Fix README error (#663)

* test=develop

* test=develop

Author: junjun315

02.recognize_digits/README.cn.md

@@ -274,18 +274,10 @@ test_reader = paddle.batch(
             paddle.dataset.mnist.test(), batch_size=BATCH_SIZE)
 ```
 
-### Trainer 配置
+### Trainer 训练过程
 
-现在，我们需要构建一个 `Trainer`。`Trainer` 包含一个训练程序 `train_program`, `place` 和优化器 `optimizer`，并包含训练迭代、检查训练期间测试误差以及保存所需要用来预测的模型参数。
+现在，我们需要构建一个训练过程。将使用到前面定义的训练程序 `train_program`, `place` 和优化器 `optimizer`，并包含训练迭代、检查训练期间测试误差以及保存所需要用来预测的模型参数。
 
-```python
-# 该模型运行在单个CPU上
-use_cuda = False # set to True if training with GPU
-place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
-
-trainer = Trainer(
-    train_func=train_program, place=place, optimizer_func=optimizer_program)
-```
 
 #### Event Handler 配置
 

02.recognize_digits/index.cn.html

@@ -316,18 +316,10 @@
             paddle.dataset.mnist.test(), batch_size=BATCH_SIZE)
 ```
 
-### Trainer 配置
+### Trainer 训练过程
 
-现在，我们需要构建一个 `Trainer`。`Trainer` 包含一个训练程序 `train_program`, `place` 和优化器 `optimizer`，并包含训练迭代、检查训练期间测试误差以及保存所需要用来预测的模型参数。
+现在，我们需要构建一个训练过程。将使用到前面定义的训练程序 `train_program`, `place` 和优化器 `optimizer`，并包含训练迭代、检查训练期间测试误差以及保存所需要用来预测的模型参数。
 
-```python
-# 该模型运行在单个CPU上
-use_cuda = False # set to True if training with GPU
-place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
-
-trainer = Trainer(
-    train_func=train_program, place=place, optimizer_func=optimizer_program)
-```
 
 #### Event Handler 配置
 

04.word2vec/README.cn.md

@@ -233,32 +233,28 @@ dict_size = len(word_dict)
 - 我们来定义我们的 N-gram 神经网络结构。这个结构在训练和预测中都会使用到。因为词向量比较稀疏，我们传入参数 `is_sparse == True`, 可以加速稀疏矩阵的更新。
 
 ```python
-def inference_program(is_sparse):
-    first_word = fluid.layers.data(name='firstw', shape=[1], dtype='int64')
-    second_word = fluid.layers.data(name='secondw', shape=[1], dtype='int64')
-    third_word = fluid.layers.data(name='thirdw', shape=[1], dtype='int64')
-    fourth_word = fluid.layers.data(name='fourthw', shape=[1], dtype='int64')
+def inference_program(words, is_sparse):
 
     embed_first = fluid.layers.embedding(
-        input=first_word,
+        input=words[0],
         size=[dict_size, EMBED_SIZE],
         dtype='float32',
         is_sparse=is_sparse,
         param_attr='shared_w')
     embed_second = fluid.layers.embedding(
-        input=second_word,
+        input=words[1],
         size=[dict_size, EMBED_SIZE],
         dtype='float32',
         is_sparse=is_sparse,
         param_attr='shared_w')
     embed_third = fluid.layers.embedding(
-        input=third_word,
+        input=words[2],
         size=[dict_size, EMBED_SIZE],
         dtype='float32',
         is_sparse=is_sparse,
         param_attr='shared_w')
     embed_fourth = fluid.layers.embedding(
-        input=fourth_word,
+        input=words[3],
         size=[dict_size, EMBED_SIZE],
         dtype='float32',
         is_sparse=is_sparse,
@@ -276,74 +272,112 @@ def inference_program(is_sparse):
 - 基于以上的神经网络结构，我们可以如下定义我们的`训练`方法
 
