百度一直使用自己開發的一個深度學習框架Padddle，以前沒有接觸過，最近剛好有機會來學習一下，先來看一下它怎麼安裝。

一、安裝百度的深度學習框架Paddle

使用官方提供的pip命令安裝

pip install paddlepaddle-gpu

發現會出現下面的問題

使用pip命令安裝一直報錯，可以選擇下載whl包安裝。

使用whl包安裝

（1）下載安裝包

網址：https://pypi.doubanio.com/simple/

在上面網頁中找到paddlepaddle和paddlepaddle-gpu，這是cpu和gpu的安裝包，選擇需要安裝的點進去，我需要安裝GPU版本的，所以選擇paddlepaddle-gpu。

在這個網址下選擇你需要的安裝包下載，注意python版本和cp後數字一致，CUDA版本和cuDnn版本和post後數字一致，不一致可能會報錯。

（2）在命令行下使用pip install "name+.whl"安裝paddle。

（3）測試安裝，安裝完後使用import paddle導入paddle包，沒有報錯則安裝成功了，下一步開始學習吧。

二、Paddlepaddle框架的使用

看一下官方給出的例子

（1）導入Paddlepaddle，配置網絡

# Include libraries.import paddle
import paddle.fluid as fluid
import numpy

# Configure the neural network.
def net(x, y):
 y_predict = fluid.layers.fc(input=x, size=1, act=None)
 cost = fluid.layers.square_error_cost(input=y_predict, label=y)
 avg_cost = fluid.layers.mean(cost)
 return y_predict, avg_cost

（2）定義訓練和預測函數

# Include libraries.import paddle
import paddle.fluid as fluid
import numpy

# Configure the neural network.
def net(x, y):
 y_predict = fluid.layers.fc(input=x, size=1, act=None)
 cost = fluid.layers.square_error_cost(input=y_predict, label=y)
 avg_cost = fluid.layers.mean(cost)
 return y_predict, avg_cost

# Define train function.
def train(save_dirname):
 x = fluid.layers.data(name='x', shape=[13], dtype='float32')
 y = fluid.layers.data(name='y', shape=[1], dtype='float32')
 y_predict, avg_cost = net(x, y)
 sgd_optimizer = fluid.optimizer.SGD(learning_rate=0.001)
 sgd_optimizer.minimize(avg_cost)
 train_reader = paddle.batch(
 paddle.reader.shuffle(paddle.dataset.uci_housing.train(), buf_size=500),
 batch_size=20)
 place = fluid.CPUPlace()
 exe = fluid.Executor(place)
 
 def train_loop(main_program):
 feeder = fluid.DataFeeder(place=place, feed_list=[x, y])
 exe.run(fluid.default_startup_program())

 PASS_NUM = 1000
 for pass_id in range(PASS_NUM):
 total_loss_pass = 0 

 for data in train_reader():
 avg_loss_value, = exe.run(
 main_program, feed=feeder.feed(data), fetch_list=[avg_cost])
 total_loss_pass += avg_loss_value
 if avg_loss_value < 5.0:
 if save_dirname is not None:
 fluid.io.save_inference_model(
 save_dirname, ['x'], [y_predict], exe)
 return
 print("Pass %d, total avg cost = %f" % (pass_id, total_loss_pass))
 t
 rain_loop(fluid.default_main_program())

# Infer by using provided test data.
def infer(save_dirname=None):
 place = fluid.CPUPlace()
 exe = fluid.Executor(place)
 inference_scope = fluid.core.Scope()
 with fluid.scope_guard(inference_scope):
 [inference_program, feed_target_names, fetch_targets] = (
 fluid.io.load_inference_model(save_dirname, exe))
 test_reader = paddle.batch(paddle.dataset.uci_housing.test(), batch_size=20)
 test_data = test_reader().next()
 test_feat = numpy.array(map(lambda x: x[0], test_data)).astype("float32")
 test_label = numpy.array(map(lambda x: x[1], test_data)).astype("float32")
 results = exe.run(inference_program,
 feed={feed_target_names[0]: numpy.array(test_feat)},
 fetch_list=fetch_targets)
 print("infer results: ", results[0])
 print("ground truth: ", test_label)

（3）執行訓練和預測

# Include libraries.import paddle
import paddle.fluid as fluid
import numpy

# Configure the neural network.
def net(x, y):
 y_predict = fluid.layers.fc(input=x, size=1, act=None)
 cost = fluid.layers.square_error_cost(input=y_predict, label=y)
 avg_cost = fluid.layers.mean(cost)
 return y_predict, avg_cost

# Define train function.
def train(save_dirname):
 x = fluid.layers.data(name='x', shape=[13], dtype='float32')
 y = fluid.layers.data(name='y', shape=[1], dtype='float32')
 y_predict, avg_cost = net(x, y) 

 sgd_optimizer = fluid.optimizer.SGD(learning_rate=0.001)
 sgd_optimizer.minimize(avg_cost)
 train_reader = paddle.batch(
 paddle.reader.shuffle(paddle.dataset.uci_housing.train(), buf_size=500),
 batch_size=20)
 place = fluid.CPUPlace()
 exe = fluid.Executor(place)

 def train_loop(main_program):
 feeder = fluid.DataFeeder(place=place, feed_list=[x, y])
 exe.run(fluid.default_startup_program())
 PASS_NUM = 1000
 for pass_id in range(PASS_NUM):
 total_loss_pass = 0
 for data in train_reader():
 avg_loss_value, = exe.run(
 main_program, feed=feeder.feed(data), fetch_list=[avg_cost])
 total_loss_pass += avg_loss_value
 if avg_loss_value < 5.0:
 if save_dirname is not None:
 fluid.io.save_inference_model(
 save_dirname, ['x'], [y_predict], exe)
 return
 print("Pass %d, total avg cost = %f" % (pass_id, total_loss_pass))

 train_loop(fluid.default_main_program())

# Infer by using provided test data.
def infer(save_dirname=None):
 place = fluid.CPUPlace()
 exe = fluid.Executor(place)
 inference_scope = fluid.core.Scope()
 with fluid.scope_guard(inference_scope):
 [inference_program, feed_target_names, fetch_targets] = (
 fluid.io.load_inference_model(save_dirname, exe))
 test_reader = paddle.batch(paddle.dataset.uci_housing.test(), batch_size=20)
 test_data = test_reader().next()
 test_feat = numpy.array(map(lambda x: x[0], test_data)).astype("float32")
 test_label = numpy.array(map(lambda x: x[1], test_data)).astype("float32")
 results = exe.run(inference_program,
 feed={feed_target_names[0]: numpy.array(test_feat)},
 fetch_list=fetch_targets)
 print("infer results: ", results[0])
 print("ground truth: ", test_label)


# Run train and infer.
if __name__ == "__main__":
 save_dirname = "fit_a_line.inference.model"
 train(save_dirname) 

 infer(save_dirname)