fix dssm

models/match/dssm/config.yaml

@@ -11,44 +11,61 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-evaluate:
-  reader:
-    batch_size: 1
-    class: "{workspace}/synthetic_evaluate_reader.py"
-    test_data_path: "{workspace}/data/train"
- 
-train:
-  trainer:
-    # for cluster training
-    strategy: "async"
 
-  epochs: 4
-  workspace: "paddlerec.models.match.dssm"
+# 轮数
+epochs: 4
+# 设备
+device: cpu
+# 工作目录
+workspace: "paddlerec.models.match.dssm"
 
-  reader:
-    batch_size: 4
-    class: "{workspace}/synthetic_reader.py"
-    train_data_path: "{workspace}/data/train"
+# dataset列表
+dataset:
+- name: dataset_train # 名字，用来区分不同的dataset
+  batch_size: 4
+  type: QueueDataset
+  data_path: "{workspace}/data/train" # 数据路径
+  data_converter: "{workspace}/synthetic_reader.py"
+#- name: dataset_infer # 名字，用来区分不同的dataset
+#  batch_size: 1
+#  type: QueueDataset
+#  data_path: "{workspace}/data/train" # 数据路径
+#  data_converter: "{workspace}/synthetic_evaluate_reader.py"
 
-  model:
-    models: "{workspace}/model.py"
-    hyper_parameters:
-      TRIGRAM_D: 1000
-      NEG: 4
-      fc_sizes: [300, 300, 128]
-      fc_acts: ['tanh', 'tanh', 'tanh']
-      learning_rate: 0.01
-      optimizer: sgd
+# 超参数
+hyper_parameters:
+  #优化器
+  optimizer:
+    class: sgd
+    learning_rate: 0.01
+    strategy: async
+  # 用户自定义
+  TRIGRAM_D: 1000
+  NEG: 4
+  fc_sizes: [300, 300, 128]
+  fc_acts: ['tanh', 'tanh', 'tanh']
 
-  save:
-    increment:
-      dirname: "increment"
-      epoch_interval: 2
-      save_last: True
+# executor配置
+epoch:
+  name:
+  trainer_class: single
+  save_checkpoint_interval: 2 # 保存模型
+  save_inference_interval: 4 # 保存预测模型
+  save_checkpoint_path: "increment" # 保存模型路径
+  save_inference_path: "inference" # 保存预测模型路径
+  save_inference_feed_varnames: ["query", "doc_pos"] # 预测模型feed vars
+  save_inference_fetch_varnames: ["cos_sim_0.tmp_0"] # 预测模型 fetch vars
+  #init_model_path: "xxxx" # 加载模型
 
-    inference:
-      dirname: "inference"
-      epoch_interval: 4
-      feed_varnames: ["query", "doc_pos"]
-      fetch_varnames: ["cos_sim_0.tmp_0"]
-      save_last: True
+# 执行器，每轮要跑的所有模型
+executor:
+ - name: train
+   model: "{workspace}/model.py" # 模型路径
+   dataset_name: dataset_train # 名字，用来区分不同的阶段
+   thread_num: 1 # 线程数
+   is_infer: False # 是否是infer
+# - name: infer
+#   model: "{workspace}/model.py" # 模型路径
+#   dataset_name: dataset_infer # 名字，用来区分不同的阶段
+#   thread_num: 1 # 线程数
+#   is_infer: True # 是否是infer 

models/match/dssm/model.py

@@ -22,45 +22,35 @@ class Model(ModelBase):
     def __init__(self, config):
         ModelBase.__init__(self, config)
 
-    def input(self):
-        TRIGRAM_D = envs.get_global_env("hyper_parameters.TRIGRAM_D", None,
-                                        self._namespace)
-
-        Neg = envs.get_global_env("hyper_parameters.NEG", None,
-                                  self._namespace)
-
-        self.query = fluid.data(
-            name="query", shape=[-1, TRIGRAM_D], dtype='float32', lod_level=0)
-        self.doc_pos = fluid.data(
+    def _init_hyper_parameters(self):
+        self.TRIGRAM_D = envs.get_global_env("hyper_parameters.TRIGRAM_D")
+        self.Neg = envs.get_global_env("hyper_parameters.NEG")
+        self.hidden_layers = envs.get_global_env("hyper_parameters.fc_sizes")
+        self.hidden_acts = envs.get_global_env("hyper_parameters.fc_acts")
+        self.learning_rate = envs.get_global_env("hyper_parameters.learning_rate")
+
+    def input_data(self, is_infer=False, **kwargs):
+        query = fluid.data(
+            name="query", shape=[-1, self.TRIGRAM_D], dtype='float32', lod_level=0)
+        doc_pos = fluid.data(
             name="doc_pos",
-            shape=[-1, TRIGRAM_D],
+            shape=[-1, self.TRIGRAM_D],
             dtype='float32',
             lod_level=0)
-        self.doc_negs = [
+        
+        if is_infer:
+            return [query, doc_pos]
+
+        doc_negs = [
             fluid.data(
                 name="doc_neg_" + str(i),
-                shape=[-1, TRIGRAM_D],
+                shape=[-1, self.TRIGRAM_D],
                 dtype="float32",
-                lod_level=0) for i in range(Neg)
+                lod_level=0) for i in range(self.Neg)
         ]
-        self._data_var.append(self.query)
-        self._data_var.append(self.doc_pos)
-        for input in self.doc_negs:
-            self._data_var.append(input)
-
-        if self._platform != "LINUX":
-            self._data_loader = fluid.io.DataLoader.from_generator(
-                feed_list=self._data_var,
-                capacity=64,
-                use_double_buffer=False,
-                iterable=False)
-
-    def net(self, is_infer=False):
-        hidden_layers = envs.get_global_env("hyper_parameters.fc_sizes", None,
-                                            self._namespace)
-        hidden_acts = envs.get_global_env("hyper_parameters.fc_acts", None,
-                                          self._namespace)
+        return [query, doc_pos] + doc_negs
 
