update to low level api--06 understand sentiment,test=develop

06.understand_sentiment/README.cn.md

@@ -110,24 +110,16 @@ Paddle在`dataset/imdb.py`中提实现了imdb数据集的自动下载和读取
 from __future__ import print_function
 import paddle
 import paddle.fluid as fluid
-from functools import partial
 import numpy as np
-try:
-    from paddle.fluid.contrib.trainer import *
-    from paddle.fluid.contrib.inferencer import *
-except ImportError:
-    print(
-        "In the fluid 1.0, the trainer and inferencer are moving to paddle.fluid.contrib",
-        file=sys.stderr)
-    from paddle.fluid.trainer import *
-    from paddle.fluid.inferencer import *
+import sys
+import math
 
 CLASS_DIM = 2
 EMB_DIM = 128
 HID_DIM = 512
 STACKED_NUM = 3
 BATCH_SIZE = 128
-USE_GPU = False
+
 ```
 
 
@@ -212,8 +204,7 @@ def inference_program(word_dict):
 在测试过程中，分类器会计算各个输出的概率。第一个返回的数值规定为 损耗(cost)。
 
 ```python
-def train_program(word_dict):
-    prediction = inference_program(word_dict)
+def train_program(prediction):
     label = fluid.layers.data(name="label", shape=[1], dtype="int64")
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
     avg_cost = fluid.layers.mean(cost)
@@ -258,59 +249,77 @@ train_reader = paddle.batch(
 训练器需要一个训练程序和一个训练优化函数。
 
 ```python
-trainer = Trainer(
-    train_func=partial(train_program, word_dict),
-    place=place,
-    optimizer_func=optimizer_func)
+exe = fluid.Executor(place)
+prediction = inference_program(word_dict)
+[avg_cost, accuracy] = train_program(prediction)
+sgd_optimizer = optimizer_func()
+sgd_optimizer.minimize(avg_cost)
 ```
 
-### 提供数据
+### 提供数据并构建主训练循环
 
 `feed_order`用来定义每条产生的数据和`paddle.layer.data`之间的映射关系。比如，`imdb.train`产生的第一列的数据对应的是`words`这个特征。
 
-```python
-feed_order = ['words', 'label']
-```
-
-### 事件处理器
-
-回调函数event_handler在一个之前定义好的事件发生后会被调用。例如，我们可以在每步训练结束后查看误差。
-
 ```python
 # Specify the directory path to save the parameters
 params_dirname = "understand_sentiment_conv.inference.model"
 
-def event_handler(event):
-    if isinstance(event, EndStepEvent):
-        print("Step {0}, Epoch {1} Metrics {2}".format(
-                event.step, event.epoch, list(map(np.array, event.metrics))))
-
-        if event.step == 10:
-            trainer.save_params(params_dirname)
-            trainer.stop()
+feed_order = ['words', 'label']
+pass_num = 1
+
+def train_loop(main_program):
+    exe.run(fluid.default_startup_program())
+    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)
+
+    test_program = fluid.default_main_program().clone(for_test=True)
+
+    for epoch_id in range(pass_num):
+        for step_id, data in enumerate(train_reader()):
+            metrics = exe.run(main_program,
+                              feed=feeder.feed(data),
+                              fetch_list=[avg_cost, accuracy])
+
+            avg_cost_test, acc_test = train_test(test_program, test_reader)
+            print('Step {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
+                step_id, avg_cost_test, acc_test))
+
+            print("Step {0}, Epoch {1} Metrics {2}".format(
+                step_id, epoch_id, list(map(np.array,
+                                            metrics))))
+
+            if step_id == 30:
+                if params_dirname is not None:
+                    fluid.io.save_inference_model(params_dirname, ["words"],
+                                                  prediction, exe)
+                return
 ```
 
+### 训练过程处理
+
+我们在训练主循环里打印了每一步输出，可以观察训练情况。
+
 ### 开始训练
 
-最后，我们传入训练循环数（num_epoch）和一些别的参数，调用 trainer.train 来开始训练。
+最后，我们启动训练主循环来开始训练。训练时间较长，如果为了更快的返回结果，可以通过调整损耗值范围或者训练步数，以减少准确率的代价来缩短训练时间。
 
 ```python
-trainer.train(
-    num_epochs=1,
-    event_handler=event_handler,
-    reader=train_reader,
-    feed_order=feed_order)
+train_loop(fluid.default_main_program())
 ```
 
