Installation

Dependency

sudo apt-get install build-essential -y #必要的编译工具依赖
sudo apt-get install --no-install-recommends libboost-all-dev
sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev
sudo apt-get install libatlas-base-dev

sudo apt-get install libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libhdf5-serial-dev protobuf-compiler

sudo apt-get install libblas-dev liblapack-dev libatlas-base-dev gfortran python-numpy 

cd ~/caffe/python
sudo su # 使用超级权限
for req in $(cat "requirements.txt"); do pip install -i https://pypi.tuna.tsinghua.edu.cn/simple $req; done

python

sudo pip install hypothesis
sudo pip install six
sudo pip install pydot

NCCL

多GPU交互在神经网络是常见的, 所以在安装caffe2之前需要安装NCCL, 来保证多GPU之间的相互交流:

git clone https://gitee.com/ares1899/xyport-nccl
#rename xyport-nccl to nccl
cd nccl
make CUDA_HOME=/user/local/cuda test

#test
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:./build/lib
./build/test/single/all_reduce_test
./build/test/single/all_reduce_test 10000000
make install

Caffe2

下载caffe2, 其中的--recuresive不能丢掉，否则会无法下载第三方库:

git clone --recuresive https://gitee.com/ares1899/xyport-caffe2

Build

rename xyport-caffe2 -> caffe2

cd caffe2
./scripts/build_tegra_x1.sh

cd caffe2
make -j
cd build
make install

cmake 过程中可能会出现 Eigen 相关的错误，可以修改caffe2 的文件 ./cmake/Dependencies.cmake:

# Dependencies.cmake

# ---[ EIGEN
# Due to license considerations, we will only use the MPL2 parts of Eigen.
set(EIGEN_MPL2_ONLY 1)
find_package(Eigen3)
if(EIGEN3_FOUND)
  message(STATUS "Found system Eigen at " ${EIGEN3_INCLUDE_DIR})
  include_directories(${EIGEN3_INCLUDE_DIR})
else()
message("Eigen: Using third party subdirectory.")
include_directories(${PROJECT_SOURCE_DIR}/third_party/eigen)
endif()



#CHANGING TO:

set(EIGEN_MPL2_ONLY 1)
message("Eigen: Using third party subdirectory.")
include_directories(${PROJECT_SOURCE_DIR}/third_party/eigen)

数值数序数量

export PYTHONPATH=~/caffe2/caffe2/python:~/caffe2/build:$PYTHONPATH

Operator with engine CUDNN is not available for operator ReluGradient.

数据 Data

写一个简单的多层神经网络并训练:

数据如何定义：训练数据和网络参数以什么形式aru?

数据如何流动：训练数据经过哪些运算得到输出?

数据如何训练：使用什么样的梯度更新方法与参数?

*caffe

blob: 数据和权值储存在Blob类的实例当中;
layer: 对数据最基本的运算单位是layer. 每一层(layer) 定义了不同的计算方式, 输入blobs经过不同层相应的运算往前传递, 得到输出blobs;
net: 由多个layers组成, 构成整体的计算网络;
solver: 使用solver类来给定梯度更新的规则, 当数据流动的方式构建好了, 反向传递的梯度计算的方式也确定, 网络在solver的控制下, 不断让数据前传, 再反传求梯度, 再使用梯度更新权值, 循环往复.

Caffe2

caffe2中, operator取代了caffe中layer作为net的基本构造单位, 其接受一串输入, 产生一串输出. operator的接口定义在 caffe2/proto/caffe2.proto:

e.g.1 可以使用一个InnerProduct操作运输符号来完成InnerProductLayer的功能。

workspace*: 可以理解成变量的空间，便于管理网络和变量
blob: 数据和权值储存在Blob类的实例当中;
operator: 输入blob, 输出blob, 定义了计算规则;
net: 由多个operator组合实现

详见:

Caffe2 初探 https://my.oschina.net/ares1899/blog/1649363

Python Profile

先导入caffe2.core和workspace，基础的类和函数都在其中

导入caffe2.proto来对protobuf文件进行必要操作。

# We'll also import a few standard python libraries
from matplotlib import pyplot
import numpy as np
import time

# These are the droids you are looking for.
from caffe2.python import core, workspace
from caffe2.proto import caffe2_pb2
# Let's show all plots inline.
%matplotlib inline

workspace

我们可以把定义好的数据blob或net放到都在一个workspace中，也可以用不用的workspace来区分。

下面我们打印一下当前workspace中blob情况。Blobs()取出blob，HasBlobs(name)判断是否有此名字的blob。

print("Current blobs in the workspace: {}".format(workspace.Blobs()))
print("Workspace has blob 'X'? {}".format(workspace.HasBlob("X")))

一开始，当然结果是啥也没有。

我们使用FeedBlob来给当前workspace添加blob，再打印出来：

X = np.random.randn(2, 3).astype(np.float32)
print("Generated X from numpy:\n{}".format(X))
workspace.FeedBlob("X", X)

Generated X from numpy:
[[-0.56927377 -1.28052795 -0.95808828]
 [-0.44225693 -0.0620895  -0.50509363]]

print("Current blobs in the workspace: {}".format(workspace.Blobs()))
print("Workspace has blob 'X'? {}".format(workspace.HasBlob("X")))
print("Fetched X:\n{}".format(workspace.FetchBlob("X")))

Current blobs in the workspace: [u'X']
Workspace has blob 'X'? True
Fetched X:
[[-0.56927377 -1.28052795 -0.95808828]
 [-0.44225693 -0.0620895  -0.50509363]]

当然，我们也用多个名字定义多个workspace，并且可以切换工作空间。我们可以使用currentworkspace()在访问当前工作空间，使用switchworkspace(name)来切换工作空间。

print("Current workspace: {}".format(workspace.CurrentWorkspace()))
print("Current blobs in the workspace: {}".format(workspace.Blobs()))

# Switch the workspace. The second argument "True" means creating
# the workspace if it is missing.
workspace.SwitchWorkspace("gutentag", True)

# Let's print the current workspace. Note that there is nothing in the
# workspace yet.
print("Current workspace: {}".format(workspace.CurrentWorkspace()))
print("Current blobs in the workspace: {}".format(workspace.Blobs()))

Current workspace: default
Current blobs in the workspace: ['X']
Current workspace: gutentag
Current blobs in the workspace: []

Operators

使用core.CreateOperator来直接创造;
使用core.Net来访问创建operator;
使用modelHelper来访问创建operators.

