Building your Deep Neural Network: Step by Step
导包
import numpy as np
import h5py
import matplotlib.pyplot as plt
from testCases_v2 import *
from dnn_utils_v2 import sigmoid, sigmoid_backward, relu, relu_backward
%matplotlib inline
plt.rcParams['figure.figsize'] = (5.0, 4.0) # set default size of plots
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'
%load_ext autoreload
%autoreload 2
np.random.seed(1)
initialize_parameters
- 初始化每一层的w,b
# GRADED FUNCTION: initialize_parameters
def initialize_parameters(n_x, n_h, n_y):
"""
Argument:
n_x -- size of the input layer
n_h -- size of the hidden layer
n_y -- size of the output layer
Returns:
parameters -- python dictionary containing your parameters:
W1 -- weight matrix of shape (n_h, n_x)
b1 -- bias vector of shape (n_h, 1)
W2 -- weight matrix of shape (n_y, n_h)
b2 -- bias vector of shape (n_y, 1)
"""
np.random.seed(1)
### START CODE HERE ### (≈ 4 lines of code)
W1 = np.random.randn(n_h , n_x) * 0.01
b1 = np.zeros((n_h , 1))
W2 = np.random.randn(n_y , n_h) * 0.01
b2 = np.zeros((n_y , 1))
### END CODE HERE ###
assert(W1.shape == (n_h, n_x))
assert(b1.shape == (n_h, 1))
assert(W2.shape == (n_y, n_h))
assert(b2.shape == (n_y, 1))
parameters = {"W1": W1,
"b1": b1,
"W2": W2,
"b2": b2}
return parameters
initialize_parameters_deep
# GRADED FUNCTION: initialize_parameters_deep
def initialize_parameters_deep(layer_dims):
"""
Arguments:
layer_dims -- python array (list) containing the dimensions of each layer in our network
Returns:
parameters -- python dictionary containing your parameters "W1", "b1", ..., "WL", "bL":
Wl -- weight matrix of shape (layer_dims[l], layer_dims[l-1])
bl -- bias vector of shape (layer_dims[l], 1)
"""
np.random.seed(3)
parameters = {}
L = len(layer_dims) # number of layers in the network
for l in range(1, L):
### START CODE HERE ### (≈ 2 lines of code)
parameters['W' + str(l)] = np.random.randn(layer_dims[l] , layer_dims[l-1]) * 0.01
parameters['b' + str(l)] = np.zeros((layer_dims[l] , 1))
### END CODE HERE ###
assert(parameters['W' + str(l)].shape == (layer_dims[l], layer_dims[l-1]))
assert(parameters['b' + str(l)].shape == (layer_dims[l], 1))
return parameters
linear_forward
- 共有的线性方程求Z
- 返回当前未更新参数的A,W,b
# GRADED FUNCTION: linear_forward
def linear_forward(A, W, b):
"""
Implement the linear part of a layer's forward propagation.
Arguments:
A -- activations from previous layer (or input data): (size of previous layer, number of examples)
W -- weights matrix: numpy array of shape (size of current layer, size of previous layer)
b -- bias vector, numpy array of shape (size of the current layer, 1)
Returns:
Z -- the input of the activation function, also called pre-activation parameter
cache -- a python dictionary containing "A", "W" and "b" ; stored for computing the backward pass efficiently
"""
### START CODE HERE ### (≈ 1 line of code)
Z = np.dot(W , A) + b
### END CODE HERE ###
assert(Z.shape == (W.shape[0], A.shape[1]))
cache = (A, W, b)
return Z, cache
linear_activation_forward
函数输入A_prev,W,b,activation,输出这下层的激活参数以及这一层的相关cache
- linear_cache A 是前一层的激活输出(或输入层的输入数据), W 是当前层的权重矩阵, b 是当前层的偏置向量
- activation_cache 是应用激活函数前的线性输出 Z 。
# GRADED FUNCTION: linear_activation_forward
def linear_activation_forward(A_prev, W, b, activation):
"""
Implement the forward propagation for the LINEAR->ACTIVATION layer
Arguments:
A_prev -- activations from previous layer (or input data): (size of previous layer, number of examples)
W -- weights matrix: numpy array of shape (size of current layer, size of previous layer)
b -- bias vector, numpy array of shape (size of the current layer, 1)
activation -- the activation to be used in this layer, stored as a text string: "sigmoid" or "relu"
Returns:
A -- the output of the activation function, also called the post-activation value
cache -- a python dictionary containing "linear_cache" and "activation_cache";
stored for computing the backward pass efficiently
"""
if activation == "sigmoid":