+    def net(self, inputs, is_infer=False):
         def fc(data, hidden_layers, hidden_acts, names):
             fc_inputs = [data]
             for i in range(len(hidden_layers)):
@@ -77,71 +67,31 @@ class Model(ModelBase):
                 fc_inputs.append(out)
             return fc_inputs[-1]
 
-        query_fc = fc(self.query, hidden_layers, hidden_acts,
+        query_fc = fc(inputs[0], self.hidden_layers, self.hidden_acts,
                       ['query_l1', 'query_l2', 'query_l3'])
-        doc_pos_fc = fc(self.doc_pos, hidden_layers, hidden_acts,
+        doc_pos_fc = fc(inputs[1], self.hidden_layers, self.hidden_acts,
                         ['doc_pos_l1', 'doc_pos_l2', 'doc_pos_l3'])
-        self.R_Q_D_p = fluid.layers.cos_sim(query_fc, doc_pos_fc)
+        R_Q_D_p = fluid.layers.cos_sim(query_fc, doc_pos_fc)
 
         if is_infer:
+            self._infer_results["query_doc_sim"] = R_Q_D_p
             return
 
         R_Q_D_ns = []
-        for i, doc_neg in enumerate(self.doc_negs):
-            doc_neg_fc_i = fc(doc_neg, hidden_layers, hidden_acts, [
+        for i in range(len(inputs)-2):
+            doc_neg_fc_i = fc(inputs[i+2], self.hidden_layers, self.hidden_acts, [
                 'doc_neg_l1_' + str(i), 'doc_neg_l2_' + str(i),
                 'doc_neg_l3_' + str(i)
             ])
             R_Q_D_ns.append(fluid.layers.cos_sim(query_fc, doc_neg_fc_i))
         concat_Rs = fluid.layers.concat(
-            input=[self.R_Q_D_p] + R_Q_D_ns, axis=-1)
+            input=[R_Q_D_p] + R_Q_D_ns, axis=-1)
         prob = fluid.layers.softmax(concat_Rs, axis=1)
 
         hit_prob = fluid.layers.slice(
             prob, axes=[0, 1], starts=[0, 0], ends=[4, 1])
         loss = -fluid.layers.reduce_sum(fluid.layers.log(hit_prob))
-        self.avg_cost = fluid.layers.mean(x=loss)
-
-    def infer_results(self):
-        self._infer_results['query_doc_sim'] = self.R_Q_D_p
-
-    def avg_loss(self):
-        self._cost = self.avg_cost
-
-    def metrics(self):
-        self._metrics["LOSS"] = self.avg_cost
-
-    def train_net(self):
-        self.input()
-        self.net(is_infer=False)
-        self.avg_loss()
-        self.metrics()
-
-    def optimizer(self):
-        learning_rate = envs.get_global_env("hyper_parameters.learning_rate",
-                                            None, self._namespace)
-        optimizer = fluid.optimizer.SGD(learning_rate)
-        return optimizer
-
-    def infer_input(self):
-        TRIGRAM_D = envs.get_global_env("hyper_parameters.TRIGRAM_D", None,
-                                        self._namespace)
-        self.query = fluid.data(
-            name="query", shape=[-1, TRIGRAM_D], dtype='float32', lod_level=0)
-        self.doc_pos = fluid.data(
-            name="doc_pos",
-            shape=[-1, TRIGRAM_D],
-            dtype='float32',
-            lod_level=0)
-        self._infer_data_var = [self.query, self.doc_pos]
-
-        self._infer_data_loader = fluid.io.DataLoader.from_generator(
-            feed_list=self._infer_data_var,
-            capacity=64,
-            use_double_buffer=False,
-            iterable=False)
+        avg_cost = fluid.layers.mean(x=loss)
+        self._cost = avg_cost
+        self._metrics["LOSS"] = avg_cost
 
-    def infer_net(self):
-        self.infer_input()
-        self.net(is_infer=True)
-        self.infer_results()