在这里我们使用core.CreateOperator来简单理解operator，在实际情况下，我们创建网络的时候，不会直接创建每个operator，这样太麻烦，一般使用modelhelper来帮忙我们创建网络。

# Create an operator.
op = core.CreateOperator(
    "Relu", # The type of operator that we want to run
    ["X"], # A list of input blobs by their names
    ["Y"], # A list of output blobs by their names
)
# and we are done!

上面的代码创建了一个Relu运算符，在这里需要知道，在python中创建一个operator，只是定义了一个operator，其实并没有运行这个operator。在上面代码中创建的op，实际上是一个protobuf对象。

print("Type of the created op is: {}".format(type(op)))
print("Content:\n")
print(str(op))

Type of the created op is: 
Content: 

input: "X"
output: "Y"
name: ""
type: "Relu"

在创造op之后，我们在当前的工作区中添加输入X，然后使用RunOperatorOnce运行这个operator。运行之后，我们对比下得到的结果。

workspace.FeedBlob("X", np.random.randn(2, 3).astype(np.float32))
workspace.RunOperatorOnce(op)

print("Current blobs in the workspace: {}\n".format(workspace.Blobs()))
print("X:\n{}\n".format(workspace.FetchBlob("X")))
print("Y:\n{}\n".format(workspace.FetchBlob("Y")))
print("Expected:\n{}\n".format(np.maximum(workspace.FetchBlob("X"), 0)))

Current blobs in the workspace: ['X', 'Y']

X:
[[ 1.03125858  1.0038228   0.0066975 ]
 [ 1.33142471  1.80271244 -0.54222912]]

Y:
[[ 1.03125858  1.0038228   0.0066975 ]
 [ 1.33142471  1.80271244  0.        ]]

Expected:
[[ 1.03125858  1.0038228   0.0066975 ]
 [ 1.33142471  1.80271244  0.        ]]

此外，operator相对于layer更为抽象。operator不仅仅可以替代layer类，还可以接受无参数的输入来输出数据，从而用来生成数据，常用来初始化权值。下面这一段就可以用来初始化权值。

op = core.CreateOperator(
    "GaussianFill",
    [], # GaussianFill does not need any parameters.
    ["W"],
    shape=[100, 100], # shape argument as a list of ints.
    mean=1.0,  # mean as a single float
    std=1.0, # std as a single float
)
print("Content of op:\n")
print(str(op))

Content of op:

output: "W"
name: ""
type: "GaussianFill"
arg {
  name: "std"
  f: 1.0
}
arg {
  name: "shape"
  ints: 100
  ints: 100
}
arg {
  name: "mean"
  f: 1.0
}

workspace.RunOperatorOnce(op)
temp = workspace.FetchBlob("Z")
pyplot.hist(temp.flatten(), bins=50)
pyplot.title("Distribution of Z")

Nets

Nets是一系列operator的集合，从本质上，是由operator构成的计算图。Caffe2中core.net 封装了源码中 NetDef 类。我们举个栗子，创建网络来实现以下的公式。

X = np.random.randn(2, 3)
W = np.random.randn(5, 3)
b = np.ones(5)
Y = X * W^T + b

首先创建网络：

net = core.Net("my_first_net")
print("Current network proto:\n\n{}".format(net.Proto()))

Current network proto:

name: "my_first_net"

首先使用生成权值和输入，在这里，使用core.net来访问创建：

X = net.GaussianFill([], ["X"], mean=0.0, std=1.0, shape=[2, 3], run_once=0)
print("New network proto:\n\n{}".format(net.Proto()))
W = net.GaussianFill([], ["W"], mean=0.0, std=1.0, shape=[5, 3], run_once=0)
b = net.ConstantFill([], ["b"], shape=[5,], value=1.0, run_once=0)

生成输出：

Y = net.FC([X, W, b], ["Y"])

我们打印下当前的网络：

print("Current network proto:\n\n{}".format(net.Proto()))

Current network proto:

name: "my_first_net"
op {
  output: "X"
  name: ""
  type: "GaussianFill"
  arg {
    name: "std"
    f: 1.0
  }
  arg {
    name: "run_once"
    i: 0
  }
  arg {
    name: "shape"
    ints: 2
    ints: 3
  }
  arg {
    name: "mean"
    f: 0.0
  }
}
op {
  output: "W"
  name: ""
  type: "GaussianFill"
  arg {
    name: "std"
    f: 1.0
  }
  arg {
    name: "run_once"
    i: 0
  }
  arg {
    name: "shape"
    ints: 5
    ints: 3
  }
  arg {
    name: "mean"
    f: 0.0
  }
}
op {
  output: "b"
  name: ""
  type: "ConstantFill"
  arg {
    name: "run_once"
    i: 0
  }
  arg {
    name: "shape"
    ints: 5
  }
  arg {
    name: "value"
    f: 1.0
  }
}
op {
  input: "X"
  input: "W"
  input: "b"
  output: "Y"
  name: ""
  type: "FC"
}

在这里，我们可以画出来定义的网络：

from caffe2.python import net_drawer
from IPython import display
graph = net_drawer.GetPydotGraph(net, rankdir="LR")
display.Image(graph.create_png(), width=800)

out

和operator类似，在这里我们只定义了一个net，但是并没有运行net的计算。当我们在python运行网络时，实际上在c++层面做了两件事情：

由protobuf定义初始化c++ 的net对象
调用初始化了的net的run函数

在python中有两种方法来运行一个net：

方法1:使用workspace.RunNetOnce,初始化网络，运行网络，然后销毁网络。
方法2:先使用workspace.CreateNet初始化网络，然后使用workspace.RunNet来运行网络

