1. 程式人生 > >caffe2 教程入門 例項 影象處理 線性迴歸

caffe2 教程入門 例項 影象處理 線性迴歸

學習思路

1、先看官方文件,學習如何使用python呼叫caffe2包,包括

  • Basics of Caffe2 - Workspaces, Operators, and Nets
  • Toy Regression
  • Image Pre-Processing
  • Loading Pre-Trained Models
  • MNIST - Create a CNN from Scratch

caffe2官方教程以python語言為主,指導如何使用python呼叫caffe2,文件依次從最基本caffe中的幾個重要的類的概念、如何使用基礎類搭建一個小網路、如何資料預處理、如何使用預訓練的模型、如何構造複雜的網路來講述caffe2的使用。初學者可以先行學習官方文件

caffe2-tutorials,理解caffe2 中的網路構建、網路訓練的理念與思路,體會caffe2與caffe在整體構造上的不同。

2、結合著caffe2原始碼看python實際呼叫的c++類

在python中,caffe2這個包中類與函式大部分是封裝了原始碼資料夾caffe2/caffe2/core下的c++原始檔,如基礎資料類Tensor,操作類Operator等,通過使用python中類的使用,找到對應c++原始碼中類和函式的構造和實現,可以為使用c++直接構建和訓練網路打下準備。

以下總結基於官方文件和部分網路資料。

基礎知識

首先從我們自己的角度出發來思考,假設我們自己需要寫一個簡單的多層神經網路並訓練,一般邏輯上我們需要考慮資料的定義、資料的流動 、資料的更新。

  • 資料如何定義:訓練資料和網路引數以什麼形式儲存
  • 資料如何流動:訓練資料經過哪些運算得到輸出,其實就是網路的定義
  • 資料如何更新:使用什麼樣的梯度更新方法與引數,其實就是如何訓練

在caffe中,資料儲存在Blob類的例項當中,在這裡,我們可以理解blob就像是numpy中陣列,起的作用就是儲存資料。輸入的blobs經過不同層的往前傳遞,得到輸出的blobs,caffe中,我們可以認為對資料最基本的運算單位是layer。每一層的layer定義了不同的計算方式,資料經過不同的層,都做了相應的運算,由這些layers組合到一起網路即構成了net,net本質上是一個計算網路。當資料流動的方式構建好了,反向傳遞的梯度計算的方式也確定,在這個基礎之上,caffe中使用solver類來給定梯度更新的規則,網路在solver的控制下,不斷讓資料前傳,再反傳求梯度,再使用梯度更新權值,迴圈往復。

所以對應著caffe中,基礎組成有四類:

  • blob:儲存資料和權值
  • layer:輸入資料blob 形式,輸出資料blob形式,層定義了計算
  • net:由多個layers組成,構成整體的網路
  • solver:定義了訓練規則

再看caffe2中:

在caffe2中,operator是caffe2中的特色,取代了caffe中layer作為net的基本構造單位。如下圖所示,我們可以使用一個InnerProduct操作運輸符號來完成InnerProductLayer的功能。operator的介面定義在caffe2/proto/caffe2.proto,一般來說,operator接受一串輸入,產生一串輸出。

operator

由於operator定義很基礎,很抽象,因此caffe2中的權值初始化、前傳、反傳、梯度更新都可以用operator實現,所以solver、layer類在caffe2中都不是必要的。在caffe2中,對應的基礎組成有

  • blob:儲存資料
  • operator:輸入blob,輸出blob,定義了計算規則
  • 網路:net,由多個operator組合實現
  • workspace:caffe中沒有,可以理解成變數的空間,便於管理網路和變數

具體使用和理解如下,先用python:

在使用之前,我們先匯入caffe2.core和workspace,基礎的類和函式都在其中。同時我們需要匯入caffe2.proto來對protobuf檔案進行必要操作。

# 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

1、workspace

我們可以把workspace理解成matlab中變數儲存區,我們可以把定義好的資料blob或net放到都在一個workspace中,也可以用不用的workspace來區分。

下面我們列印一下當前workspace中blob情況。Blobs()取出blob,HasBlobs(name)判斷是否有此名字的blob。

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

一開始,當然結果是啥也沒有。

我們使用FeedBlob來給當前workspace新增blob,再打印出來:

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]]

當然,我們也用多個名字定義多個workspace,並且可以切換工作空間。我們可以使用currentworkspace()在訪問當前工作空間,使用switchworkspace(name)來切換工作空間。

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: []

