Skip to content

B
book

PaddlePaddle / book

通知 17
Star 4
Fork 0
B
book
“50da2d3114a6a7af9468aad3c6bf6995c04e079c”上不存在“mobile/src/operators/kernel/arm/activation_kernel.cpp”
提交 89d558cc 编写于 作者: N Nicky
浏览文件
操作

Add inference example instead of random data and update per team's comments

上级 cec2c1da
隐藏空白更改
内联 并排
Showing with 178 addition and 106 deletion
06.understand_sentiment/README.md
浏览文件 @ 89d558cc
......@@ -183,7 +183,7 @@ The above stacked bidirectional LSTM network extracts high-level features and ma
To reiterate, we can either invoke `convolution_net` or `stacked_lstm_net`. In below steps, we will go with `convolution_net`.
Next we define a `inference_program` that simply uses `convolution_net` to predict output with the input from `fluid.layer.data`.
Next we define an `inference_program` that simply uses `convolution_net` to predict output with the input from `fluid.layer.data`.
```python
def inference_program(word_dict):
......@@ -200,6 +200,7 @@ Also define `optimizer_func` to specify the optimizer.
In the context of supervised learning, labels of the training set are defined in `paddle.layer.data` too. During training, cross-entropy is used as loss function in `paddle.layer.classification_cost` and as the output of the network; During testing, the outputs are the probabilities calculated in the classifier.
First result that returns from the list must be cost.
```python
def train_program(word_dict):
......@@ -309,18 +310,38 @@ inferencer = fluid.Inferencer(
place=place)
```
### Create Lod Tensor with test data
To do inference, we pick 3 potential reviews out of our mind as testing data. Feel free to modify any of them.
We map each word in the reviews to id from `word_dict`, replaced by 'unknown' if the word is not in `word_dict`.
Then we create lod data with the id list and use `create_lod_tensor` to create lod tensor.
```python
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)
```
### Infer
Now we can infer with inputs that we provide in `feed_order` during training.
Now we can infer and predict probability of positive or negative from each review above.
```python
lod = [[3, 4, 2]]
base_shape = [1]
# The range of random integers is [low, high]
tensor_words = fluid.create_random_int_lodtensor(
lod, base_shape, place, low=0, high=len(word_dict) - 1)
results = inferencer.infer({'words': tensor_words})
print("infer results: ", results)
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], "\'")
```
......
06.understand_sentiment/index.html
浏览文件 @ 89d558cc
......@@ -225,7 +225,7 @@ The above stacked bidirectional LSTM network extracts high-level features and ma
To reiterate, we can either invoke `convolution_net` or `stacked_lstm_net`. In below steps, we will go with `convolution_net`.
Next we define a `inference_program` that simply uses `convolution_net` to predict output with the input from `fluid.layer.data`.
Next we define an `inference_program` that simply uses `convolution_net` to predict output with the input from `fluid.layer.data`.
```python
def inference_program(word_dict):
......@@ -242,6 +242,7 @@ Also define `optimizer_func` to specify the optimizer.
In the context of supervised learning, labels of the training set are defined in `paddle.layer.data` too. During training, cross-entropy is used as loss function in `paddle.layer.classification_cost` and as the output of the network; During testing, the outputs are the probabilities calculated in the classifier.
First result that returns from the list must be cost.
```python
def train_program(word_dict):
......@@ -351,18 +352,38 @@ inferencer = fluid.Inferencer(
place=place)
```
### Create Lod Tensor with test data
To do inference, we pick 3 potential reviews out of our mind as testing data. Feel free to modify any of them.
We map each word in the reviews to id from `word_dict`, replaced by 'unknown' if the word is not in `word_dict`.