方法一：

workspace.ResetWorkspace()
print("Current blobs in the workspace: {}".format(workspace.Blobs()))
workspace.RunNetOnce(net)
print("Blobs in the workspace after execution: {}".format(workspace.Blobs()))
# Let's dump the contents of the blobs
for name in workspace.Blobs():
    print("{}:\n{}".format(name, workspace.FetchBlob(name)))

Current blobs in the workspace: []
Blobs in the workspace after execution: ['W', 'X', 'Y', 'b']
W:
[[-0.29295802  0.02897477 -1.25667715]
 [-1.82299471  0.92877913  0.33613944]
 [-0.64382178 -0.68545657 -0.44015241]
 [ 1.10232282  1.38060772 -2.29121733]
 [-0.55766547  1.97437167  0.39324901]]
X:
[[-0.47522315 -0.40166432  0.7179445 ]
 [-0.8363331  -0.82451206  1.54286408]]
Y:
[[ 0.22535783  1.73460138  1.2652775  -1.72335696  0.7543118 ]
 [-0.71776152  2.27745867  1.42452145 -4.59527397  0.4452306 ]]
b:
[ 1.  1.  1.  1.  1.]

方法二：

workspace.ResetWorkspace()
print("Current blobs in the workspace: {}".format(workspace.Blobs()))
workspace.CreateNet(net)
workspace.RunNet(net.Proto().name)
print("Blobs in the workspace after execution: {}".format(workspace.Blobs()))
for name in workspace.Blobs():
    print("{}:\n{}".format(name, workspace.FetchBlob(name)))

Current blobs in the workspace: []
Blobs in the workspace after execution: ['W', 'X', 'Y', 'b']
W:
[[-0.29295802  0.02897477 -1.25667715]
 [-1.82299471  0.92877913  0.33613944]
 [-0.64382178 -0.68545657 -0.44015241]
 [ 1.10232282  1.38060772 -2.29121733]
 [-0.55766547  1.97437167  0.39324901]]
X:
[[-0.47522315 -0.40166432  0.7179445 ]
 [-0.8363331  -0.82451206  1.54286408]]
Y:
[[ 0.22535783  1.73460138  1.2652775  -1.72335696  0.7543118 ]
 [-0.71776152  2.27745867  1.42452145 -4.59527397  0.4452306 ]]
b:
[ 1.  1.  1.  1.  1.]

在这里，大家可能比较疑惑为什么会有两种运行网络的方式，在之后的实际应用中，大家就会慢慢理解，在这里，暂时记住有这样两种运行网络的方式即可。

Exepriment

1. 回归 Regression

Re: Caffe2 框架下网络构建, 参数初始化, 训练, 图 ...

Q. 拟合回归函数 y = wx + b; (w=[2.0, 1.5], b=0.5)

数据直接用caffe2中的operator生成(拟读入)

1) 导入包

from caffe2.python import core, cnn, net_drawer, workspace, visualize
import numpy as np
from IPython import display
from matplotlib import pyplot

建立两个网络图：

一个用来生成训练数据、初始化权值的网络图
一个用来用来训练，更新剃度的网络图

这里caffe2的思路和caffe不太一样，在caffe中，我们在训练网络中定义好了参数的初始化方式，网络加载时，程序会根据网络定义，自动初始化权值，我们只需要对这个网络，使用solver不断的前传和反传，更新参数即可。

在caffe2中，我们要把所有网络的搭建、初始化、梯度生成、梯度更新都使用operator这样一个方式来实现，所有的数据的生成、流动都要在图中反映出来。这样，那么初始化这一部分我就需要一些operators来实现，这些operators组成的net，我们把它单独拿出来用于初始化的网络

首先，我们创建一个生成训练数据和初始化权值的网络。

init_net = core.Net("init")
# The ground truth parameters.
W_gt = init_net.GivenTensorFill(
    [], "W_gt", shape=[1, 2], values=[2.0, 1.5])
B_gt = init_net.GivenTensorFill([], "B_gt", shape=[1], values=[0.5])
# Constant value ONE is used in weighted sum when updating parameters.
ONE = init_net.ConstantFill([], "ONE", shape=[1], value=1.)
# ITER is the iterator count.
ITER = init_net.ConstantFill([], "ITER", shape=[1], value=0, dtype=core.DataType.INT32)

# For the parameters to be learned: we randomly initialize weight
# from [-1, 1] and init bias with 0.0.
W = init_net.UniformFill([], "W", shape=[1, 2], min=-1., max=1.)
B = init_net.ConstantFill([], "B", shape=[1], value=0.0)
print('Created init net.')

接下来，我们定义一个用来训练的网络。

train_net = core.Net("train")
# First, we generate random samples of X and create the ground truth.
X = train_net.GaussianFill([], "X", shape=[64, 2], mean=0.0, std=1.0, run_once=0)
Y_gt = X.FC([W_gt, B_gt], "Y_gt")
# We add Gaussian noise to the ground truth
noise = train_net.GaussianFill([], "noise", shape=[64, 1], mean=0.0, std=1.0, run_once=0)
Y_noise = Y_gt.Add(noise, "Y_noise")
# Note that we do not need to propagate the gradients back through Y_noise,
# so we mark StopGradient to notify the auto differentiating algorithm
# to ignore this path.
Y_noise = Y_noise.StopGradient([], "Y_noise")

# Now, for the normal linear regression prediction, this is all we need.
Y_pred = X.FC([W, B], "Y_pred")

# The loss function is computed by a squared L2 distance, and then averaged
# over all items in the minibatch.
dist = train_net.SquaredL2Distance([Y_noise, Y_pred], "dist")
loss = dist.AveragedLoss([], ["loss"])