總結一下,在這裡workspace功能類似於matlab中的工作區,變數儲存在其中,我們可以通過工作區去訪問在工作區中net和blob。

2、Operators

通常我們在python中,可以使用core.CreateOperator來直接創造,也可以使用core.Net來訪問建立operator,還可以使用modelHelper來訪問建立operators。在這裡我們使用core.CreateOperator來簡單理解operator,在實際情況下,我們建立網路的時候,不會直接建立每個operator,這樣太麻煩,一般使用modelhelper來幫忙我們建立網路。

# 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!

上面的程式碼建立了一個Relu運算子,在這裡需要知道,在python中建立一個operator,只是定義了一個operator,其實並沒有執行這個operator。在上面程式碼中建立的op,實際上是一個protobuf物件。

print("Type of the created op is: {}".format(type(op)))
print("Content:\n")
print(str(op))
Type of the created op is: <class 'caffe2.proto.caffe2_pb2.OperatorDef'>
Content:

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

在創造op之後,我們在當前的工作區中新增輸入X,然後使用RunOperatorOnce執行這個operator。執行之後,我們對比下得到的結果。

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相對於layer更為抽象。operator不僅僅可以替代layer類,還可以接受無引數的輸入來輸出資料,從而用來生成資料,常用來初始化權值。下面這一段就可以用來初始化權值。

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")

3、Nets

Nets是一系列operator的集合,從本質上,是由operator構成的計算圖。Caffe2中core.net 封裝了原始碼中 NetDef 類。我們舉個栗子,建立網路來實現以下的公式。

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

首先建立網路:

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

name: "my_first_net"

首先使用生成權值和輸入,在這裡,使用core.net來訪問建立:

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)

生成輸出:

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

我們列印下當前的網路:

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"
}

在這裡,我們可以畫出來定義的網路:

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

和operator類似,在這裡我們只定義了一個net,但是並沒有執行net的計算。當我們在python執行網路時,實際上在c++層面做了兩件事情:

  • 由protobuf定義初始化c++ 的net物件
  • 呼叫初始化了的net的run函式

在python中有兩種方法來執行一個net:

  • 方法1:使用workspace.RunNetOnce,初始化網路,執行網路,然後銷燬網路。
  • 方法2:先使用workspace.CreateNet初始化網路,然後使用workspace.RunNet來執行網路

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.]

在這裡,大家可能比較疑惑為什麼會有兩種執行網路的方式,在之後的實際應用中,大家就會慢慢理解,在這裡,暫時記住有這樣兩種執行網路的方式即可。

總結一下,在caffe2中

  • workspace是工作空間,在worspace中,可以儲存網路結構類Net和資料儲存類Blob.
  • 輸入資料、權值、輸出資料都儲存在Blob中
  • Operator類用來定義來資料如何計算,由多個operators構成Net,operator的作用強大
  • Net類是由operator構成的整體。

應用舉例

在基礎知識中,我們理解了workspace,operator,net等基本的概念,在這裡我們結合caffe2的官方文件簡單舉出幾個例子。

栗子1-迴歸的小栗子

第一個栗子幫助大家理解caffe2框架網路構建、引數初始化、訓練、圖等的一些關於整體框架的理念。

假設我們要做訓練一個簡單的網路,擬合下面這樣的一個迴歸函式:

y = wx + b
其中:w=[2.0, 1.5]  b=0.5

一般訓練資料是從外部讀進來,在這裡訓練資料我們直接用caffe2中的operator生成,我們在後面的栗子中有會舉例說明如何從外部讀入資料。

首先匯入必要的包:

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

在這裡,首先我們需要建立兩個網路圖:

  • 一個用來生成訓練資料、初始化權值的網路圖
  • 一個用來用來訓練,更新剃度的網路圖

這裡caffe2的思路和caffe不太一樣,在caffe中,我們在訓練網路中定義好了引數的初始化方式,網路載入時,程式會根據網路定義,自動初始化權值,我們只需要對這個網路,使用solver不斷的前傳和反傳,更新引數即可。在caffe2中,我們要把所有網路的搭建、初始化、梯度生成、梯度更新都使用operator這樣一個方式來實現,所有的資料的生成、流動都要在圖中反映出來。這樣,那麼初始化這一部分我就需要一些operators來實現,這些operators組成的net,我們把它單獨拿出來,稱它為用於初始化的網路。我們可以結合著程式碼來理解。

首先,我們建立一個生成訓練資料和初始化權值的網路。

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.')

