Skip to content

B
book

PaddlePaddle / book

通知 16
Star 4
Fork 0
B
book
提交 2ef9e287 编写于 作者: L lujun 提交者： Cheerego
浏览文件
操作

Fix README error (#663) 

* test=develop

* test=develop
上级 64c82c57
隐藏空白更改
内联 并排
Showing with 321 addition and 229 deletion
02.recognize_digits/README.cn.md
浏览文件 @ 2ef9e287
......@@ -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
浏览文件 @ 2ef9e287
......@@ -316,18 +316,10 @@ 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
......
04.word2vec/README.cn.md
浏览文件 @ 2ef9e287
......@@ -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)
......
04.word2vec/index.cn.html
浏览文件 @ 2ef9e287
......@@ -275,32 +275,28 @@ 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,
......@@ -318,74 +314,112 @@ 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
......@@ -402,53 +436,75 @@ 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：
......@@ -461,14 +517,11 @@ 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)
......
04.word2vec/train.py
浏览文件 @ 2ef9e287
......@@ -22,7 +22,7 @@ import math
EMBED_SIZE = 32
HIDDEN_SIZE = 256
N = 5
BATCH_SIZE = 32
BATCH_SIZE = 100
PASS_NUM = 100
use_cuda = False # set to True if training with GPU
......@@ -143,16 +143,16 @@ def train(if_use_cuda, params_dirname, is_sparse=True):
main_program, feed=feeder.feed(data), fetch_list=[avg_cost])
if step % 10 == 0:
#outs = train_test(test_program, test_reader)
outs = train_test(test_program, test_reader)
# print("Step %d: Average Cost %f" % (step, avg_cost_np[0]))
print("Step %d: Average Cost %f" % (step, avg_cost_np[0]))
print("Step %d: Average Cost %f" % (step, outs[0]))
# print(outs)
# 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 avg_cost_np[0] < 5.8:
if outs[0] < 5.8:
if params_dirname is not None:
fluid.io.save_inference_model(params_dirname, [
'firstw', 'secondw', 'thirdw', 'fourthw'
......
08.machine_translation/README.cn.md
浏览文件 @ 2ef9e287
......@@ -451,6 +451,7 @@ for data in test_data():
return_numpy=False)
result_ids = np.array(results[0])
result_ids_lod = results[0].lod()
result_scores = np.array(results[1])
print("Original sentence:")
......
08.machine_translation/index.cn.html
浏览文件 @ 2ef9e287
......@@ -493,6 +493,7 @@ for data in test_data():
return_numpy=False)
result_ids = np.array(results[0])
result_ids_lod = results[0].lod()
result_scores = np.array(results[1])
print("Original sentence:")
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或