 ## 应用模型
 
 ### 构建预测器
 
-传入`inference_program`和`params_dirname`来初始化一个预测器, `params_dirname`用来存放训练过程中的各个参数。
+和训练过程一样，我们需要创建一个预测过程，并使用训练得到的模型和参数来进行预测，`params_dirname`用来存放训练过程中的各个参数。
 
 ```python
-inferencer = Inferencer(
-        infer_func=partial(inference_program, word_dict), param_path=params_dirname, place=place)
+place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
+exe = fluid.Executor(place)
+inference_scope = fluid.core.Scope()
 ```
 
 ### 生成测试用输入数据
@@ -334,15 +343,25 @@ base_shape = [[len(c) for c in lod]]
 tensor_words = fluid.create_lod_tensor(lod, base_shape, place)
 ```
 
-## 应用模型
+## 应用模型并进行预测
 
 现在我们可以对每一条评论进行正面或者负面的预测啦。
 
 ```python
-results = inferencer.infer({'words': tensor_words})
-
-for i, r in enumerate(results[0]):
-    print("Predict probability of ", r[0], " to be positive and ", r[1], " to be negative for review \'", reviews_str[i], "\'")
+with fluid.scope_guard(inference_scope):
+
+    [inferencer, feed_target_names,
+     fetch_targets] = fluid.io.load_inference_model(params_dirname, exe)
+
+    assert feed_target_names[0] == "words"
+    results = exe.run(inference_program,
+                      feed={feed_target_names[0]: tensor_words},
+                      fetch_list=fetch_targets,
+                      return_numpy=False)
+    np_data = np.array(results[0])
+    for i, r in enumerate(np_data):
+        print("Predict probability of ", r[0], " to be positive and ", r[1],
+              " to be negative for review \'", reviews_str[i], "\'")
 
 ```
 

06.understand_sentiment/index.cn.html

@@ -152,24 +152,16 @@ Paddle在`dataset/imdb.py`中提实现了imdb数据集的自动下载和读取
 from __future__ import print_function
 import paddle
 import paddle.fluid as fluid
-from functools import partial
 import numpy as np
-try:
-    from paddle.fluid.contrib.trainer import *
-    from paddle.fluid.contrib.inferencer import *
-except ImportError:
-    print(
-        "In the fluid 1.0, the trainer and inferencer are moving to paddle.fluid.contrib",
-        file=sys.stderr)
-    from paddle.fluid.trainer import *
-    from paddle.fluid.inferencer import *
+import sys
+import math
 
 CLASS_DIM = 2
 EMB_DIM = 128
 HID_DIM = 512
 STACKED_NUM = 3
 BATCH_SIZE = 128
-USE_GPU = False
+
 ```
 
 
@@ -254,8 +246,7 @@ def inference_program(word_dict):
 在测试过程中，分类器会计算各个输出的概率。第一个返回的数值规定为 损耗(cost)。
 
 ```python
-def train_program(word_dict):
-    prediction = inference_program(word_dict)
+def train_program(prediction):
     label = fluid.layers.data(name="label", shape=[1], dtype="int64")
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
     avg_cost = fluid.layers.mean(cost)
@@ -300,59 +291,77 @@ train_reader = paddle.batch(
 训练器需要一个训练程序和一个训练优化函数。
 
 ```python
-trainer = Trainer(
-    train_func=partial(train_program, word_dict),
-    place=place,
-    optimizer_func=optimizer_func)
+exe = fluid.Executor(place)
+prediction = inference_program(word_dict)
+[avg_cost, accuracy] = train_program(prediction)
+sgd_optimizer = optimizer_func()
+sgd_optimizer.minimize(avg_cost)
 ```
 
-### 提供数据
+### 提供数据并构建主训练循环
 
 `feed_order`用来定义每条产生的数据和`paddle.layer.data`之间的映射关系。比如，`imdb.train`产生的第一列的数据对应的是`words`这个特征。
 
-```python
-feed_order = ['words', 'label']
-```
-
-### 事件处理器
-
-回调函数event_handler在一个之前定义好的事件发生后会被调用。例如，我们可以在每步训练结束后查看误差。
-
 ```python
 # Specify the directory path to save the parameters
 params_dirname = "understand_sentiment_conv.inference.model"
 