接下來,我們定義一個用來訓練的網路。

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"])

我們來畫出我們定義的訓練網路的圖:

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

在這裡,通過上面的圖,我們可以看到init_net部分生成了訓練資料、初始化的權值W,以及用來生成計算過程中需要的常數矩陣,而train_net構建了前向計算過程。

但是我們還沒有定義如何反向傳導,和很多其他的深度學習框架類似,caffe2支援自動梯度推導,自動生成產生梯度的operator。

接下來,我們給train_net加上梯度運算:

# 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,網路後半部分進行了求梯度運算,輸出了各學習引數的梯度值,當我們得到這些梯度值後,我們再獲得當前訓練的學習率,我們就可以使用梯度下降方法更新引數。

接下來,我們在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)

到這裡,整個模型的引數初始化、前傳、反傳、梯度更新全都使用operator定義好了。這個就是caffe2中使用operator的威力,它使得caffe2較caffe具有不可比擬的靈活性。在這裡注意,我們只是定義了網路,還沒有執行網路,下面讓我們來執行它們:

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")))

在這裡,我們需要注意一點,我們使用了RunNetOnce和RunNet兩種不同的方式來執行網路,還記得兩種執行網路的方式麼?

  • 方法1:使用workspace.RunNetOnce,這個函式會初始化網路,執行網路,然後銷燬網路。
  • 方法2:先使用workspace.CreateNet初始化網路,然後使用workspace.RunNet來執行網路

一開始我也不明白為什麼要有兩種方式執行網路,現在結合init_net和train_net來看,就非常明白了。RunNetOnce用來執行生成權值和資料的網路,常用於初始化,這樣的網路一次生成完,權值輸出或資料就存在當前的workspace中,網路本身就沒有存在的必要了,就直接銷燬,而RunNet可以用來重複訓練網路,一開始使用CreateNet,不斷迭代呼叫RunNet就可以不斷執行網路更新引數了。

以下是訓練結果:

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]

,總結一下:

  • caffe2中使用operator完成初始化引數、前傳、反傳、梯度更新
  • caffe2中一個模型通常包含一個初始化網路,一個訓練網路

最後,還要說明一點,這個例子中,我們直接使用operator來構建網路。對於常見的深度網路,直接用operator構建會步驟會非常繁瑣,所以caffe2中為了簡化網路的搭建,又封裝了model_helper類來幫助我們方便地搭建網路,譬如對於卷積神經網路中的常見的層,我們就可以直接使用model_helper來構建。在之後的栗子中也有說明。

栗子二-影象預處理

眾所周知,網路中訓練需要做一系列的資料預處理,在這裡,caffe和caffe2中處理的方式一樣。都需要經過XXX等步。因為沒有什麼區別,在這裡就不舉了,直接參考官方教程Image Pre-Processing,解釋非常清楚。給個贊。

栗子三-載入預訓練模型

首先,我們使用一個caffe2中定義的下載模組去下載一個預訓練好的模型,命令列中輸入如下的命令會下載squeezenet這個預訓練模型:

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

當下載完成時,在caffe2/python/model底下有一個squeezenet檔案,資料夾底下有兩個檔案init_net.pb,predict_net.pb分別儲存了權值和網路定義。

在python中我們使用caffe2的workspace來存放這個模型的網路定義和權重,並且把它們載入到blob、init_net和predict_net。我們需要使用一個workspace.Predictor來接收兩個protobuf,然後剩下的就可以交給caffe2了。

所以一般載入預測模型只需要幾步:

1、讀入protobuf檔案

 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來載入從protobuf中取到的blobs:

 p = workspace.Predictor(init_net, predict_net)

3、執行網路,得到結果:

 results = p.run([img])

需要注意的這裡的img是預處理過的影象。

以下是官方文件下的一個完整的栗子:

首先配置一下問檔案路徑等,匯入常用包:

# 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!"

定義資料預處理的函式:

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

執行一下,輸出結果:

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

image output

image output

當影象經過處理之後,就可以按照前面的安排載入和執行網路。

# 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)

這裡輸出來了1000個值,表示這張圖片分別對應1000類的概率。我們可以取出來其中概率最高的值,來找到它對應的標籤:

# 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

栗子四-建立一個CNN模型

1、模型、幫助函式、brew

在前面我們已經基本介紹了在python中關於caffe2中基本的操作。

這個例子中,我們來簡單搭建一個CNN模型。在這個需要說明一點:

  • 在caffe中,我們通常說一個模型,其實就是一個網路,一個Net
  • 而在caffe2中,我們通常使用modelHelper來代表一個model,而這個model包含多個Net,就像我們前面看到的,我們會使用一個初始化網路init_net,還有有一個訓練網路net,這兩個網路圖都是model的一部分。

這一點需要大家區分開,不然容易疑惑。舉例,如果我們要構造一個模型,只有一個FC層,在這裡使用modelHelper來表示一個model,使用operators來構造網路,一般model有一個param_init_net和一個net。分別用於模型初始化和訓練:

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,我們說過在日常搭建網路的時候呢,我們通常不是完全使用operator搭建網路,因為使用這種方式,每個引數都需要我們手動初始化,以及每個operator都需要構造,太過於繁瑣。我們想著,對於常用層,能不能把構造它的operators都封裝起來,封裝成一個函式,我們構造時只需給這個函式要提供必要的引數,函式中的程式碼就能幫助我們完成層初始化和operator的構建。

在caffe2中,為了便於開發者搭建網路,caffe2在python/helpers中提供了許多help函式,像上面例子中的FC層,使用python/helpers/fc.py來構造,非常簡單就一行程式碼:

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

這裡面help函式能夠幫助我們將權值初始化和計算網路自動分開到兩個網路,這樣一來就簡單多了。caffe2為了更方便呼叫和管理,把這些幫助函式集合到一起,放在brew這個包裡面。可以通過匯入brew這個包來呼叫這些幫助函式。像上面的fc層的實現就可以使用:

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

我們使用brew構造網路就十分簡單,下面的程式碼就構造了一個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提供很多構造網路的幫助函式,大大簡化了我們構建網路的過程。但實際上,這些只是封裝的結果,網路構造的原理和之前說的使用operators構建的原理是一樣的。

2、建立一個CNN模型用於MNIST手寫體資料集

首先,匯入必要的包:

%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!")

下載MNIST dataset,並且把資料集轉成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)

在這裡,我們使用modelHelper來代表我們的模型,使用brew和operators來搭建模型,modelHelper包含了兩個net,包括param_init_net和net,分別代表初始化網路和主訓練網路。

我們來一步一步分塊構造模型:

(1)輸入部分(AddInput function)
(2)網路計算部分(AddLeNetModel function)
(3)網路訓練部分,新增梯度運算,更新等(AddTrainingOperators function)
(4)記錄統計部分,列印一些統計資料來觀察(AddBookkeepingOperators function)

(1)輸入部分(AddInput function)

AddInput會從DB載入data,AddInput載入完成之後,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

在這裡簡單解釋一下AddInput中的一些操作,首先將data轉換成float型別,這樣做是因為我們主要做浮點運算。為了保證計算穩定,我們將影象從[0,255]縮放到[0,1],並且這裡做的事佔位運算,不需要儲存未縮放之前的值。當計算反向過程中,這一部分不需要計算梯度,我們使用StopGradient來禁止梯度反傳,這樣自動生成梯度時,這個operator和它之前的operator就不會變了。

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

在這個基礎上,就是加入網路AddLenetModel,同時加入一個AddAccuracy來追蹤模型的準確率:

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

接下來,我們將加入梯度生成和更新,這部分由AddTrainingOperators實現,梯度生成和更新和之前例子中的原理一樣。

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)

接下來,我們使用AddBookkeepingOperations來列印一些統計資料供我們之後觀察,這一部分不影響訓練部分,只是統計,列印日誌。

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")

在這裡,我們一共做了四件事:

(1)輸入部分(AddInput function)
(2)網路計算部分(AddLeNetModel function)
(3)網路訓練部分,新增梯度運算,更新等(AddTrainingOperators function)
(4)記錄統計部分,列印一些統計資料來觀察(AddBookkeepingOperators function)

基本的操作我們都定義好了,接下來呼叫定義模型,在這裡,它定義了一個訓練模型,用於訓練,一個部署模型,用於部署:

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.

執行網路,列印損耗曲線:

# 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')

我們也可以輸出來預測:

# 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')

記得我們也定義了一個test_model,我們可以執行它得到測試集準確率,雖然test_model的權值由train_model來載入,但是測試資料輸入還需要執行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

這樣,我們就簡單的完成了模型的搭建,訓練,部署。

這個教程是caffe2的蟒介面教程。教程例子基本都是官方提供的,只是加了些自己的理解思路,也簡單對比了CAFFE,可能有疏忽和理解錯的地方,敬請指正。