我们来画出我们定义的训练网络的图：

graph = net_drawer.GetPydotGraph(train_net.Proto().op, "train", rankdir="LR")
display.Image(graph.create_png(), width=800)

在这里，通过上面的图，我们可以看到init_net部分生成了训练数据、初始化的权值W，以及用来生成计算过程中需要的常数矩阵，而train_net构建了前向计算过程。

但是我们还没有定义如何反向传导，和很多其他的深度学习框架类似，caffe2支持自动梯度推导，自动生成产生梯度的operator。

接下来，我们给train_net加上梯度运算：

# Get gradients for all the computations above.
gradient_map = train_net.AddGradientOperators([loss])
graph = net_drawer.GetPydotGraph(train_net.Proto().op, "train", rankdir="LR")
display.Image(graph.create_png(), width=800)

可以看到，网络后半部分进行了求梯度运算，输出了各学习参数的梯度值，当我们得到这些梯度值后，我们再获得当前训练的学习率，我们就可以使用梯度下降方法更新参数。

接下来，我们在train_net加上SGD更新的部分：

# Increment the iteration by one.
train_net.Iter(ITER, ITER)
# Compute the learning rate that corresponds to the iteration.
LR = train_net.LearningRate(ITER, "LR", base_lr=-0.1,
                            policy="step", stepsize=20, gamma=0.9)

# Weighted sum
train_net.WeightedSum([W, ONE, gradient_map[W], LR], W)
train_net.WeightedSum([B, ONE, gradient_map[B], LR], B)

# Let's show the graph again.
graph = net_drawer.GetPydotGraph(train_net.Proto().op, "train", rankdir="LR")
display.Image(graph.create_png(), width=800)

到这里，整个模型的参数初始化、前传、反传、梯度更新全都使用operator定义好了。这个就是caffe2中使用operator的威力，它使得caffe2较caffe具有不可比拟的灵活性。在这里注意，我们只是定义了网络，还没有运行网络，下面让我们来运行它们：

workspace.RunNetOnce(init_net)
workspace.CreateNet(train_net)
print("Before training, W is: {}".format(workspace.FetchBlob("W")))
print("Before training, B is: {}".format(workspace.FetchBlob("B")))

True
Before training, W is: [[-0.77634162 -0.88467366]]
Before training, B is: [ 0.]

#run the train net 100 times 
for i in range(100):
    workspace.RunNet(train_net.Proto().name)
    
print("After training, W is: {}".format(workspace.FetchBlob("W")))
print("After training, B is: {}".format(workspace.FetchBlob("B")))
print("Ground truth W is: {}".format(workspace.FetchBlob("W_gt")))
print("Ground truth B is: {}".format(workspace.FetchBlob("B_gt")))

在这里，我们需要注意一点，我们使用了RunNetOnce和RunNet两种不同的方式来运行网络，还记得两种运行网络的方式么？

方法1:使用workspace.RunNetOnce,这个函数会初始化网络，运行网络，然后销毁网络。
方法2:先使用workspace.CreateNet初始化网络，然后使用workspace.RunNet来运行网络

一开始我也不明白为什么要有两种方式运行网络，现在结合init_net和train_net来看，就非常明白了。RunNetOnce用来运行生成权值和数据的网络，常用于初始化，这样的网络一次生成完，权值输出或数据就存在当前的workspace中，网络本身就没有存在的必要了，就直接销毁，而RunNet可以用来重复训练网络，一开始使用CreateNet，不断迭代调用RunNet就可以不断运行网络更新参数了。

以下是训练结果：

After training, W is: [[ 1.95769441  1.47348857]]
After training, B is: [ 0.45236012]
Ground truth W is: [[ 2.   1.5]]
Ground truth B is: [ 0.5]

，总结一下：

caffe2中使用operator完成初始化参数、前传、反传、梯度更新
caffe2中一个模型通常包含一个初始化网络，一个训练网络

最后，还要说明一点，这个例子中，我们直接使用operator来构建网络。对于常见的深度网络，直接用operator构建会步骤会非常繁琐，所以caffe2中为了简化网络的搭建，又封装了model_helper类来帮助我们方便地搭建网络，譬如对于卷积神经网络中的常见的层，我们就可以直接使用model_helper来构建。在之后的栗子中也有说明。

2. 预处理

教程: Image Pre-Processing .

3. 加载预训练模型

首先，我们使用一个caffe2中定义的下载模块去下载一个预训练好的模型，命令行中输入如下的命令会下载squeezenet这个预训练模型：

python -m caffe2.python.models.download -i squeezenet

当下载完成时，在caffe2/python/model底下有一个squeezenet文件，文件夹底下有两个文件init_net.pb,predict_net.pb分别保存了权值和网络定义。

在python中我们使用caffe2的workspace来存放这个模型的网络定义和权重，并且把它们加载到blob、init_net和predict_net。我们需要使用一个workspace.Predictor来接收两个protobuf，然后剩下的就可以交给caffe2了。

所以一般加载预测模型只需要几步：

1、读入protobuf文件

 with open("init_net.pb") as f:
     init_net = f.read()
 with open("predict_net.pb") as f:
     predict_net = f.read()

2、使用workspace中的Predictor来加载从protobuf中取到的blobs：

 p = workspace.Predictor(init_net, predict_net)

3、运行网络，得到结果：

 results = p.run([img])

需要注意的这里的img是预处理过的图像。

以下是官方文档下的一个完整的栗子：

首先配置一下问文件路径等，导入常用包：

# where you installed caffe2. Probably '~/caffe2' or '~/src/caffe2'.
CAFFE2_ROOT = "~/caffe2"
# assumes being a subdirectory of caffe2
CAFFE_MODELS = "~/caffe2/caffe2/python/models"
# if you have a mean file, place it in the same dir as the model

%matplotlib inline
from caffe2.proto import caffe2_pb2
import numpy as np
import skimage.io
import skimage.transform
from matplotlib import pyplot
import os
from caffe2.python import core, workspace
import urllib2
print("Required modules imported.")