-def event_handler(event):
-    if isinstance(event, EndStepEvent):
-        print("Step {0}, Epoch {1} Metrics {2}".format(
-                event.step, event.epoch, list(map(np.array, event.metrics))))
-
-        if event.step == 10:
-            trainer.save_params(params_dirname)
-            trainer.stop()
+feed_order = ['words', 'label']
+pass_num = 1
+
+def train_loop(main_program):
+    exe.run(fluid.default_startup_program())
+    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)
+
+    test_program = fluid.default_main_program().clone(for_test=True)
+
+    for epoch_id in range(pass_num):
+        for step_id, data in enumerate(train_reader()):
+            metrics = exe.run(main_program,
+                              feed=feeder.feed(data),
+                              fetch_list=[avg_cost, accuracy])
+
+            avg_cost_test, acc_test = train_test(test_program, test_reader)
+            print('Step {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
+                step_id, avg_cost_test, acc_test))
+
+            print("Step {0}, Epoch {1} Metrics {2}".format(
+                step_id, epoch_id, list(map(np.array,
+                                            metrics))))
+
+            if step_id == 30:
+                if params_dirname is not None:
+                    fluid.io.save_inference_model(params_dirname, ["words"],
+                                                  prediction, exe)
+                return
 ```
 
+### 训练过程处理
+
+我们在训练主循环里打印了每一步输出，可以观察训练情况。
+
 ### 开始训练
 
-最后，我们传入训练循环数（num_epoch）和一些别的参数，调用 trainer.train 来开始训练。
+最后，我们启动训练主循环来开始训练。训练时间较长，如果为了更快的返回结果，可以通过调整损耗值范围或者训练步数，以减少准确率的代价来缩短训练时间。
 
 ```python
-trainer.train(
-    num_epochs=1,
-    event_handler=event_handler,
-    reader=train_reader,
-    feed_order=feed_order)
+train_loop(fluid.default_main_program())
 ```
 
 ## 应用模型
 
 ### 构建预测器
 
-传入`inference_program`和`params_dirname`来初始化一个预测器, `params_dirname`用来存放训练过程中的各个参数。
+和训练过程一样，我们需要创建一个预测过程，并使用训练得到的模型和参数来进行预测，`params_dirname`用来存放训练过程中的各个参数。
 
 ```python
-inferencer = Inferencer(
-        infer_func=partial(inference_program, word_dict), param_path=params_dirname, place=place)
+place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
+exe = fluid.Executor(place)
+inference_scope = fluid.core.Scope()
 ```
 
 ### 生成测试用输入数据
@@ -376,15 +385,25 @@ base_shape = [[len(c) for c in lod]]
 tensor_words = fluid.create_lod_tensor(lod, base_shape, place)
 ```
 
-## 应用模型
+## 应用模型并进行预测
 
 现在我们可以对每一条评论进行正面或者负面的预测啦。
 
 ```python
-results = inferencer.infer({'words': tensor_words})
-
-for i, r in enumerate(results[0]):
-    print("Predict probability of ", r[0], " to be positive and ", r[1], " to be negative for review \'", reviews_str[i], "\'")
+with fluid.scope_guard(inference_scope):
+
+    [inferencer, feed_target_names,
+     fetch_targets] = fluid.io.load_inference_model(params_dirname, exe)
+
+    assert feed_target_names[0] == "words"
+    results = exe.run(inference_program,
+                      feed={feed_target_names[0]: tensor_words},
+                      fetch_list=fetch_targets,
+                      return_numpy=False)
+    np_data = np.array(results[0])
+    for i, r in enumerate(np_data):
+        print("Predict probability of ", r[0], " to be positive and ", r[1],
+              " to be negative for review \'", reviews_str[i], "\'")
 
 ```
 

06.understand_sentiment/train_conv.py

@@ -14,22 +14,11 @@
 
 from __future__ import print_function
 
-import os
 import paddle
 import paddle.fluid as fluid
-from functools import partial
 import numpy as np
 import sys
-
-try:
-    from paddle.fluid.contrib.trainer import *
-    from paddle.fluid.contrib.inferencer import *
-except ImportError:
-    print(
-        "In the fluid 1.0, the trainer and inferencer are moving to paddle.fluid.contrib",
-        file=sys.stderr)
-    from paddle.fluid.trainer import *
-    from paddle.fluid.inferencer import *
+import math
 
 CLASS_DIM = 2
 EMB_DIM = 128
@@ -66,8 +55,7 @@ def inference_program(word_dict):
     return net
 
 
-def train_program(word_dict):
-    prediction = inference_program(word_dict)
+def train_program(prediction):
     label = fluid.layers.data(name="label", shape=[1], dtype="int64")
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
     avg_cost = fluid.layers.mean(cost)
@@ -79,8 +67,9 @@ def optimizer_func():
     return fluid.optimizer.Adagrad(learning_rate=0.002)
 