# Inputs: "A_prev, W, b". Outputs: "A, activation_cache".
### START CODE HERE ### (≈ 2 lines of code)
Z, linear_cache= linear_forward(A_prev, W, b)
A, activation_cache = sigmoid(Z)
### END CODE HERE ###
elif activation == "relu":
# Inputs: "A_prev, W, b". Outputs: "A, activation_cache".
### START CODE HERE ### (≈ 2 lines of code)
Z, linear_cache = linear_forward(A_prev, W , b)
A, activation_cache = relu(Z)
### END CODE HERE ###
assert (A.shape == (W.shape[0], A_prev.shape[1]))
'''
linear_cache 是前一层的 A 是前一层的激活输出(或输入层的输入数据), W 是当前层的权重矩阵, b 是当前层的偏置向量
activation_cache 是应用激活函数前的线性输出 Z 。
'''
cache = (linear_cache, activation_cache)
return A, cache
L_model_forward
前L-1层调用 relu ,最后第L层调用 sigmoid
- AL 是最后的输出结果
- caches保存每一层的 A,W,b,Z
# GRADED FUNCTION: L_model_forward
def L_model_forward(X, parameters):
"""
Implement forward propagation for the [LINEAR->RELU]*(L-1)->LINEAR->SIGMOID computation
Arguments:
X -- data, numpy array of shape (input size, number of examples)
parameters -- output of initialize_parameters_deep()
Returns:
AL -- last post-activation value
caches -- list of caches containing:
every cache of linear_relu_forward() (there are L-1 of them, indexed from 0 to L-2)
the cache of linear_sigmoid_forward() (there is one, indexed L-1)
"""
caches = []
A = X
L = len(parameters) // 2 # number of layers in the neural network
# Implement [LINEAR -> RELU]*(L-1). Add "cache" to the "caches" list.
for l in range(1, L):
A_prev = A
### START CODE HERE ### (≈ 2 lines of code)
A, cache = linear_activation_forward(A_prev , parameters["W" + str(l)] , parameters["b" + str(l)] , activation="relu")
caches.append(cache)
### END CODE HERE ###
# Implement LINEAR -> SIGMOID. Add "cache" to the "caches" list.
### START CODE HERE ### (≈ 2 lines of code)
AL, cache = linear_activation_forward(A, parameters["W" + str(L)], parameters["b" + str(L)] , activation="sigmoid")
caches.append(cache)
### END CODE HERE ###
assert(AL.shape == (1,X.shape[1]))
return AL, caches
compute_cost
J = − 1 m ∑ i = 1 m ( y ( i ) log ( a [ L ] ( i ) ) + ( 1 − y ( i ) ) log ( 1 − a [ L ] ( i ) ) ) J = -\frac{1}{m} \sum\limits_{i = 1}^{m} (y^{(i)}\log\left(a^{[L] (i)}\right) + (1-y^{(i)})\log\left(1- a^{[L](i)}\right)) J=−m1i=1∑m(y(i)log(a[L](i))+(1−y(i))log(1−a[L](i)))
# GRADED FUNCTION: compute_cost
def compute_cost(AL, Y):
"""
Implement the cost function defined by equation (7).
