def get_trainer(self, datadim, type_size, parameters_path):
# 获得图片对于的信息标签
label = paddle.layer.data(name="label",
type=paddle.data_type.integer_value(type_size))
# 获取全连接层,也就是分类器
out = vgg_bn_drop(datadim=datadim, type_size=type_size)
# out = convolutional_neural_network(datadim=datadim, type_size=type_size)
# 获得损失函数
cost = paddle.layer.classification_cost(input=out, label=label)
# 获得参数
if not parameters_path:
parameters = self.get_parameters(cost=cost)
else:
parameters = self.get_parameters(parameters_path=parameters_path)
'''
定义优化方法
learning_rate 迭代的速度
momentum 跟前面动量优化的比例
regularzation 正则化,防止过拟合
'''
# ********************如果使用VGG网络模型就用这个优化方法******************
optimizer = paddle.optimizer.Momentum(
momentum=0.9,
regularization=paddle.optimizer.L2Regularization(rate=0.0005 * 128),
learning_rate=0.0001 / 128,
learning_rate_decay_a=0.1,
learning_rate_decay_b=128000 * 35,
learning_rate_schedule="discexp", )
# ********************如果使用LeNet-5网络模型就用这个优化方法******************
# optimizer = paddle.optimizer.Momentum(learning_rate=0.00001 / 128.0,
# momentum=0.9,
# regularization=paddle.optimizer.L2Regularization(rate=0.005 * 128))
'''
创建训练器
cost 分类器
parameters 训练参数,可以通过创建,也可以使用之前训练好的参数
update_equation 优化方法
'''
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=optimizer)
return trainer
def get_trainer(self):
# 数据大小
datadim = 3 * 32 * 32
# 获得图片对于的信息标签
lbl = paddle.layer.data(name="label",
type=paddle.data_type.integer_value(10))
# 获取全连接层,也就是分类器
#
out = vgg_bn_drop(datadim=datadim)
# out = resnet_cifar10(datadim=datadim)
# 获得损失函数
cost = paddle.layer.classification_cost(input=out, label=lbl)
# 使用之前保存好的参数文件获得参数
# parameters = self.get_parameters(parameters_path="../model/model.tar")
# 使用损失函数生成参数
parameters = self.get_parameters(cost=cost)
'''
定义优化方法
learning_rate 学习率
momentum 跟前面动量优化的比例
regularzation 正则化,防止过拟合
'''
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")
'''
创建训练器
cost 分类器
parameters 训练参数,可以通过创建,也可以使用之前训练好的参数
update_equation 优化方法
'''
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=momentum_optimizer)
return trainer
def main():
datadim = 3 * 32 * 32
classdim = 10
# PaddlePaddle init
paddle.init(use_gpu=with_gpu, 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')
# Create trainer
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=momentum_optimizer)
# 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):
# save parameters
with open('params_pass_%d.tar' % event.pass_id, 'w') as f:
trainer.save_parameter_to_tar(f)
result = trainer.test(reader=paddle.batch(
paddle.dataset.cifar.test10(), batch_size=128),
feeding={
'image': 0,
'label': 1
})
print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
# Save the inference topology to protobuf.
inference_topology = paddle.topology.Topology(layers=out)
with open("inference_topology.pkl", 'wb') as f:
inference_topology.serialize_for_inference(f)
trainer.train(reader=paddle.batch(paddle.reader.shuffle(
paddle.dataset.cifar.train10(), buf_size=50000),
batch_size=128),
num_passes=200,
event_handler=event_handler,
feeding={
'image': 0,
'label': 1
})
# inference
from PIL import Image
import numpy as np
import os
def load_image(file):
im = Image.open(file)
im = im.resize((32, 32), Image.ANTIALIAS)
im = np.array(im).astype(np.float32)
# The storage order of the loaded image is W(widht),
# H(height), C(channel). PaddlePaddle requires
# the CHW order, so transpose them.
im = im.transpose((2, 0, 1)) # CHW
# In the training phase, the channel order of CIFAR
# image is B(Blue), G(green), R(Red). But PIL open
# image in RGB mode. It must swap the channel order.
im = im[(2, 1, 0), :, :] # BGR
im = im.flatten()
im = im / 255.0
return im
test_data = []
cur_dir = os.path.dirname(os.path.realpath(__file__))
test_data.append((load_image(cur_dir + '/image/dog.png'), ))
# users can remove the comments and change the model name
# with open('params_pass_50.tar', 'r') as f:
# parameters = paddle.parameters.Parameters.from_tar(f)
probs = paddle.infer(output_layer=out,
parameters=parameters,
input=test_data)
lab = np.argsort(-probs) # probs and lab are the results of one batch data
print "Label of image/dog.png is: %d" % lab[0][0]
if __name__ == '__main__':
paddle.init(use_gpu=False, trainer_count=2)
# 类别总数
type_size = 5
# 图片大小
imageSize = 200
# 保存的model路径
parameters_path = "../model/model.tar"
# 数据的大小
datadim = 3 * imageSize * imageSize
# *******************************开始预测**************************************
# 添加数据
image_path = []
image_path.append(
"../images/vegetables/loofah/71070c44-4dd7-11e8-8192-3c970e769528.jpg")
image_path.append(
"../images/vegetables/pumpkin/d9fcc518-4dd7-11e8-8192-3c970e769528.jpg"
)
image_path.append(
"../images/vegetables/baby_cabbage/45cad792-4dd5-11e8-8192-3c970e769528.jpg"
)
out = vgg_bn_drop(datadim=datadim, type_size=type_size)
parameters = get_parameters(parameters_path=parameters_path)
all_result = to_prediction(image_paths=image_path,
parameters=parameters,
out=out,
imageSize=imageSize)
for i in range(0, all_result.__len__()):
print '预测结果为:%d,可信度为:%f' % (all_result[i][0], all_result[i][1])
datadim = 3 * 32 * 32
# 分类的维度
classdim = 10
# PaddlePaddle init
paddle.init(use_gpu=with_gpu, 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)
# 预测分类输出值
out = paddle.layer.fc(
input=net, size=classdim, act=paddle.activation.Softmax())
# 真实标签值
lbl = paddle.layer.data(
name="label", type=paddle.data_type.integer_value(classdim))
# 输出值和真实值之间的损失
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,
# CIFAR训练图片通道顺序为B(蓝),G(绿),R(红),
# 而PIL打开图片默认通道顺序为RGB,因为需要交换通道。
im = im[(2, 1, 0), :, :] # BGR
im = im.flatten()
im = im / 255.0
return im
# 获得要预测的图片
test_data = []
test_data.append((load_image(image_path), ))
# 获得预测结果
probs = paddle.infer(output_layer=out,
parameters=parameters,
input=test_data)
# 处理预测结果
lab = np.argsort(-probs)
# 返回概率最大的值和其对应的概率值
return lab[0][0], probs[0][(lab[0][0])]
if __name__ == '__main__':
testCIFAR = TestCIFAR()
# 开始预测
out = vgg_bn_drop(3 * 32 * 32)
parameters = testCIFAR.get_parameters("../model/model.tar")
image_path = "../images/airplane1.png"
result, probability = testCIFAR.to_prediction(image_path=image_path,
out=out,
parameters=parameters)
print '预测结果为:%d,可信度为:%f' % (result, probability)