 
-def train(use_cuda, train_program, params_dirname):
+def train(use_cuda, params_dirname):
     place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
+
     print("Loading IMDB word dict....")
     word_dict = paddle.dataset.imdb.word_dict()
 
@@ -94,83 +83,131 @@ def train(use_cuda, train_program, params_dirname):
     test_reader = paddle.batch(
         paddle.dataset.imdb.test(word_dict), batch_size=BATCH_SIZE)
 
-    trainer = Trainer(
-        train_func=partial(train_program, word_dict),
-        place=place,
-        optimizer_func=optimizer_func)
-
     feed_order = ['words', 'label']
+    pass_num = 1
 
-    def event_handler(event):
-        if isinstance(event, EndStepEvent):
-            if event.step % 10 == 0:
-                avg_cost, acc = trainer.test(
-                    reader=test_reader, feed_order=feed_order)
-
-                print('Step {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
-                    event.step, avg_cost, acc))
-
-                print("Step {0}, Epoch {1} Metrics {2}".format(
-                    event.step, event.epoch, list(map(np.array,
-                                                      event.metrics))))
-
-        elif isinstance(event, EndEpochEvent):
-            trainer.save_params(params_dirname)
-
-    trainer.train(
-        num_epochs=1,
-        event_handler=event_handler,
-        reader=train_reader,
-        feed_order=feed_order)
-
-
-def infer(use_cuda, inference_program, params_dirname=None):
+    main_program = fluid.default_main_program()
+    star_program = fluid.default_startup_program()
+    prediction = inference_program(word_dict)
+    train_func_outputs = train_program(prediction)
+    avg_cost = train_func_outputs[0]
+
+    test_program = main_program.clone(for_test=True)
+
+    # [avg_cost, accuracy] = train_program(prediction)
+    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(train_func_outputs) * [0]
+        for test_data in reader():
+            avg_cost_np = test_exe.run(
+                program=program,
+                feed=feeder_test.feed(test_data),
+                fetch_list=train_func_outputs)
+            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():
+
+        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 epoch_id in range(pass_num):
+            for step_id, data in enumerate(train_reader()):
+                metrics = exe.run(
+                    main_program,
+                    feed=feeder.feed(data),
+                    fetch_list=[var.name for var in train_func_outputs])
+                print("step: {0}, Metrics {1}".format(
+                    step_id, list(map(np.array, metrics))))
+                if (step_id + 1) % 10 == 0:
+                    avg_cost_test, acc_test = train_test(test_program,
+                                                         test_reader)
+                    print('Step {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
+                        step_id, avg_cost_test, acc_test))
+
+                    print("Step {0}, Epoch {1} Metrics {2}".format(
+                        step_id, epoch_id, list(map(np.array, metrics))))
+                if math.isnan(float(metrics[0])):
+                    sys.exit("got NaN loss, training failed.")
+            if params_dirname is not None:
+                fluid.io.save_inference_model(params_dirname, ["words"],
+                                              prediction, exe)
+
+    train_loop()
+
+
+def infer(use_cuda, params_dirname=None):
     place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
     word_dict = paddle.dataset.imdb.word_dict()
 
