Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into macosx
liaogang
8 years ago
commit
7955e3fca5
@ -0,0 +1,61 @@
|
||||
import numpy
|
||||
import paddle.v2 as paddle
|
||||
|
||||
import mnist_util
|
||||
|
||||
|
||||
def train_reader():
|
||||
train_file = './data/raw_data/train'
|
||||
generator = mnist_util.read_from_mnist(train_file)
|
||||
for item in generator:
|
||||
yield item
|
||||
|
||||
|
||||
def main():
|
||||
paddle.init(use_gpu=False, trainer_count=1)
|
||||
|
||||
# define network topology
|
||||
images = paddle.layer.data(
|
||||
name='pixel', type=paddle.data_type.dense_vector(784))
|
||||
label = paddle.layer.data(
|
||||
name='label', type=paddle.data_type.integer_value(10))
|
||||
hidden1 = paddle.layer.fc(input=images, size=200)
|
||||
hidden2 = paddle.layer.fc(input=hidden1, size=200)
|
||||
inference = paddle.layer.fc(input=hidden2,
|
||||
size=10,
|
||||
act=paddle.activation.Softmax())
|
||||
cost = paddle.layer.classification_cost(input=inference, label=label)
|
||||
|
||||
parameters = paddle.parameters.create(cost)
|
||||
for param_name in parameters.keys():
|
||||
array = parameters.get(param_name)
|
||||
array[:] = numpy.random.uniform(low=-1.0, high=1.0, size=array.shape)
|
||||
parameters.set(parameter_name=param_name, value=array)
|
||||
|
||||
adam_optimizer = paddle.optimizer.Adam(learning_rate=0.01)
|
||||
|
||||
def event_handler(event):
|
||||
if isinstance(event, paddle.event.EndIteration):
|
||||
para = parameters.get('___fc_2__.w0')
|
||||
print "Pass %d, Batch %d, Cost %f, Weight Mean Of Fc 2 is %f" % (
|
||||
event.pass_id, event.batch_id, event.cost, para.mean())
|
||||
|
||||
else:
|
||||
pass
|
||||
|
||||
trainer = paddle.trainer.SGD(update_equation=adam_optimizer)
|
||||
|
||||
trainer.train(train_data_reader=train_reader,
|
||||
topology=cost,
|
||||
parameters=parameters,
|
||||
event_handler=event_handler,
|
||||
batch_size=32, # batch size should be refactor in Data reader
|
||||
data_types={ # data_types will be removed, It should be in
|
||||
# network topology
|
||||
'pixel': images.type,
|
||||
'label': label.type
|
||||
})
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,161 @@
|
||||
# Python Data Reader Design Doc
|
||||
|
||||
At training and testing time, PaddlePaddle programs need to read data. To ease the users' work to write data reading code, we define that
|
||||
|
||||
- A *reader* is a function that reads data (from file, network, random number generator, etc) and yields data items.
|
||||
- A *reader creator* is a function that returns a reader function.
|
||||
- A *reader* decorator is a function, which accepts one or more readers, and returns a reader.
|
||||
|
||||
and provide frequently used reader creators and reader decorators.
|
||||
|
||||
## Data Reader Interface
|
||||
|
||||
Indeed, *data reader* doesn't have to be a function that reads and yields data items. It can be any function with no parameter that creates a iterable (anything can be used in `for x in iterable`):
|
||||
|
||||
```
|
||||
iterable = data_reader()
|
||||
```
|
||||
|
||||
Element produced from the iterable should be a **single** entry of data, **not** a mini batch. That entry of data could be a single item, or a tuple of items. Item should be of [supported type](http://www.paddlepaddle.org/doc/ui/data_provider/pydataprovider2.html?highlight=dense_vector#input-types) (e.g., numpy 1d array of float32, int, list of int)
|
||||
|
||||
An example implementation for single item data reader creator:
|
||||
|
||||
```python
|
||||
def reader_creator_random_image(width, height):
|
||||
def reader():
|
||||
while True:
|
||||
yield numpy.random.uniform(-1, 1, size=width*height)
|
||||
return reader
|
||||
```
|
||||
|
||||
An example implementation for multiple item data reader creator:
|
||||
```python
|
||||
def reader_creator_random_imageand_label(widht, height, label):
|
||||
def reader():
|
||||
while True:
|
||||
yield numpy.random.uniform(-1, 1, size=width*height), label
|
||||
return reader
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
data reader, mapping from item(s) read to data layer, batch size and number of total pass will be passed into `paddle.train`:
|
||||
|
||||
```python
|
||||
# two data layer is created:
|
||||
image_layer = paddle.layer.data("image", ...)
|
||||
label_layer = paddle.layer.data("label", ...)
|
||||
|
||||
# ...
|
||||
|
||||
paddle.train(paddle.dataset.mnist, {"image":0, "label":1}, 128, 10, ...)
|
||||
```
|
||||
|
||||
## Data Reader Decorator
|
||||
|
||||
*Data reader decorator* takes a single or multiple data reader, returns a new data reader. It is similar to a [python decorator](https://wiki.python.org/moin/PythonDecorators), but it does not use `@` syntax.