Arguments:
AL -- probability vector corresponding to your label predictions, shape (1, number of examples)
Y -- true "label" vector (for example: containing 0 if non-cat, 1 if cat), shape (1, number of examples)
Returns:
cost -- cross-entropy cost
"""
m = Y.shape[1]
# Compute loss from aL and y.
### START CODE HERE ### (≈ 1 lines of code)
cost = - np.sum( Y * np.log(AL) + (1-Y)* np.log(1-AL)) / m
### END CODE HERE ###
cost = np.squeeze(cost) # To make sure your cost's shape is what we expect (e.g. this turns [[17]] into 17).
return cost
linear_backward
d
W
[
l
]
=
∂
L
∂
W
[
l
]
=
1
m
d
Z
[
l
]
A
[
l
−
1
]
T
dW^{[l]} = \frac{\partial \mathcal{L} }{\partial W^{[l]}} = \frac{1}{m} dZ^{[l]} A^{[l-1] T}
dW[l]=∂W[l]∂L=m1dZ[l]A[l−1]T
d
b
[
l
]
=
∂
L
∂
b
[
l
]
=
1
m
∑
i
=
1
m
d
Z
[
l
]
(
i
)
db^{[l]} = \frac{\partial \mathcal{L} }{\partial b^{[l]}} = \frac{1}{m} \sum_{i = 1}^{m} dZ^{[l](i)}
db[l]=∂b[l]∂L=m1i=1∑mdZ[l](i)
d
A
[
l
−
1
]
=
∂
L
∂
A
[
l
−
1
]
=
W
[
l
]
T
d
Z
[
l
]
dA^{[l-1]} = \frac{\partial \mathcal{L} }{\partial A^{[l-1]}} = W^{[l] T} dZ^{[l]}
dA[l−1]=∂A[l−1]∂L=W[l]TdZ[l]
- 共有操作,已知dz,求dw,db,dA_prev
# GRADED FUNCTION: linear_backward
def linear_backward(dZ, cache):
"""
Implement the linear portion of backward propagation for a single layer (layer l)
Arguments:
dZ -- Gradient of the cost with respect to the linear output (of current layer l)
cache -- tuple of values (A_prev, W, b) coming from the forward propagation in the current layer
Returns:
dA_prev -- Gradient of the cost with respect to the activation (of the previous layer l-1), same shape as A_prev
dW -- Gradient of the cost with respect to W (current layer l), same shape as W
db -- Gradient of the cost with respect to b (current layer l), same shape as b
"""
A_prev, W, b = cache
m = A_prev.shape[1]
### START CODE HERE ### (≈ 3 lines of code)
dW = np.dot(dZ , A_prev.T) / m
db = np.sum(dZ , axis=1 , keepdims=True) / m
dA_prev = np.dot(W.T , dZ)
### END CODE HERE ###
assert (dA_prev.shape == A_prev.shape)
assert (dW.shape == W.shape)
assert (db.shape == b.shape)
return dA_prev, dW, db
linear_activation_backward
d Z [ l ] = d A [ l ] ∗ g ′ ( Z [ l ] ) dZ^{[l]} = dA^{[l]} * g'(Z^{[l]}) dZ[l]=dA[l]∗g′(Z[l])
- 根据activation_cache的Z 以及 已知的dA,求dZ
- 根据dZ,用上面的函数linear_backward,求dw,db,dA_prev
# GRADED FUNCTION: linear_activation_backward
def linear_activation_backward(dA, cache, activation):
"""
Implement the backward propagation for the LINEAR->ACTIVATION layer.