IMAGE_LOCATION =  "https://cdn.pixabay.com/photo/2015/02/10/21/28/flower-631765_1280.jpg"

# What model are we using? You should have already converted or downloaded one.
# format below is the model's:
# folder, INIT_NET, predict_net, mean, input image size
# you can switch the comments on MODEL to try out different model conversions
MODEL = 'squeezenet', 'init_net.pb', 'predict_net.pb', 'ilsvrc_2012_mean.npy', 227

# codes - these help decypher the output and source from a list from AlexNet's object codes to provide an result like "tabby cat" or "lemon" depending on what's in the picture you submit to the neural network.
# The list of output codes for the AlexNet models (also squeezenet)
codes =  "https://gist.githubusercontent.com/aaronmarkham/cd3a6b6ac071eca6f7b4a6e40e6038aa/raw/9edb4038a37da6b5a44c3b5bc52e448ff09bfe5b/alexnet_codes"
print "Config set!"

定义数据预处理的函数：

def crop_center(img,cropx,cropy):
    y,x,c = img.shape
    startx = x//2-(cropx//2)
    starty = y//2-(cropy//2)    
    return img[starty:starty+cropy,startx:startx+cropx]

def rescale(img, input_height, input_width):
    print("Original image shape:" + str(img.shape) + " and remember it should be in H, W, C!")
    print("Model's input shape is %dx%d") % (input_height, input_width)
    aspect = img.shape[1]/float(img.shape[0])
    print("Orginal aspect ratio: " + str(aspect))
    if(aspect>1):
        # landscape orientation - wide image
        res = int(aspect * input_height)
        imgScaled = skimage.transform.resize(img, (input_width, res))
    if(aspect<1):
        # portrait orientation - tall image
        res = int(input_width/aspect)
        imgScaled = skimage.transform.resize(img, (res, input_height))
    if(aspect == 1):
        imgScaled = skimage.transform.resize(img, (input_width, input_height))
    pyplot.figure()
    pyplot.imshow(imgScaled)
    pyplot.axis('on')
    pyplot.title('Rescaled image')
    print("New image shape:" + str(imgScaled.shape) + " in HWC")
    return imgScaled
print "Functions set."

# set paths and variables from model choice and prep image
CAFFE2_ROOT = os.path.expanduser(CAFFE2_ROOT)
CAFFE_MODELS = os.path.expanduser(CAFFE_MODELS)

# mean can be 128 or custom based on the model
# gives better results to remove the colors found in all of the training images
MEAN_FILE = os.path.join(CAFFE_MODELS, MODEL[0], MODEL[3])
if not os.path.exists(MEAN_FILE):
    mean = 128
else:
    mean = np.load(MEAN_FILE).mean(1).mean(1)
    mean = mean[:, np.newaxis, np.newaxis]
print "mean was set to: ", mean

# some models were trained with different image sizes, this helps you calibrate your image
INPUT_IMAGE_SIZE = MODEL[4]

# make sure all of the files are around...
if not os.path.exists(CAFFE2_ROOT):
    print("Houston, you may have a problem.")
INIT_NET = os.path.join(CAFFE_MODELS, MODEL[0], MODEL[1])
print 'INIT_NET = ', INIT_NET
PREDICT_NET = os.path.join(CAFFE_MODELS, MODEL[0], MODEL[2])
print 'PREDICT_NET = ', PREDICT_NET
if not os.path.exists(INIT_NET):
    print(INIT_NET + " not found!")
else:
    print "Found ", INIT_NET, "...Now looking for", PREDICT_NET
    if not os.path.exists(PREDICT_NET):
        print "Caffe model file, " + PREDICT_NET + " was not found!"
    else:
        print "All needed files found! Loading the model in the next block."

# load and transform image
img = skimage.img_as_float(skimage.io.imread(IMAGE_LOCATION)).astype(np.float32)
img = rescale(img, INPUT_IMAGE_SIZE, INPUT_IMAGE_SIZE)
img = crop_center(img, INPUT_IMAGE_SIZE, INPUT_IMAGE_SIZE)
print "After crop: " , img.shape
pyplot.figure()
pyplot.imshow(img)
pyplot.axis('on')
pyplot.title('Cropped')

# switch to CHW
img = img.swapaxes(1, 2).swapaxes(0, 1)
pyplot.figure()
for i in range(3):
    # For some reason, pyplot subplot follows Matlab's indexing
    # convention (starting with 1). Well, we'll just follow it...
    pyplot.subplot(1, 3, i+1)
    pyplot.imshow(img[i])
    pyplot.axis('off')
    pyplot.title('RGB channel %d' % (i+1))

# switch to BGR
img = img[(2, 1, 0), :, :]

# remove mean for better results
img = img * 255 - mean

# add batch size
img = img[np.newaxis, :, :, :].astype(np.float32)
print "NCHW: ", img.shape

运行一下，输出结果：

Functions set.
mean was set to:  128
INIT_NET =  /home/aaron/models/squeezenet/init_net.pb
PREDICT_NET =  /home/aaron/models/squeezenet/predict_net.pb
Found  /home/aaron/models/squeezenet/init_net.pb ...Now looking for /home/aaron/models/squeezenet/predict_net.pb
All needed files found! Loading the model in the next block.
Original image shape:(751, 1280, 3) and remember it should be in H, W, C!
Model's input shape is 227x227
Orginal aspect ratio: 1.70439414115
New image shape:(227, 386, 3) in HWC
After crop:  (227, 227, 3)
NCHW:  (1, 3, 227, 227)

image output

当图像经过处理之后，就可以按照前面的安排加载和运行网络。

# initialize the neural net

with open(INIT_NET) as f:
    init_net = f.read()
with open(PREDICT_NET) as f:
    predict_net = f.read()

p = workspace.Predictor(init_net, predict_net)

# run the net and return prediction
results = p.run([img])

# turn it into something we can play with and examine which is in a multi-dimensional array
results = np.asarray(results)
print "results shape: ", results.shape

results shape:  (1, 1, 1000, 1, 1)