Then we create lod data with the id list and use `create_lod_tensor` to create lod tensor.
```python
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)
```
### Infer
Now we can infer with inputs that we provide in `feed_order` during training.
Now we can infer and predict probability of positive or negative from each review above.
```python
lod = [[3, 4, 2]]
base_shape = [1]
# The range of random integers is [low, high]
tensor_words = fluid.create_random_int_lodtensor(
lod, base_shape, place, low=0, high=len(word_dict) - 1)
results = inferencer.infer({'words': tensor_words})
print("infer results: ", results)
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], "\'")
```
......
06.understand_sentiment/train_conv.py
浏览文件 @ 89d558cc
......@@ -69,14 +69,11 @@ def optimizer_func():
def train(use_cuda, train_program, params_dirname):
import time
place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
print("Loading IMDB word dict....")
word_dict = paddle.dataset.imdb.word_dict()
print("Reading training data....")
train_reader = paddle.batch(
paddle.reader.shuffle(
paddle.dataset.imdb.train(word_dict), buf_size=25000),
......@@ -95,18 +92,18 @@ def train(use_cuda, train_program, params_dirname):
def event_handler(event):
if isinstance(event, fluid.EndStepEvent):
avg_cost, acc = trainer.test(
reader=test_reader, feed_order=feed_order)
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}, 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, map(np.array, event.metrics)))
print("Step {0}, Epoch {1} Metrics {2}".format(
event.step, event.epoch, map(np.array, event.metrics)))
if event.step == 10: # Adjust this number for accuracy
trainer.save_params(params_dirname)
trainer.stop()
elif isinstance(event, fluid.EndEpochEvent):
trainer.save_params(params_dirname)
trainer.train(
num_epochs=1,
......@@ -134,13 +131,26 @@ def infer(use_cuda, inference_program, params_dirname=None):
# 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.
lod = [[3, 4, 2]]
base_shape = [1]
# The range of random integers is [low, high]
tensor_words = fluid.create_random_int_lodtensor(
lod, base_shape, place, low=0, high=len(word_dict) - 1)
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})
print("infer results: ", results)
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], "\'")
def main(use_cuda):
......
06.understand_sentiment/train_dyn_rnn.py
浏览文件 @ 89d558cc
......@@ -87,49 +87,46 @@ def optimizer_func():
def train(use_cuda, train_program, params_dirname):
place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
print("Loading IMDB word dict....")
word_dict = paddle.dataset.imdb.word_dict()
print("Reading training data....")
train_reader = paddle.batch(
paddle.reader.shuffle(
paddle.dataset.imdb.train(word_dict), buf_size=25000),
batch_size=BATCH_SIZE)
print("Reading testing data....")
test_reader = paddle.batch(
paddle.dataset.imdb.test(word_dict), batch_size=BATCH_SIZE)
trainer = fluid.Trainer(
train_func=partial(train_program, word_dict),
place=place,
optimizer_func=optimizer_func)
feed_order = ['words', 'label']
def event_handler(event):
if isinstance(event, fluid.EndEpochEvent):
test_reader = paddle.batch(
paddle.dataset.imdb.test(word_dict), batch_size=BATCH_SIZE)
avg_cost, acc = trainer.test(
reader=test_reader, feed_order=['words', 'label'])
print("avg_cost: %s" % avg_cost)
print("acc : %s" % acc)
if acc > 0.2: # Smaller value to increase CI speed
trainer.save_params(params_dirname)
trainer.stop()
else:
print('BatchID {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
event.epoch + 1, avg_cost, acc))
if math.isnan(avg_cost):
sys.exit("got NaN loss, training failed.")
elif isinstance(event, fluid.EndStepEvent):
print("Step {0}, Epoch {1} Metrics {2}".format(
event.step, event.epoch, map(np.array, event.metrics)))
if event.step == 1: # Run 2 iterations to speed CI
trainer.save_params(params_dirname)
trainer.stop()