Arguments:
dA -- post-activation gradient for current layer l
cache -- tuple of values (linear_cache, activation_cache) we store for computing backward propagation efficiently
activation -- the activation to be used in this layer, stored as a text string: "sigmoid" or "relu"
Returns:
dA_prev -- Gradient of the cost with respect to the activation (of the previous layer l-1), same shape as A_prev
dW -- Gradient of the cost with respect to W (current layer l), same shape as W
db -- Gradient of the cost with respect to b (current layer l), same shape as b
"""
linear_cache, activation_cache = cache
if activation == "relu":
### START CODE HERE ### (≈ 2 lines of code)
dZ = relu_backward(dA , activation_cache)
dA_prev, dW, db = linear_backward(dZ , linear_cache)
### END CODE HERE ###
elif activation == "sigmoid":
### START CODE HERE ### (≈ 2 lines of code)
dZ = sigmoid_backward(dA , activation_cache)
dA_prev, dW, db = linear_backward(dZ , linear_cache)
### END CODE HERE ###
return dA_prev, dW, db
L_model_backwar
第L层用sigmoid的后向传播,剩下L-1层用relu的后向传播
A
[
L
]
=
σ
(
Z
[
L
]
)
A^{[L]} = \sigma(Z^{[L]})
A[L]=σ(Z[L])
d
A
[
L
]
=
∂
L
∂
A
[
L
]
dA^{[L]}= \frac{\partial \mathcal{L}}{\partial A^{[L]}}
dA[L]=∂A[L]∂L
dAL = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL))
- grads 记录每一层的dA,dW,db
- 用后一层的dA,上面的函数linear_activation_backward,求dA,dW,db,并保存。
# GRADED FUNCTION: L_model_backward
def L_model_backward(AL, Y, caches):
"""
Implement the backward propagation for the [LINEAR->RELU] * (L-1) -> LINEAR -> SIGMOID group
Arguments:
AL -- probability vector, output of the forward propagation (L_model_forward())
Y -- true "label" vector (containing 0 if non-cat, 1 if cat)
caches -- list of caches containing:
every cache of linear_activation_forward() with "relu" (it's caches[l], for l in range(L-1) i.e l = 0...L-2)
the cache of linear_activation_forward() with "sigmoid" (it's caches[L-1])
Returns:
grads -- A dictionary with the gradients
grads["dA" + str(l)] = ...
grads["dW" + str(l)] = ...
grads["db" + str(l)] = ...
"""
grads = {}
L = len(caches) # the number of layers
m = AL.shape[1]
Y = Y.reshape(AL.shape) # after this line, Y is the same shape as AL
# Initializing the backpropagation
### START CODE HERE ### (1 line of code)
dAL = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL))
### END CODE HERE ###
# Lth layer (SIGMOID -> LINEAR) gradients. Inputs: "AL, Y, caches". Outputs: "grads["dAL"], grads["dWL"], grads["dbL"]
### START CODE HERE ### (approx. 2 lines)
current_cache = caches[L-1]
grads["dA" + str(L)], grads['dW' + str(L)], grads["db" + str(L)]= linear_activation_backward(dAL, current_cache, activation='sigmoid')
### END CODE HERE ###
for l in reversed(range(L - 1)):
# lth layer: (RELU -> LINEAR) gradients.
# Inputs: "grads["dA" + str(l + 2)], caches". Outputs: "grads["dA" + str(l + 1)] , grads["dW" + str(l + 1)] , grads["db" + str(l + 1)]
### START CODE HERE ### (approx. 5 lines)
current_cache = caches[l]
dA_prev_temp, dW_temp, db_temp = linear_activation_backward(grads["dA" + str(l + 2)], current_cache, activation="relu")
grads["dA" + str(l + 1)] = dA_prev_temp
grads["dW" + str(l + 1)] = dW_temp
grads["db" + str(l + 1)] = db_temp
### END CODE HERE ###
return grads
update_parameters
- 已知每一层的grads(dW,db)更新parameters中每一层的W,b
# GRADED FUNCTION: update_parameters
def update_parameters(parameters, grads, learning_rate):
"""
Update parameters using gradient descent
Arguments:
parameters -- python dictionary containing your parameters
grads -- python dictionary containing your gradients, output of L_model_backward
Returns:
parameters -- python dictionary containing your updated parameters
parameters["W" + str(l)] = ...
parameters["b" + str(l)] = ...