这里输出来了1000个值，表示这张图片分别对应1000类的概率。我们可以取出来其中概率最高的值，来找到它对应的标签：

# the rest of this is digging through the results

results = np.delete(results, 1)
index = 0
highest = 0
arr = np.empty((0,2), dtype=object)
arr[:,0] = int(10)
arr[:,1:] = float(10)
for i, r in enumerate(results):
    # imagenet index begins with 1!
    i=i+1
    arr = np.append(arr, np.array([[i,r]]), axis=0)
    if (r > highest):
        highest = r
        index = i

print index, " :: ", highest

# lookup the code and return the result
# top 3 results
# sorted(arr, key=lambda x: x[1], reverse=True)[:3]

# now we can grab the code list
response = urllib2.urlopen(codes)

# and lookup our result from the list
for line in response:
    code, result = line.partition(":")[::2]
    if (code.strip() == str(index)):
        print result.strip()[1:-2]

985  ::  0.979059
daisy

4. CNN模型

Model

在前面我们已经基本介绍了在python中关于caffe2中基本的操作。

这个例子中，我们来简单搭建一个CNN模型。在这个需要说明一点:

在caffe中，我们通常说一个模型，其实就是一个网络，一个Net
而在caffe2中，我们通常使用modelHelper来代表一个model，而这个model包含多个Net，就像我们前面看到的，我们会使用一个初始化网络init_net，还有有一个训练网络net，这两个网络图都是model的一部分。

这一点需要大家区分开，不然容易疑惑。举例，如果我们要构造一个模型，只有一个FC层，在这里使用modelHelper来表示一个model，使用operators来构造网络，一般model有一个param_init_net和一个net。分别用于模型初始化和训练：

model = model_helper.ModelHelper(name="train")
# initialize your weight
weight = model.param_init_net.XavierFill(
    [],
    blob_out + '_w',
    shape=[dim_out, dim_in],
    **kwargs, # maybe indicating weight should be on GPU here
)
# initialize your bias
bias = model.param_init_net.ConstantFill(
    [],
    blob_out + '_b',
    shape=[dim_out, ],
    **kwargs,
)
# finally building FC
model.net.FC([blob_in, weights, bias], blob_out, **kwargs)

前面，我们说过在日常搭建网络的时候呢，我们通常不是完全使用operator搭建网络，因为使用这种方式，每个参数都需要我们手动初始化，以及每个operator都需要构造，太过于繁琐。我们想着，对于常用层，能不能把构造它的operators都封装起来，封装成一个函数，我们构造时只需给这个函数要提供必要的参数，函数中的代码就能帮助我们完成层初始化和operator的构建。

在caffe2中，为了便于开发者搭建网络，caffe2在python/helpers中提供了许多help函数，像上面例子中的FC层，使用python/helpers/fc.py来构造，非常简单就一行代码：

fcLayer = fc(model, blob_in, blob_out, **kwargs) # returns a blob reference

这里面help函数能够帮助我们将权值初始化和计算网络自动分开到两个网络，这样一来就简单多了。caffe2为了更方便调用和管理，把这些帮助函数集合到一起，放在brew这个包里面。可以通过导入brew这个包来调用这些帮助函数。像上面的fc层的实现就可以使用：

from caffe2.python import brew
brew.fc(model, blob_in, blob_out, ...)

我们使用brew构造网络就十分简单，下面的代码就构造了一个LeNet模型：

from caffe2.python import brew

def AddLeNetModel(model, data):
    conv1 = brew.conv(model, data, 'conv1', 1, 20, 5)
    pool1 = brew.max_pool(model, conv1, 'pool1', kernel=2, stride=2)
    conv2 = brew.conv(model, pool1, 'conv2', 20, 50, 5)
    pool2 = brew.max_pool(model, conv2, 'pool2', kernel=2, stride=2)
    fc3 = brew.fc(model, pool2, 'fc3', 50 * 4 * 4, 500)
    fc3 = brew.relu(model, fc3, fc3)
    pred = brew.fc(model, fc3, 'pred', 500, 10)
    softmax = brew.softmax(model, pred, 'softmax')

caffe2 使用brew提供很多构造网络的帮助函数，大大简化了我们构建网络的过程。但实际上，这些只是封装的结果，网络构造的原理和之前说的使用operators构建的原理是一样的。

MNIST手写体数据集

首先，导入必要的包：

%matplotlib inline
from matplotlib import pyplot
import numpy as np
import os
import shutil


from caffe2.python import core, model_helper, net_drawer, workspace, visualize, brew

# If you would like to see some really detailed initializations,
# you can change --caffe2_log_level=0 to --caffe2_log_level=-1
core.GlobalInit(['caffe2', '--caffe2_log_level=0'])
print("Necessities imported!")

下载MNIST dataset,并且把数据集转成leveldb：

./make_mnist_db --channel_first --db leveldb --image_file ~/Downloads/train-images-idx3-ubyte --label_file ~/Downloads/train-labels-idx1-ubyte --output_file ~/caffe2_notebooks/tutorial_data/mnist/mnist-train-nchw-leveldb

./make_mnist_db --channel_first --db leveldb --image_file ~/Downloads/t10k-images-idx3-ubyte --label_file ~/Downloads/t10k-labels-idx1-ubyte --output_file ~/caffe2_notebooks/tutorial_data/mnist/mnist-test-nchw-leveldb

# This section preps your image and test set in a leveldb
current_folder = os.path.join(os.path.expanduser('~'), 'caffe2_notebooks')

data_folder = os.path.join(current_folder, 'tutorial_data', 'mnist')
root_folder = os.path.join(current_folder, 'tutorial_files', 'tutorial_mnist')
image_file_train = os.path.join(data_folder, "train-images-idx3-ubyte")
label_file_train = os.path.join(data_folder, "train-labels-idx1-ubyte")
image_file_test = os.path.join(data_folder, "t10k-images-idx3-ubyte")
label_file_test = os.path.join(data_folder, "t10k-labels-idx1-ubyte")