 ```python
-def train_program(is_sparse):
+def train_program(predict_word):
     # The declaration of 'next_word' must be after the invoking of inference_program,
     # or the data input order of train program would be [next_word, firstw, secondw,
     # thirdw, fourthw], which is not correct.
-    predict_word = inference_program(is_sparse)
     next_word = fluid.layers.data(name='nextw', shape=[1], dtype='int64')
     cost = fluid.layers.cross_entropy(input=predict_word, label=next_word)
     avg_cost = fluid.layers.mean(cost)
     return avg_cost
-```
-
-- 现在我们可以开始训练啦。如今的版本较之以前就简单了许多。我们有现成的训练和测试集：`paddle.dataset.imikolov.train()`和`paddle.dataset.imikolov.test()`。两者都会返回一个读取器。在PaddlePaddle中，读取器是一个Python的函数，每次调用，会读取下一条数据。它是一个Python的generator。
 
-`paddle.batch` 会读入一个读取器，然后输出一个批次化了的读取器。`event_handler`亦可以一并传入`trainer.train`来时不时的输出每个步骤，批次的训练情况。
-
-```python
 def optimizer_func():
-    # Note here we need to choose more sophisticated optimizers
-    # such as AdaGrad with a decay rate. The normal SGD converges
-    # very slowly.
-    # optimizer=fluid.optimizer.SGD(learning_rate=0.001),
     return fluid.optimizer.AdagradOptimizer(
         learning_rate=3e-3,
         regularization=fluid.regularizer.L2DecayRegularizer(8e-4))
 
+```
+
+- 现在我们可以开始训练啦。如今的版本较之以前就简单了许多。我们有现成的训练和测试集：`paddle.dataset.imikolov.train()`和`paddle.dataset.imikolov.test()`。两者都会返回一个读取器。在PaddlePaddle中，读取器是一个Python的函数，每次调用，会读取下一条数据。它是一个Python的generator。
+
+`paddle.batch` 会读入一个读取器，然后输出一个批次化了的读取器。我们还可以在训练过程中输出每个步骤，批次的训练情况。
+
+```python
+def train(if_use_cuda, params_dirname, is_sparse=True):
+    place = fluid.CUDAPlace(0) if if_use_cuda else fluid.CPUPlace()
 
-def train(use_cuda, train_program, params_dirname):
     train_reader = paddle.batch(
         paddle.dataset.imikolov.train(word_dict, N), BATCH_SIZE)
     test_reader = paddle.batch(
         paddle.dataset.imikolov.test(word_dict, N), BATCH_SIZE)
 
-    place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
+    first_word = fluid.layers.data(name='firstw', shape=[1], dtype='int64')
+    second_word = fluid.layers.data(name='secondw', shape=[1], dtype='int64')
+    third_word = fluid.layers.data(name='thirdw', shape=[1], dtype='int64')
+    forth_word = fluid.layers.data(name='fourthw', shape=[1], dtype='int64')
+    next_word = fluid.layers.data(name='nextw', shape=[1], dtype='int64')
 
