提交 80c9f661 编写于 作者: D dangqingqing

update

# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import paddle.v2 as paddle
__all__ = ['resnet_cifar10']
def conv_bn_layer(input,
ch_out,
filter_size,
stride,
padding,
active_type=paddle.activation.Relu(),
ch_in=None):
tmp = paddle.layer.img_conv(
input=input,
filter_size=filter_size,
num_channels=ch_in,
num_filters=ch_out,
stride=stride,
padding=padding,
act=paddle.activation.Linear(),
bias_attr=False)
return paddle.layer.batch_norm(input=tmp, act=active_type)
def shortcut(ipt, n_in, n_out, stride):
if n_in != n_out:
return conv_bn_layer(ipt, n_out, 1, stride, 0,
paddle.activation.Linear())
else:
return ipt
def basicblock(ipt, ch_out, stride):
ch_in = ch_out * 2
tmp = conv_bn_layer(ipt, ch_out, 3, stride, 1)
tmp = conv_bn_layer(tmp, ch_out, 3, 1, 1, paddle.activation.Linear())
short = shortcut(ipt, ch_in, ch_out, stride)
return paddle.layer.addto(input=[tmp, short], act=paddle.activation.Relu())
def layer_warp(block_func, ipt, features, count, stride):
tmp = block_func(ipt, features, stride)
for i in range(1, count):
tmp = block_func(tmp, features, 1)
return tmp
def resnet_cifar10(ipt, depth=32):
# depth should be one of 20, 32, 44, 56, 110, 1202
assert (depth - 2) % 6 == 0
n = (depth - 2) / 6
nStages = {16, 64, 128}
conv1 = conv_bn_layer(
ipt, ch_in=3, ch_out=16, filter_size=3, stride=1, padding=1)
res1 = layer_warp(basicblock, conv1, 16, n, 1)
res2 = layer_warp(basicblock, res1, 32, n, 2)
res3 = layer_warp(basicblock, res2, 64, n, 2)
pool = paddle.layer.img_pool(
input=res3, pool_size=8, stride=1, pool_type=paddle.pooling.Avg())
return pool
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License
import sys
import paddle.v2 as paddle
from api_v2_vgg import vgg_bn_drop
from api_v2_resnet import resnet_cifar10
def main():
datadim = 3 * 32 * 32
classdim = 10
# PaddlePaddle init
paddle.init(use_gpu=True, trainer_count=1)
image = paddle.layer.data(
name="image", type=paddle.data_type.dense_vector(datadim))
# Add neural network config
# option 1. resnet
net = resnet_cifar10(image, depth=32)
# option 2. vgg
# net = vgg_bn_drop(image)
out = paddle.layer.fc(input=net,
size=classdim,
act=paddle.activation.Softmax())
lbl = paddle.layer.data(
name="label", type=paddle.data_type.integer_value(classdim))
cost = paddle.layer.classification_cost(input=out, label=lbl)
# Create parameters
parameters = paddle.parameters.create(cost)
# Create optimizer
momentum_optimizer = paddle.optimizer.Momentum(
momentum=0.9,
regularization=paddle.optimizer.L2Regularization(rate=0.0002 * 128),
learning_rate=0.1 / 128.0,
learning_rate_decay_a=0.1,
learning_rate_decay_b=50000 * 100,
learning_rate_schedule='discexp',
batch_size=128)
# End batch and end pass event handler
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 100 == 0:
print "\nPass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
else:
sys.stdout.write('.')