if isinstance(event, fluid.EndStepEvent):
if event.step % 10 == 0:
avg_cost, acc = trainer.test(
reader=test_reader, feed_order=feed_order)
train_reader = paddle.batch(
paddle.reader.shuffle(
paddle.dataset.imdb.train(word_dict), buf_size=25000),
batch_size=BATCH_SIZE)
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, map(np.array, event.metrics)))
elif isinstance(event, fluid.EndEpochEvent):
trainer.save_params(params_dirname)
trainer.train(
num_epochs=1,
event_handler=event_handler,
reader=train_reader,
feed_order=['words', 'label'])
feed_order=feed_order)
def infer(use_cuda, inference_program, params_dirname=None):
......@@ -151,13 +148,26 @@ def infer(use_cuda, inference_program, params_dirname=None):
# 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.
lod = [[3, 4, 2]]
base_shape = [1]
# The range of random integers is [low, high]
tensor_words = fluid.create_random_int_lodtensor(
lod, base_shape, place, low=0, high=len(word_dict) - 1)
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})
print("infer results: ", results)
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], "\'")
def main(use_cuda):
......
06.understand_sentiment/train_stacked_lstm.py
浏览文件 @ 89d558cc
......@@ -78,49 +78,46 @@ def optimizer_func():
def train(use_cuda, train_program, params_dirname):
place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
print("Loading IMDB word dict....")
word_dict = paddle.dataset.imdb.word_dict()
print("Reading training data....")
train_reader = paddle.batch(
paddle.reader.shuffle(
paddle.dataset.imdb.train(word_dict), buf_size=25000),
batch_size=BATCH_SIZE)
print("Reading testing data....")
test_reader = paddle.batch(
paddle.dataset.imdb.test(word_dict), batch_size=BATCH_SIZE)
trainer = fluid.Trainer(
train_func=partial(train_program, word_dict),
place=place,
optimizer_func=optimizer_func)
feed_order = ['words', 'label']
def event_handler(event):
if isinstance(event, fluid.EndEpochEvent):
test_reader = paddle.batch(
paddle.dataset.imdb.test(word_dict), batch_size=BATCH_SIZE)
avg_cost, acc = trainer.test(
reader=test_reader, feed_order=['words', 'label'])
print("avg_cost: %s" % avg_cost)
print("acc : %s" % acc)
if acc > 0.2: # Smaller value to increase CI speed
trainer.save_params(params_dirname)
trainer.stop()
else:
print('BatchID {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
event.epoch + 1, avg_cost, acc))
if math.isnan(avg_cost):
sys.exit("got NaN loss, training failed.")
elif isinstance(event, fluid.EndStepEvent):
print("Step {0}, Epoch {1} Metrics {2}".format(
event.step, event.epoch, map(np.array, event.metrics)))
if event.step == 1: # Run 2 iterations to speed CI
trainer.save_params(params_dirname)
trainer.stop()
if isinstance(event, fluid.EndStepEvent):
if event.step % 10 == 0:
avg_cost, acc = trainer.test(
reader=test_reader, feed_order=feed_order)
train_reader = paddle.batch(
paddle.reader.shuffle(
paddle.dataset.imdb.train(word_dict), buf_size=25000),
batch_size=BATCH_SIZE)
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, map(np.array, event.metrics)))
elif isinstance(event, fluid.EndEpochEvent):
trainer.save_params(params_dirname)
trainer.train(
num_epochs=1,
event_handler=event_handler,
reader=train_reader,
feed_order=['words', 'label'])
feed_order=feed_order)
def infer(use_cuda, inference_program, params_dirname=None):
......@@ -142,13 +139,26 @@ def infer(use_cuda, inference_program, params_dirname=None):
# 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.
lod = [[3, 4, 2]]
base_shape = [1]
# The range of random integers is [low, high]
tensor_words = fluid.create_random_int_lodtensor(
lod, base_shape, place, low=0, high=len(word_dict) - 1)
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})
print("infer results: ", results)
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], "\'")
def main(use_cuda):
......
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