# Get the dataset if it is missing
def DownloadDataset(url, path):
    import requests, zipfile, StringIO
    print "Downloading... ", url, " to ", path
    r = requests.get(url, stream=True)
    z = zipfile.ZipFile(StringIO.StringIO(r.content))
    z.extractall(path)

def GenerateDB(image, label, name):
    name = os.path.join(data_folder, name)
    print 'DB: ', name
    if not os.path.exists(name):
        syscall = "/usr/local/bin/make_mnist_db --channel_first --db leveldb --image_file " + image + " --label_file " + label + " --output_file " + name
        # print "Creating database with: ", syscall
        os.system(syscall)
    else:
        print "Database exists already. Delete the folder if you have issues/corrupted DB, then rerun this."
        if os.path.exists(os.path.join(name, "LOCK")):
            # print "Deleting the pre-existing lock file"
            os.remove(os.path.join(name, "LOCK"))

            if not os.path.exists(data_folder):
                os.makedirs(data_folder)
            if not os.path.exists(label_file_train):
                DownloadDataset("https://download.caffe2.ai/datasets/mnist/mnist.zip", data_folder)

            if os.path.exists(root_folder):
                print("Looks like you ran this before, so we need to cleanup those old files...")
                shutil.rmtree(root_folder)

            os.makedirs(root_folder)
            workspace.ResetWorkspace(root_folder)

            # (Re)generate the leveldb database (known to get corrupted...)
            GenerateDB(image_file_train, label_file_train, "mnist-train-nchw-leveldb")
            GenerateDB(image_file_test, label_file_test, "mnist-test-nchw-leveldb")


            print("training data folder:" + data_folder)
            print("workspace root folder:" + root_folder)

在这里，我们使用modelHelper来代表我们的模型，使用brew和operators来搭建模型，modelHelper包含了两个net，包括param_init_net和net，分别代表初始化网络和主训练网络。

我们来一步一步分块构造模型：

1. 输入函数（AddInput function)

AddInput会从DB加载data，AddInput加载完成之后，和得到data 和label：

- data with shape `(batch_size, num_channels, width, height)`
    - in this case `[batch_size, 1, 28, 28]` of data type *uint8*
- label with shape `[batch_size]` of data type *int*

def AddInput(model, batch_size, db, db_type):
    # load the data
    data_uint8, label = model.TensorProtosDBInput(
        [], ["data_uint8", "label"], batch_size=batch_size,
        db=db, db_type=db_type)
    # cast the data to float
    data = model.Cast(data_uint8, "data", to=core.DataType.FLOAT)
    # scale data from [0,255] down to [0,1]
    data = model.Scale(data, data, scale=float(1./256))
    # don't need the gradient for the backward pass
    data = model.StopGradient(data, data)
    return data, label

在这里简单解释一下AddInput中的一些操作，首先将data转换成float类型，这样做是因为我们主要做浮点运算。为了保证计算稳定，我们将图像从[0,255]缩放到[0,1]，并且这里做的事占位运算，不需要保存未缩放之前的值。当计算反向过程中，这一部分不需要计算梯度，我们使用StopGradient来禁止梯度反传，这样自动生成梯度时，这个operator和它之前的operator就不会变了。

def AddInput(model, batch_size, db, db_type):
    # load the data
    data_uint8, label = model.TensorProtosDBInput(
        [], ["data_uint8", "label"], batch_size=batch_size,
        db=db, db_type=db_type)
    # cast the data to float
    data = model.Cast(data_uint8, "data", to=core.DataType.FLOAT)
    # scale data from [0,255] down to [0,1]
    data = model.Scale(data, data, scale=float(1./256))
    # don't need the gradient for the backward pass
    data = model.StopGradient(data, data)
    return data, label

在这个基础上，就是加入网络AddLenetModel，同时加入一个AddAccuracy来追踪模型的准确率：

def AddLeNetModel(model, data):
    # Image size: 28 x 28 -> 24 x 24
    conv1 = brew.conv(model, data, 'conv1', dim_in=1, dim_out=20, kernel=5)
    # Image size: 24 x 24 -> 12 x 12
    pool1 = brew.max_pool(model, conv1, 'pool1', kernel=2, stride=2)
    # Image size: 12 x 12 -> 8 x 8
    conv2 = brew.conv(model, pool1, 'conv2', dim_in=20, dim_out=50, kernel=5)
    # Image size: 8 x 8 -> 4 x 4
    pool2 = brew.max_pool(model, conv2, 'pool2', kernel=2, stride=2)
    # 50 * 4 * 4 stands for dim_out from previous layer multiplied by the image size
    fc3 = brew.fc(model, pool2, 'fc3', dim_in=50 * 4 * 4, dim_out=500)
    fc3 = brew.relu(model, fc3, fc3)
    pred = brew.fc(model, fc3, 'pred', 500, 10)
    softmax = brew.softmax(model, pred, 'softmax')
    return softmax

def AddAccuracy(model, softmax, label):
    accuracy = model.Accuracy([softmax, label], "accuracy")
    return accuracy

接下来，我们将加入梯度生成和更新，这部分由AddTrainingOperators实现，梯度生成和更新和之前例子中的原理一样。

def AddTrainingOperators(model, softmax, label):