sys.stdout.flush()
if isinstance(event, paddle.event.EndPass):
result = trainer.test(
reader=paddle.reader.batched(
paddle.dataset.cifar.test10(), batch_size=128),
reader_dict={'image': 0,
'label': 1})
print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
# Create trainer
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=momentum_optimizer)
trainer.train(
reader=paddle.reader.batched(
paddle.reader.shuffle(
paddle.dataset.cifar.train10(), buf_size=50000),
batch_size=128),
num_passes=5,
event_handler=event_handler,
reader_dict={'image': 0,
'label': 1})
if __name__ == '__main__':
main()
# Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import paddle.v2 as paddle
__all__ = ['vgg_bn_drop']
def vgg_bn_drop(input):
def conv_block(ipt, num_filter, groups, dropouts, num_channels=None):
return paddle.networks.img_conv_group(
input=ipt,
num_channels=num_channels,
pool_size=2,
pool_stride=2,
conv_num_filter=[num_filter] * groups,
conv_filter_size=3,
conv_act=paddle.activation.Relu(),
conv_with_batchnorm=True,
conv_batchnorm_drop_rate=dropouts,
pool_type=paddle.pooling.Max())
conv1 = conv_block(input, 64, 2, [0.3, 0], 3)
conv2 = conv_block(conv1, 128, 2, [0.4, 0])
conv3 = conv_block(conv2, 256, 3, [0.4, 0.4, 0])
conv4 = conv_block(conv3, 512, 3, [0.4, 0.4, 0])
conv5 = conv_block(conv4, 512, 3, [0.4, 0.4, 0])
drop = paddle.layer.dropout(input=conv5, dropout_rate=0.5)
fc1 = paddle.layer.fc(input=drop, size=512, act=paddle.activation.Linear())
bn = paddle.layer.batch_norm(
input=fc1,
act=paddle.activation.Relu(),
layer_attr=paddle.attr.Extra(drop_rate=0.5))
fc2 = paddle.layer.fc(input=bn, size=512, act=paddle.activation.Linear())
return fc2
......@@ -40,8 +40,7 @@ def main():
reader_dict={'x': 0,
'y': 1})
if event.pass_id % 10 == 0:
print "Test %d, Cost %f, %s" % (event.pass_id, event.cost,
result.metrics)
print "Test %d, %s" % (event.pass_id, result.metrics)
# training
trainer.train(
......
......@@ -142,6 +142,20 @@ Parameter* GradientMachine::getParameter(size_t i) throw(RangeError) {
}
}
size_t GradientMachine::getNonStaticParameterSize() const {
return m->machine->getNonStaticParameters().size();
}
Parameter* GradientMachine::getNonStaticParameter(size_t i) throw(RangeError) {
auto params = m->machine->getNonStaticParameters();
if (i < params.size()) {
return Parameter::createFromSharedPtr(
&m->machine->getNonStaticParameters()[i]);
} else {
throw RangeError();
}
}
void GradientMachine::randParameters() { m->machine->randParameters(); }
Arguments* GradientMachine::getLayerOutput(const std::string& layerName) const
......
......@@ -771,6 +771,9 @@ public:
size_t getParameterSize() const;
Parameter* getParameter(size_t i) throw(RangeError);
size_t getNonStaticParameterSize() const;
Parameter* getNonStaticParameter(size_t i) throw(RangeError);
void randParameters();
Arguments* getLayerOutput(const std::string& layerName) const
......
......@@ -195,6 +195,12 @@ def __monkeypatch_gradient_machine__():
swig_paddle.GradientMachine.getParameters = getParameters
def getNonStaticParameters(self):
return (self.getNonStaticParameter(i)
for i in xrange(self.getNonStaticParameterSize()))
swig_paddle.GradientMachine.getNonStaticParameters = getNonStaticParameters
def getLayerOutputs(self, layerNames):
"""
getLayerOutputs. get outputs of layers and return a numpy matrix dict.
......
import mnist
import imikolov
import imdb
import cifar
import movielens
import uci_housing
__all__ = ['mnist', 'uci_housing']
__all__ = ['mnist', 'imikolov', 'imdb', 'cifar', 'movielens', 'uci_housing']
......@@ -120,7 +120,8 @@ class SGD(ITrainer):
feeder(data_batch), out_args, pass_type)
self.__gradient_machine__.eval(pass_evaluator)
self.__gradient_machine__.eval(batch_evaluator)
for each_param in self.__gradient_machine__.getParameters():
for each_param in self.__gradient_machine__.getNonStaticParameters(
):
updater.update(each_param)
# Get cost. We use numpy to calculate total cost for this batch.
cost_vec = out_args.getSlotValue(0)
......
Markdown is supported
0% .
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