-
-    def infer_net(self):
-        self._infer_data_var = self.input_data(is_infer=True)
-        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)

models/recall/ncf/movielens_infer_reader.py

@@ -19,7 +19,7 @@ from collections import defaultdict
 import numpy as np
 
 
-class EvaluateReader(Reader):
+class TrainReader(Reader):
     def init(self):
         pass