-    inferencer = Inferencer(
-        infer_func=partial(inference_program, word_dict),
-        param_path=params_dirname,
-        place=place)
-
-    # Setup input by creating LoDTensor to represent sequence of words.
-    # Here each word is the basic element of the LoDTensor and the shape of
-    # each word (base_shape) should be [1] since it is simply an index to
-    # look up for the corresponding word vector.
-    # Suppose the length_based level of detail (lod) info is set to [[3, 4, 2]],
-    # which has only one lod level. Then the created LoDTensor will have only
-    # one higher level structure (sequence of words, or sentence) than the basic
-    # element (word). Hence the LoDTensor will hold data for three sentences of
-    # length 3, 4 and 2, respectively.
-    # Note that lod info should be a list of lists.
-
-    reviews_str = [
-        'read the book forget the movie', 'this is a great movie',
-        'this is very bad'
-    ]
-    reviews = [c.split() for c in reviews_str]
-
-    UNK = word_dict['<unk>']
-    lod = []
-    for c in reviews:
-        lod.append([word_dict.get(words, UNK) for words in c])
-
-    base_shape = [[len(c) for c in lod]]
-
-    tensor_words = fluid.create_lod_tensor(lod, base_shape, place)
-    results = inferencer.infer({'words': tensor_words})
-
-    for i, r in enumerate(results[0]):
-        print("Predict probability of ", r[0], " to be positive and ", r[1],
-              " to be negative for review \'", reviews_str[i], "\'")
+    exe = fluid.Executor(place)
+
+    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 input by creating LoDTensor to represent sequence of words.
+        # Here each word is the basic element of the LoDTensor and the shape of
+        # each word (base_shape) should be [1] since it is simply an index to
+        # look up for the corresponding word vector.
+        # Suppose the length_based level of detail (lod) info is set to [[3, 4, 2]],
+        # which has only one lod level. Then the created LoDTensor will have only
+        # one higher level structure (sequence of words, or sentence) than the basic
+        # element (word). Hence the LoDTensor will hold data for three sentences of
+        # length 3, 4 and 2, respectively.
+        # Note that lod info should be a list of lists.
+        reviews_str = [
+            'read the book forget the movie', 'this is a great movie',
+            'this is very bad'
+        ]
+        reviews = [c.split() for c in reviews_str]
+
+        UNK = word_dict['<unk>']
+        lod = []
+        for c in reviews:
+            lod.append([word_dict.get(words, UNK) for words in c])
+
+        base_shape = [[len(c) for c in lod]]
+
+        tensor_words = fluid.create_lod_tensor(lod, base_shape, place)
+        assert feed_target_names[0] == "words"
+        results = exe.run(
+            inferencer,
+            feed={feed_target_names[0]: tensor_words},
+            fetch_list=fetch_targets,
+            return_numpy=False)
+        np_data = np.array(results[0])
+        for i, r in enumerate(np_data):
+            print("Predict probability of ", r[0], " to be positive and ", r[1],
+                  " to be negative for review \'", reviews_str[i], "\'")
 
 
 def main(use_cuda):
     if use_cuda and not fluid.core.is_compiled_with_cuda():
         return
     params_dirname = "understand_sentiment_conv.inference.model"
-    train(use_cuda, train_program, params_dirname)
-    infer(use_cuda, inference_program, params_dirname)
+    train(use_cuda, params_dirname)
+    infer(use_cuda, params_dirname)
 
 
 if __name__ == '__main__':

06.understand_sentiment/train_dyn_rnn.py

@@ -14,28 +14,16 @@
 
 from __future__ import print_function
 
-import os
 import paddle
 import paddle.fluid as fluid
-from functools import partial
 import numpy as np
 import sys
-
-try:
-    from paddle.fluid.contrib.trainer import *
-    from paddle.fluid.contrib.inferencer import *
-except ImportError:
-    print(
-        "In the fluid 1.0, the trainer and inferencer are moving to paddle.fluid.contrib",
-        file=sys.stderr)
-    from paddle.fluid.trainer import *
-    from paddle.fluid.inferencer import *
+import math
 
 CLASS_DIM = 2
 EMB_DIM = 128
 BATCH_SIZE = 128
 LSTM_SIZE = 128
-USE_GPU = False
 
 
 def dynamic_rnn_lstm(data, input_dim, class_dim, emb_dim, lstm_size):
@@ -83,8 +71,7 @@ def inference_program(word_dict):
     return pred
 
 
-def train_program(word_dict):
-    prediction = inference_program(word_dict)
+def train_program(prediction):
     label = fluid.layers.data(name="label", shape=[1], dtype="int64")
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
     avg_cost = fluid.layers.mean(cost)
@@ -96,7 +83,7 @@ def optimizer_func():
     return fluid.optimizer.Adagrad(learning_rate=0.002)
 
 
-def train(use_cuda, train_program, params_dirname):
+def train(use_cuda, params_dirname):
     place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
     print("Loading IMDB word dict....")
     word_dict = paddle.dataset.imdb.word_dict()
@@ -111,83 +98,128 @@ def train(use_cuda, train_program, params_dirname):
     test_reader = paddle.batch(
         paddle.dataset.imdb.test(word_dict), batch_size=BATCH_SIZE)
 
-    trainer = Trainer(
-        train_func=partial(train_program, word_dict),
-        place=place,
-        optimizer_func=optimizer_func)
-
     feed_order = ['words', 'label']
+    pass_num = 1
 