# something very important happens here
xent = model.LabelCrossEntropy([softmax, label], 'xent')
# compute the expected loss
loss = model.AveragedLoss(xent, "loss")
# track the accuracy of the model
AddAccuracy(model, softmax, label)
# use the average loss we just computed to add gradient operators to the model
model.AddGradientOperators([loss])
# do a simple stochastic gradient descent
ITER = model.Iter("iter")
# set the learning rate schedule
LR = model.LearningRate(
    ITER, "LR", base_lr=-0.1, policy="step", stepsize=1, gamma=0.999 )
# ONE is a constant value that is used in the gradient update. We only need
# to create it once, so it is explicitly placed in param_init_net.
ONE = model.param_init_net.ConstantFill([], "ONE", shape=[1], value=1.0)
# Now, for each parameter, we do the gradient updates.
for param in model.params:
    # Note how we get the gradient of each parameter - ModelHelper keeps
    # track of that.
    param_grad = model.param_to_grad[param]
    # The update is a simple weighted sum: param = param + param_grad * LR
    model.WeightedSum([param, ONE, param_grad, LR], param)
# let's checkpoint every 20 iterations, which should probably be fine.
# you may need to delete tutorial_files/tutorial-mnist to re-run the tutorial
model.Checkpoint([ITER] + model.params, [],
               db="mnist_lenet_checkpoint_%05d.leveldb",
               db_type="leveldb", every=20)

接下来，我们使用AddBookkeepingOperations来打印一些统计数据供我们之后观察，这一部分不影响训练部分，只是统计，打印日志。

def AddBookkeepingOperators(model):
    # Print basically prints out the content of the blob. to_file=1 routes the
    # printed output to a file. The file is going to be stored under
    #     root_folder/[blob name]
    model.Print('accuracy', [], to_file=1)
    model.Print('loss', [], to_file=1)
    # Summarizes the parameters. Different from Print, Summarize gives some
    # statistics of the parameter, such as mean, std, min and max.
    for param in model.params:
        model.Summarize(param, [], to_file=1)
        model.Summarize(model.param_to_grad[param], [], to_file=1)
    # Now, if we really want to be verbose, we can summarize EVERY blob
    # that the model produces; it is probably not a good idea, because that
    # is going to take time - summarization do not come for free. For this
    # demo, we will only show how to summarize the parameters and their
    # gradients.
print("Bookkeeping function created")

在这里，我们一共做了四件事：

输入函数(AddInput function)
网络计算部分(AddLeNetModel function)
训练函数(AddTrainingOperators function): 添加梯度运算，更新等;
记录部分(AddBookkeepingOperators function): 打印一些统计数据来观察;

基本的操作我们都定义好了，接下来调用定义模型，在这里，它定义了一个训练模型，用于训练，一个部署模型，用于部署：

arg_scope = {"order": "NCHW"}
train_model = model_helper.ModelHelper(name="mnist_train", arg_scope=arg_scope)
data, label = AddInput(
    train_model, batch_size=64,
    db=os.path.join(data_folder, 'mnist-train-nchw-leveldb'),
    db_type='leveldb')
softmax = AddLeNetModel(train_model, data)
AddTrainingOperators(train_model, softmax, label)
AddBookkeepingOperators(train_model)

# Testing model. We will set the batch size to 100, so that the testing
# pass is 100 iterations (10,000 images in total).
# For the testing model, we need the data input part, the main LeNetModel
# part, and an accuracy part. Note that init_params is set False because
# we will be using the parameters obtained from the train model.
test_model = model_helper.ModelHelper(
    name="mnist_test", arg_scope=arg_scope, init_params=False)
data, label = AddInput(
    test_model, batch_size=100,
    db=os.path.join(data_folder, 'mnist-test-nchw-leveldb'),
    db_type='leveldb')
softmax = AddLeNetModel(test_model, data)
AddAccuracy(test_model, softmax, label)

# Deployment model. We simply need the main LeNetModel part.
deploy_model = model_helper.ModelHelper(
    name="mnist_deploy", arg_scope=arg_scope, init_params=False)
AddLeNetModel(deploy_model, "data")
# You may wonder what happens with the param_init_net part of the deploy_model.
# No, we will not use them, since during deployment time we will not randomly
# initialize the parameters, but load the parameters from the db.

运行网络，打印loss曲线：

# The parameter initialization network only needs to be run once.
workspace.RunNetOnce(train_model.param_init_net)
# creating the network
workspace.CreateNet(train_model.net)
# set the number of iterations and track the accuracy & loss
total_iters = 200
accuracy = np.zeros(total_iters)
loss = np.zeros(total_iters)
# Now, we will manually run the network for 200 iterations.
for i in range(total_iters):
    workspace.RunNet(train_model.net.Proto().name)
    accuracy[i] = workspace.FetchBlob('accuracy')
    loss[i] = workspace.FetchBlob('loss')
# After the execution is done, let's plot the values.
pyplot.plot(loss, 'b')
pyplot.plot(accuracy, 'r')
pyplot.legend(('Loss', 'Accuracy'), loc='upper right')

我们也可以输出来预测：

# Let's look at some of the data.
pyplot.figure()
data = workspace.FetchBlob('data')
_ = visualize.NCHW.ShowMultiple(data)
pyplot.figure()
softmax = workspace.FetchBlob('softmax')
_ = pyplot.plot(softmax[0], 'ro')
pyplot.title('Prediction for the first image')

记得我们也定义了一个test_model，我们可以运行它得到测试集准确率，虽然test_model的权值由train_model来加载，但是测试数据输入还需要运行param_init_net。

# run a test pass on the test net
workspace.RunNetOnce(test_model.param_init_net)
workspace.CreateNet(test_model.net)
test_accuracy = np.zeros(100)
for i in range(100):
    workspace.RunNet(test_model.net.Proto().name)
    test_accuracy[i] = workspace.FetchBlob('accuracy')
# After the execution is done, let's plot the values.
pyplot.plot(test_accuracy, 'r')
pyplot.title('Acuracy over test batches.')
print('test_accuracy: %f' % test_accuracy.mean())

test_accuracy: 0.946700

完成

[G-CS-ML.NN03] Caffe2

Installation

Dependency

python

NCCL

Caffe2

Build

数据 Data

*caffe

Caffe2

Python Profile

workspace

Operators

Nets

Exepriment

1. 回归 Regression

1) 导入包

2. 预处理

3. 加载预训练模型

4. CNN模型

Model

MNIST手写体数据集

你可能感兴趣的:([G-CS-ML.NN03] Caffe2)