-    def event_handler(event):
-        if isinstance(event, EndStepEvent):
-            # We output cost every 10 steps.
-            if event.step % 10 == 0:
-                outs = trainer.test(
-                    reader=test_reader,
-                    feed_order=['firstw', 'secondw', 'thirdw', 'fourthw', 'nextw'])
-                avg_cost = outs[0]
-
-                print("Step %d: Average Cost %f" % (event.step, avg_cost))
-
-                # If average cost is lower than 5.8, we consider the model good enough to stop.
-                # Note 5.8 is a relatively high value. In order to get a better model, one should
-                # aim for avg_cost lower than 3.5. But the training could take longer time.
-                if avg_cost < 5.8:
-                    trainer.save_params(params_dirname)
-                    trainer.stop()
-
-                if math.isnan(avg_cost):
+    word_list = [first_word, second_word, third_word, forth_word, next_word]
+    feed_order = ['firstw', 'secondw', 'thirdw', 'fourthw', 'nextw']
+
+    main_program = fluid.default_main_program()
+    star_program = fluid.default_startup_program()
+
+    predict_word = inference_program(word_list, is_sparse)
+    avg_cost = train_program(predict_word)
+    test_program = main_program.clone(for_test=True)
+
+    sgd_optimizer = optimizer_func()
+    sgd_optimizer.minimize(avg_cost)
+
+    exe = fluid.Executor(place)
+
+    def train_test(program, reader):
+        count = 0
+        feed_var_list = [
+            program.global_block().var(var_name) for var_name in feed_order
+        ]
+        feeder_test = fluid.DataFeeder(feed_list=feed_var_list, place=place)
+        test_exe = fluid.Executor(place)
+        accumulated = len([avg_cost]) * [0]
+        for test_data in reader():
+            avg_cost_np = test_exe.run(
+                program=program,
+                feed=feeder_test.feed(test_data),
+                fetch_list=[avg_cost])
+            accumulated = [
+                x[0] + x[1][0] for x in zip(accumulated, avg_cost_np)
+            ]
+            count += 1
+        return [x / count for x in accumulated]
+
+    def train_loop():
+        step = 0
+        feed_var_list_loop = [
+            main_program.global_block().var(var_name) for var_name in feed_order
+        ]
+        feeder = fluid.DataFeeder(feed_list=feed_var_list_loop, place=place)
+        exe.run(star_program)
+        for pass_id in range(PASS_NUM):
+            for data in train_reader():
+                avg_cost_np = exe.run(
+                    main_program, feed=feeder.feed(data), fetch_list=[avg_cost])
+
+                if step % 10 == 0:
+                    outs = train_test(test_program, test_reader)
+
+                    print("Step %d: Average Cost %f" % (step, outs[0]))
+
+                    # it will take a few hours.
+                    # If average cost is lower than 5.8, we consider the model good enough to stop.
+                    # Note 5.8 is a relatively high value. In order to get a better model, one should
+                    # aim for avg_cost lower than 3.5. But the training could take longer time.
+                    if outs[0] < 5.8:
+                        if params_dirname is not None:
+                            fluid.io.save_inference_model(params_dirname, [
+                                'firstw', 'secondw', 'thirdw', 'fourthw'
+                            ], [predict_word], exe)
+                        return
+                step += 1
+                if math.isnan(float(avg_cost_np[0])):
                     sys.exit("got NaN loss, training failed.")
 
-    trainer = Trainer(
-        train_func=train_program,
-        optimizer_func=optimizer_func,
-        place=place)
+        raise AssertionError("Cost is too large {0:2.2}".format(avg_cost_np[0]))
 
-    trainer.train(
-        reader=train_reader,
-        num_epochs=1,
-        event_handler=event_handler,
-        feed_order=['firstw', 'secondw', 'thirdw', 'fourthw', 'nextw'])
+    train_loop()
 ```
 
-- `trainer.train`将会开始训练。从`event_handler`返回的监控情况如下：
+- `train_loop`将会开始训练。期间打印返回的监控情况如下：
 