-    def event_handler(event):
-        if isinstance(event, EndStepEvent):
-            if event.step % 10 == 0:
-                avg_cost, acc = trainer.test(
-                    reader=test_reader, feed_order=feed_order)
-
-                print('Step {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
-                    event.step, avg_cost, acc))
-
-                print("Step {0}, Epoch {1} Metrics {2}".format(
-                    event.step, event.epoch, list(map(np.array,
-                                                      event.metrics))))
-
-        elif isinstance(event, EndEpochEvent):
-            trainer.save_params(params_dirname)
-
-    trainer.train(
-        num_epochs=1,
-        event_handler=event_handler,
-        reader=train_reader,
-        feed_order=feed_order)
-
-
-def infer(use_cuda, inference_program, params_dirname=None):
+    main_program = fluid.default_main_program()
+    star_program = fluid.default_startup_program()
+    prediction = inference_program(word_dict)
+    train_func_outputs = train_program(prediction)
+    avg_cost = train_func_outputs[0]
+
+    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(train_func_outputs) * [0]
+        for test_data in reader():
+            avg_cost_np = test_exe.run(
+                program=program,
+                feed=feeder_test.feed(test_data),
+                fetch_list=train_func_outputs)
+            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():
+
+        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(fluid.default_startup_program())
+
+        for epoch_id in range(pass_num):
+            for step_id, data in enumerate(train_reader()):
+                metrics = exe.run(
+                    main_program,
+                    feed=feeder.feed(data),
+                    fetch_list=[var.name for var in train_func_outputs])
+                if (step_id + 1) % 10 == 0:
+
+                    #avg_cost_test, acc_test = train_test(test_program, test_reader)
+                    #print('Step {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
+                    #    step_id, avg_cost_test, acc_test))
+
+                    print("Step {0}, Epoch {1} Metrics {2}".format(
+                        step_id, epoch_id, list(map(np.array, metrics))))
+                if math.isnan(float(metrics[0])):
+                    sys.exit("got NaN loss, training failed.")
+            if params_dirname is not None:
+                fluid.io.save_inference_model(params_dirname, ["words"],
+                                              prediction, exe)
+
+    train_loop()
+
+
+def infer(use_cuda, params_dirname=None):
     place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
     word_dict = paddle.dataset.imdb.word_dict()
 
-    inferencer = Inferencer(
-        infer_func=partial(inference_program, word_dict),
-        param_path=params_dirname,
-        place=place)
-
-    # Setup input by creating LoDTensor to represent sequence of words.
-    # Here each word is the basic element of the LoDTensor and the shape of
-    # each word (base_shape) should be [1] since it is simply an index to
-    # look up for the corresponding word vector.
-    # Suppose the length_based level of detail (lod) info is set to [[3, 4, 2]],
-    # which has only one lod level. Then the created LoDTensor will have only
-    # one higher level structure (sequence of words, or sentence) than the basic
-    # element (word). Hence the LoDTensor will hold data for three sentences of
-    # length 3, 4 and 2, respectively.
-    # Note that lod info should be a list of lists.
-
-    reviews_str = [
-        'read the book forget the movie', 'this is a great movie',
-        'this is very bad'
-    ]
-    reviews = [c.split() for c in reviews_str]
-
-    UNK = word_dict['<unk>']
-    lod = []
-    for c in reviews:
-        lod.append([word_dict.get(words, UNK) for words in c])
-
-    base_shape = [[len(c) for c in lod]]
-
-    tensor_words = fluid.create_lod_tensor(lod, base_shape, place)
-    results = inferencer.infer({'words': tensor_words})
-
-    for i, r in enumerate(results[0]):
-        print("Predict probability of ", r[0], " to be positive and ", r[1],
-              " to be negative for review \'", reviews_str[i], "\'")
+    exe = fluid.Executor(place)
+
+    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 input by creating LoDTensor to represent sequence of words.
+        # Here each word is the basic element of the LoDTensor and the shape of
+        # each word (base_shape) should be [1] since it is simply an index to
+        # look up for the corresponding word vector.
+        # Suppose the length_based level of detail (lod) info is set to [[3, 4, 2]],
+        # which has only one lod level. Then the created LoDTensor will have only
+        # one higher level structure (sequence of words, or sentence) than the basic
+        # element (word). Hence the LoDTensor will hold data for three sentences of
+        # length 3, 4 and 2, respectively.
+        # Note that lod info should be a list of lists.
+        reviews_str = [
+            'read the book forget the movie', 'this is a great movie',
+            'this is very bad'
+        ]
+        reviews = [c.split() for c in reviews_str]
+
+        UNK = word_dict['<unk>']
+        lod = []
+        for c in reviews:
+            lod.append([word_dict.get(words, UNK) for words in c])
+
+        base_shape = [[len(c) for c in lod]]
+
+        tensor_words = fluid.create_lod_tensor(lod, base_shape, place)
+        assert feed_target_names[0] == "words"
+        results = exe.run(
+            inferencer,
+            feed={feed_target_names[0]: tensor_words},
+            fetch_list=fetch_targets,
+            return_numpy=False)
+        np_data = np.array(results[0])
+        for i, r in enumerate(np_data):
+            print("Predict probability of ", r[0], " to be positive and ", r[1],
+                  " to be negative for review \'", reviews_str[i], "\'")
 
