Merge pull request #1474 from helinwang/word2vec

word2vec v2 api

demo/word2vec/train_v2.py

@@ -0,0 +1,80 @@
+import math
+
+import paddle.v2 as paddle
+
+dictsize = 1953
+embsize = 32
+hiddensize = 256
+N = 5
+
+
+def wordemb(inlayer):
+    wordemb = paddle.layer.table_projection(
+        input=inlayer,
+        size=embsize,
+        param_attr=paddle.attr.Param(
+            name="_proj",
+            initial_std=0.001,
+            learning_rate=1,
+            l2_rate=0, ))
+    return wordemb
+
+
+def main():
+    paddle.init(use_gpu=False, trainer_count=1)
+    word_dict = paddle.dataset.imikolov.build_dict()
+    dict_size = len(word_dict)
+    firstword = paddle.layer.data(
+        name="firstw", type=paddle.data_type.integer_value(dict_size))
+    secondword = paddle.layer.data(
+        name="secondw", type=paddle.data_type.integer_value(dict_size))
+    thirdword = paddle.layer.data(
+        name="thirdw", type=paddle.data_type.integer_value(dict_size))
+    fourthword = paddle.layer.data(
+        name="fourthw", type=paddle.data_type.integer_value(dict_size))
+    nextword = paddle.layer.data(
+        name="fifthw", type=paddle.data_type.integer_value(dict_size))
+
+    Efirst = wordemb(firstword)
+    Esecond = wordemb(secondword)
+    Ethird = wordemb(thirdword)
+    Efourth = wordemb(fourthword)
+
+    contextemb = paddle.layer.concat(input=[Efirst, Esecond, Ethird, Efourth])
+    hidden1 = paddle.layer.fc(input=contextemb,
+                              size=hiddensize,
+                              act=paddle.activation.Sigmoid(),
+                              layer_attr=paddle.attr.Extra(drop_rate=0.5),
+                              bias_attr=paddle.attr.Param(learning_rate=2),
+                              param_attr=paddle.attr.Param(
+                                  initial_std=1. / math.sqrt(embsize * 8),
+                                  learning_rate=1))
+    predictword = paddle.layer.fc(input=hidden1,
+                                  size=dict_size,
+                                  bias_attr=paddle.attr.Param(learning_rate=2),
+                                  act=paddle.activation.Softmax())
+
+    def event_handler(event):
+        if isinstance(event, paddle.event.EndIteration):
+            if event.batch_id % 100 == 0:
+                result = trainer.test(
+                    paddle.batch(
+                        paddle.dataset.imikolov.test(word_dict, N), 32))
+                print "Pass %d, Batch %d, Cost %f, %s, Testing metrics %s" % (
+                    event.pass_id, event.batch_id, event.cost, event.metrics,
+                    result.metrics)
+
+    cost = paddle.layer.classification_cost(input=predictword, label=nextword)
+    parameters = paddle.parameters.create(cost)
+    adam_optimizer = paddle.optimizer.Adam(
+        learning_rate=3e-3,
+        regularization=paddle.optimizer.L2Regularization(8e-4))
+    trainer = paddle.trainer.SGD(cost, parameters, adam_optimizer)
+    trainer.train(
+        paddle.batch(paddle.dataset.imikolov.train(word_dict, N), 32),
+        num_passes=30,
+        event_handler=event_handler)
+
+
+if __name__ == '__main__':
+    main()