 ```text
 Step 0: Average Cost 7.337213
@@ -360,53 +394,75 @@ Step 20: Average Cost 5.766995
 我们可以用我们训练过的模型，在得知之前的 N-gram 后，预测下一个词。
 
 ```python
-def infer(use_cuda, inference_program, params_dirname=None):
+def infer(use_cuda, params_dirname=None):
     place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
-    inferencer = Inferencer(
-        infer_func=inference_program, param_path=params_dirname, place=place)
-
-    # Setup inputs by creating 4 LoDTensors representing 4 words. Here each word
-    # is simply an index to look up for the corresponding word vector and hence
-    # the shape of word (base_shape) should be [1]. The length-based level of
-    # detail (lod) info of each LoDtensor should be [[1]] meaning there is only
-    # one lod_level and there is only one sequence of one word on this level.
-    # Note that lod info should be a list of lists.
-
-    data1 = [[211]]  # 'among'
-    data2 = [[6]]    # 'a'
-    data3 = [[96]]   # 'group'
-    data4 = [[4]]    # 'of'
-    lod = [[1]]
-
-    first_word  = fluid.create_lod_tensor(data1, lod, place)
-    second_word = fluid.create_lod_tensor(data2, lod, place)
-    third_word  = fluid.create_lod_tensor(data3, lod, place)
-    fourth_word = fluid.create_lod_tensor(data4, lod, place)
-
-    result = inferencer.infer(
-        {
-            'firstw': first_word,
-            'secondw': second_word,
-            'thirdw': third_word,
-            'fourthw': fourth_word
-        },
-        return_numpy=False)
-
-    print(numpy.array(result[0]))
-    most_possible_word_index = numpy.argmax(result[0])
-    print(most_possible_word_index)
-    print([
-        key for key, value in six.iteritems(word_dict)
-        if value == most_possible_word_index
-    ][0])
+
+    exe = fluid.Executor(place)
+
+    inference_scope = fluid.core.Scope()
+
+    inference_scope = fluid.core.Scope()
+    with fluid.scope_guard(inference_scope):
+        # Use fluid.io.load_inference_model to obtain the inference program desc,
+        # the feed_target_names (the names of variables that will be feeded
+        # data using feed operators), and the fetch_targets (variables that
+        # we want to obtain data from using fetch operators).
+        [inferencer, feed_target_names,
+         fetch_targets] = fluid.io.load_inference_model(params_dirname, exe)
+
+        # Setup inputs by creating 4 LoDTensors representing 4 words. Here each word
+        # is simply an index to look up for the corresponding word vector and hence
+        # the shape of word (base_shape) should be [1]. The recursive_sequence_lengths,
+        # which is length-based level of detail (lod) of each LoDTensor, should be [[1]]
+        # meaning there is only one level of detail and there is only one sequence of
+        # one word on this level.
+        # Note that recursive_sequence_lengths should be a list of lists.
+        data1 = [[211]]  # 'among'
+        data2 = [[6]]  # 'a'
+        data3 = [[96]]  # 'group'
+        data4 = [[4]]  # 'of'
+        lod = [[1]]
+
+        first_word = fluid.create_lod_tensor(data1, lod, place)
+        second_word = fluid.create_lod_tensor(data2, lod, place)
+        third_word = fluid.create_lod_tensor(data3, lod, place)
+        fourth_word = fluid.create_lod_tensor(data4, lod, place)
+
+        assert feed_target_names[0] == 'firstw'
+        assert feed_target_names[1] == 'secondw'
+        assert feed_target_names[2] == 'thirdw'
+        assert feed_target_names[3] == 'fourthw'
+
+        # Construct feed as a dictionary of {feed_target_name: feed_target_data}
+        # and results will contain a list of data corresponding to fetch_targets.
+        results = exe.run(
+            inferencer,
+            feed={
+                feed_target_names[0]: first_word,
+                feed_target_names[1]: second_word,
+                feed_target_names[2]: third_word,
+                feed_target_names[3]: fourth_word
+            },
+            fetch_list=fetch_targets,
+            return_numpy=False)
+
+        print(numpy.array(results[0]))
+        most_possible_word_index = numpy.argmax(results[0])
+        print(most_possible_word_index)
+        print([
+            key for key, value in six.iteritems(word_dict)
+            if value == most_possible_word_index
+        ][0])
+
+
 ```
 
-在经历3分钟的短暂训练后，我们得到如下的预测。我们的模型预测 `among a group of` 的下一个词是`a`。这比较符合文法规律。如果我们训练时间更长，比如几个小时，那么我们会得到的下一个预测是 `workers`。
+由于词向量矩阵本身比较稀疏，训练的过程如果要达到一定的精度耗时会比较长。为了能简单看到效果，教程只设置了经过很少的训练就结束并得到如下的预测。我们的模型预测 `among a group of` 的下一个词是`the`。这比较符合文法规律。如果我们训练时间更长，比如几个小时，那么我们会得到的下一个预测是 `workers`。
 
 ```text
-[[0.00106646 0.0007907  0.00072041 ... 0.00049024 0.00041355 0.00084464]]
-6
-a
+[[0.03768077 0.03463154 0.00018074 ... 0.00022283 0.00029888 0.02967956]]
+0
+the
 ```
 
 整个程序的入口很简单：
@@ -419,14 +475,11 @@ def main(use_cuda, is_sparse):
     params_dirname = "word2vec.inference.model"
 
     train(
-        use_cuda=use_cuda,
-        train_program=partial(train_program, is_sparse),
-        params_dirname=params_dirname)
-
-    infer(
-        use_cuda=use_cuda,
-        inference_program=partial(inference_program, is_sparse),
-        params_dirname=params_dirname)
+        if_use_cuda=use_cuda,
+        params_dirname=params_dirname,
+        is_sparse=is_sparse)
+
+    infer(use_cuda=use_cuda, params_dirname=params_dirname)
 
 
 main(use_cuda=use_cuda, is_sparse=True)