 
 def main(use_cuda):
     if use_cuda and not fluid.core.is_compiled_with_cuda():
         return
     params_dirname = "understand_sentiment_conv.inference.model"
-    train(use_cuda, train_program, params_dirname)
-    infer(use_cuda, inference_program, params_dirname)
+    train(use_cuda, params_dirname)
+    infer(use_cuda, params_dirname)
 
 
 if __name__ == '__main__':

06.understand_sentiment/train_stacked_lstm.py

@@ -17,19 +17,9 @@ from __future__ import print_function
 import os
 import paddle
 import paddle.fluid as fluid
-from functools import partial
 import numpy as np
 import sys
-
-try:
-    from paddle.fluid.contrib.trainer import *
-    from paddle.fluid.contrib.inferencer import *
-except ImportError:
-    print(
-        "In the fluid 1.0, the trainer and inferencer are moving to paddle.fluid.contrib",
-        file=sys.stderr)
-    from paddle.fluid.trainer import *
-    from paddle.fluid.inferencer import *
+import math
 
 CLASS_DIM = 2
 EMB_DIM = 128
@@ -74,8 +64,8 @@ def inference_program(word_dict):
     return net
 
 
-def train_program(word_dict):
-    prediction = inference_program(word_dict)
+def train_program(prediction):
+    # prediction = inference_program(word_dict)
     label = fluid.layers.data(name="label", shape=[1], dtype="int64")
     cost = fluid.layers.cross_entropy(input=prediction, label=label)
     avg_cost = fluid.layers.mean(cost)
@@ -87,8 +77,9 @@ def optimizer_func():
     return fluid.optimizer.Adagrad(learning_rate=0.002)
 
 
-def train(use_cuda, train_program, params_dirname):
+def train(use_cuda, params_dirname):
     place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
+
     print("Loading IMDB word dict....")
     word_dict = paddle.dataset.imdb.word_dict()
 
@@ -102,83 +93,131 @@ def train(use_cuda, train_program, params_dirname):
     test_reader = paddle.batch(
         paddle.dataset.imdb.test(word_dict), batch_size=BATCH_SIZE)
 
-    trainer = Trainer(
-        train_func=partial(train_program, word_dict),
-        place=place,
-        optimizer_func=optimizer_func)
-
     feed_order = ['words', 'label']
+    pass_num = 1
 
-    def event_handler(event):
-        if isinstance(event, EndStepEvent):
-            if event.step % 10 == 0:
-                avg_cost, acc = trainer.test(
-                    reader=test_reader, feed_order=feed_order)
-
-                print('Step {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
-                    event.step, avg_cost, acc))
-
-                print("Step {0}, Epoch {1} Metrics {2}".format(
-                    event.step, event.epoch, list(map(np.array,
-                                                      event.metrics))))
-
-        elif isinstance(event, EndEpochEvent):
-            trainer.save_params(params_dirname)
-
-    trainer.train(
-        num_epochs=1,
-        event_handler=event_handler,
-        reader=train_reader,
-        feed_order=feed_order)
-
-
-def infer(use_cuda, inference_program, params_dirname=None):
+    main_program = fluid.default_main_program()
+    star_program = fluid.default_startup_program()
+    prediction = inference_program(word_dict)
+    train_func_outputs = train_program(prediction)
+    avg_cost = train_func_outputs[0]
+
+    test_program = main_program.clone(for_test=True)
+
+    # [avg_cost, accuracy] = train_program(prediction)
+    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(train_func_outputs) * [0]
+        for test_data in reader():
+            avg_cost_np = test_exe.run(
+                program=program,
+                feed=feeder_test.feed(test_data),
+                fetch_list=train_func_outputs)
+            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():
+
+        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(fluid.default_startup_program())
+
+        for epoch_id in range(pass_num):
+            for step_id, data in enumerate(train_reader()):
+                metrics = exe.run(
+                    main_program,
+                    feed=feeder.feed(data),
+                    fetch_list=[var.name for var in train_func_outputs])
+                print("step: {0}, Metrics {1}".format(
+                    step_id, list(map(np.array, metrics))))
+                if (step_id + 1) % 10 == 0:
+                    avg_cost_test, acc_test = train_test(test_program,
+                                                         test_reader)
+                    print('Step {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
+                        step_id, avg_cost_test, acc_test))
+
+                    print("Step {0}, Epoch {1} Metrics {2}".format(
+                        step_id, epoch_id, list(map(np.array, metrics))))
+                if math.isnan(float(metrics[0])):
+                    sys.exit("got NaN loss, training failed.")
+            if params_dirname is not None:
+                fluid.io.save_inference_model(params_dirname, ["words"],
+                                              prediction, exe)
+
+    train_loop()
+
+
+def infer(use_cuda, params_dirname=None):
     place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
     word_dict = paddle.dataset.imdb.word_dict()
 