|
||||
|
||||
Since we have a strict interface for data readers (no parameter, return a single data item). Data reader can be used flexiable via data reader decorators. Following are a few examples:
|
||||
|
||||
### Prefetch Data
|
||||
|
||||
Since reading data may take time and training can not proceed without data. It is generally a good idea to prefetch data.
|
||||
|
||||
Use `paddle.reader.buffered` to prefetch data:
|
||||
|
||||
```python
|
||||
buffered_reader = paddle.reader.buffered(paddle.dataset.mnist, 100)
|
||||
```
|
||||
|
||||
`buffered_reader` will try to buffer (prefetch) `100` data entries.
|
||||
|
||||
### Compose Multiple Data Readers
|
||||
|
||||
For example, we want to use a source of real images (reusing mnist dataset), and a source of random images as input for [Generative Adversarial Networks](https://arxiv.org/abs/1406.2661).
|
||||
|
||||
We can do:
|
||||
|
||||
```python
|
||||
def reader_creator_random_image(width, height):
|
||||
def reader():
|
||||
while True:
|
||||
yield numpy.random.uniform(-1, 1, size=width*height)
|
||||
return reader
|
||||
|
||||
def reader_creator_bool(t):
|
||||
def reader:
|
||||
while True:
|
||||
yield t
|
||||
return reader
|
||||
|
||||
true_reader = reader_creator_bool(True)
|
||||
false_reader = reader_creator_bool(False)
|
||||
|
||||
reader = paddle.reader.compose(paddle.dataset.mnist, data_reader_creator_random_image(20, 20), true_reader, false_reader)
|
||||
# Skipped 1 because paddle.dataset.mnist produces two items per data entry.
|
||||
# And we don't care second item at this time.
|
||||
paddle.train(reader, {"true_image":0, "fake_image": 2, "true_label": 3, "false_label": 4}, ...)
|
||||
```
|
||||
|
||||
### Shuffle
|
||||
|
||||
Given shuffle buffer size `n`, `paddle.reader.shuffle` will return a data reader that buffers `n` data entries and shuffle them before a data entry is read.
|
||||
|
||||
Example:
|
||||
```python
|
||||
reader = paddle.reader.shuffle(paddle.dataset.mnist, 512)
|
||||
```
|
||||
|
||||
## Q & A
|
||||
|
||||
### Why return only a single entry, but not a mini batch?
|
||||
|
||||
If a mini batch is returned, data reader need to take care of batch size. But batch size is a concept for training, it makes more sense for user to specify batch size as a parameter for `train`.
|
||||
|
||||
Practically, always return a single entry make reusing existing data readers much easier (e.g., if existing reader return not a single entry but 3 entries, training code will be more complex because it need to handle cases like batch size 2).
|
||||
|
||||
### Why use a dictionary but not a list to provide mapping?
|
||||
|
||||
We decided to use dictionary (`{"image":0, "label":1}`) instead of list (`["image", "label"]`) is because that user can easily resue item (e.g., using `{"image_a":0, "image_b":0, "label":1}`) or skip item (e.g., using `{"image_a":0, "label":2}`).
|
||||
|
||||
### How to create custom data reader creator
|
||||
|
||||
```python
|
||||
def image_reader_creator(image_path, label_path, n):
|
||||
def reader():
|
||||
f = open(image_path)
|
||||
l = open(label_path)
|
||||
images = numpy.fromfile(
|
||||
f, 'ubyte', count=n * 28 * 28).reshape((n, 28 * 28)).astype('float32')
|
||||
images = images / 255.0 * 2.0 - 1.0
|
||||
labels = numpy.fromfile(l, 'ubyte', count=n).astype("int")
|
||||
for i in xrange(n):
|
||||
yield images[i, :], labels[i] # a single entry of data is created each time
|
||||
f.close()
|
||||
l.close()
|
||||
return reader
|
||||
|
||||
# images_reader_creator creates a reader
|
||||
reader = image_reader_creator("/path/to/image_file", "/path/to/label_file", 1024)
|
||||
paddle.train(reader, {"image":0, "label":1}, ...)
|
||||
```
|
||||
|
||||
### How is `paddle.train` implemented
|
||||
|
||||
An example implementation of paddle.train could be:
|
||||
|
||||
```python
|
||||
def make_minibatch(reader, minibatch_size):
|
||||
def ret():
|
||||
r = reader()
|
||||
buf = [r.next() for x in xrange(minibatch_size)]
|
||||
while len(buf) > 0:
|
||||
yield buf
|
||||
buf = [r.next() for x in xrange(minibatch_size)]
|
||||
return ret
|
||||
|
||||
def train(reader, mapping, batch_size, total_pass):
|
||||
for pass_idx in range(total_pass):
|
||||
for mini_batch in make_minibatch(reader): # this loop will never end in online learning.
|
||||
do_forward_backward(mini_batch, mapping)
|
||||
```
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in new issue