-    inferencer = Inferencer(
-        infer_func=partial(inference_program, word_dict),
-        param_path=params_dirname,
-        place=place)
-
-    # Setup input by creating LoDTensor to represent sequence of words.
-    # Here each word is the basic element of the LoDTensor and the shape of
-    # each word (base_shape) should be [1] since it is simply an index to
-    # look up for the corresponding word vector.
-    # Suppose the length_based level of detail (lod) info is set to [[3, 4, 2]],
-    # which has only one lod level. Then the created LoDTensor will have only
-    # one higher level structure (sequence of words, or sentence) than the basic
-    # element (word). Hence the LoDTensor will hold data for three sentences of
-    # length 3, 4 and 2, respectively.
-    # Note that lod info should be a list of lists.
-
-    reviews_str = [
-        'read the book forget the movie', 'this is a great movie',
-        'this is very bad'
-    ]
-    reviews = [c.split() for c in reviews_str]
-
-    UNK = word_dict['<unk>']
-    lod = []
-    for c in reviews:
-        lod.append([word_dict.get(words, UNK) for words in c])
-
-    base_shape = [[len(c) for c in lod]]
-
-    tensor_words = fluid.create_lod_tensor(lod, base_shape, place)
-    results = inferencer.infer({'words': tensor_words})
-
-    for i, r in enumerate(results[0]):
-        print("Predict probability of ", r[0], " to be positive and ", r[1],
-              " to be negative for review \'", reviews_str[i], "\'")
+    exe = fluid.Executor(place)
+
+    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 input by creating LoDTensor to represent sequence of words.
+        # Here each word is the basic element of the LoDTensor and the shape of
+        # each word (base_shape) should be [1] since it is simply an index to
+        # look up for the corresponding word vector.
+        # Suppose the length_based level of detail (lod) info is set to [[3, 4, 2]],
+        # which has only one lod level. Then the created LoDTensor will have only
+        # one higher level structure (sequence of words, or sentence) than the basic
+        # element (word). Hence the LoDTensor will hold data for three sentences of
+        # length 3, 4 and 2, respectively.
+        # Note that lod info should be a list of lists.
+        reviews_str = [
+            'read the book forget the movie', 'this is a great movie',
+            'this is very bad'
+        ]
+        reviews = [c.split() for c in reviews_str]
+
+        UNK = word_dict['<unk>']
+        lod = []
+        for c in reviews:
+            lod.append([word_dict.get(words, UNK) for words in c])
+
+        base_shape = [[len(c) for c in lod]]
+
+        tensor_words = fluid.create_lod_tensor(lod, base_shape, place)
+        assert feed_target_names[0] == "words"
+        results = exe.run(
+            inferencer,
+            feed={feed_target_names[0]: tensor_words},
+            fetch_list=fetch_targets,
+            return_numpy=False)
+        np_data = np.array(results[0])
+        for i, r in enumerate(np_data):
+            print("Predict probability of ", r[0], " to be positive and ", r[1],
+                  " to be negative for review \'", reviews_str[i], "\'")
 
 
 def main(use_cuda):
     if use_cuda and not fluid.core.is_compiled_with_cuda():
         return
     params_dirname = "understand_sentiment_stacked_lstm.inference.model"
-    train(use_cuda, train_program, params_dirname)
-    infer(use_cuda, inference_program, params_dirname)
+    train(use_cuda, params_dirname)
+    infer(use_cuda, params_dirname)
 
 
 if __name__ == '__main__':