"""
L = len(parameters) // 2 # number of layers in the neural network
# Update rule for each parameter. Use a for loop.
### START CODE HERE ### (≈ 3 lines of code)
for l in range(L):
parameters['W' + str(l+1)] = parameters['W' + str(l+1)] - learning_rate * grads['dW' + str[l+1]]
parameters['b' + str(l+1)] = parameters['b' + str(l+1)] - learning_rate * grads['db' + str[l+1]]
### END CODE HERE ###
return parameters
model
def L_layer_model(X,Y,layers_dims,learning_rate=0.0075,num_iterations=3000,print_cost=False,isPlot=True):
grads = {}#梯度
costs = []
#初始化参数
parameters = initialize_parameters_deep(layers_dims)
#开始进行迭代
for i in range(0,num_iterations):
#前向传播
AL, caches = L_model_forward(X, parameters)
#计算成本
cost = compute_cost(AL,Y)
#后向传播
grads = L_model_backward(AL , Y , caches)
#更新参数
parameters = update_parameters(parameters,grads,learning_rate)
#打印成本值,迭代100次打印一次,如果print_cost=False则忽略
if i % 100 == 0:
#记录成本
costs.append(cost)
#是否打印成本值
if print_cost:
print("第", i ,"次迭代,成本值为:" ,np.squeeze(cost))
#迭代完成,绘制图
if isPlot:
plt.plot(np.squeeze(costs))
plt.ylabel('cost')
plt.xlabel('iterations (per tens)')
plt.title("Learning rate =" + str(learning_rate))
plt.show()
#返回parameters
return parameters
跑数据
import time
import numpy as np
import h5py
import matplotlib.pyplot as plt
import scipy
from PIL import Image
from scipy import ndimage
from dnn_app_utils_v2 import *
# load_data predict print_mislabeled_images 都这个文件里 dnn_app_utils_v2
%matplotlib inline
plt.rcParams['figure.figsize'] = (5.0, 4.0) # set default size of plots
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'
%load_ext autoreload
%autoreload 2
np.random.seed(1)
train_x_orig, train_y, test_x_orig, test_y, classes = load_data()
# Example of a picture
index = 7
plt.imshow(train_x_orig[index])
print ("y = " + str(train_y[0,index]) + ". It's a " + classes[train_y[0,index]].decode("utf-8") + " picture.")
# Explore your dataset
m_train = train_x_orig.shape[0]
num_px = train_x_orig.shape[1]
m_test = test_x_orig.shape[0]
print ("Number of training examples: " + str(m_train))
print ("Number of testing examples: " + str(m_test))
print ("Each image is of size: (" + str(num_px) + ", " + str(num_px) + ", 3)")
print ("train_x_orig shape: " + str(train_x_orig.shape))
print ("train_y shape: " + str(train_y.shape))
print ("test_x_orig shape: " + str(test_x_orig.shape))
print ("test_y shape: " + str(test_y.shape))
# Reshape the training and test examples
train_x_flatten = train_x_orig.reshape(train_x_orig.shape[0], -1).T # The "-1" makes reshape flatten the remaining dimensions
test_x_flatten = test_x_orig.reshape(test_x_orig.shape[0], -1).T
# Standardize data to have feature values between 0 and 1.
train_x = train_x_flatten/255.
test_x = test_x_flatten/255.
print ("train_x's shape: " + str(train_x.shape))
print ("test_x's shape: " + str(test_x.shape))
layers_dims = [12288, 20, 7, 5, 1]
parameters = L_layer_model(train_x, train_y, layers_dims, num_iterations = 2500, print_cost = True)
pred_train = predict(train_x, train_y, parameters) # 0.9856459330143539
pred_test = predict(test_x, test_y, parameters) # 0.8
# 打印错误识别的图像
print_mislabeled_images(classes, test_x, test_y, pred_test)
测试自己的数据
my_image = "my_image5.jpg"
my_label_y = 1
fname = "images/" + my_image
image = np.array(plt.imread(fname))
my_image = np.array(Image.fromarray(image).resize((num_px, num_px)))
my_image_flatten = my_image.reshape(1 , -1).T # (64 * 64 * 3 , 1)
my_image_x = my_image_flatten / 255
my_predicted_image = predict(my_image_x, my_label_y, parameters)
plt.imshow(image)
print ("y = " + str(np.squeeze(my_predicted_image)) + ", your L-layer model predicts a \"" + classes[int(np.squeeze(my_predicted_image)),].decode("utf-8") + "\" picture.")
- 预测结果挺准的,hahaha,挺有成就感的。
- 当然,模型还是很基础。如果拿一个狗的图像测试就不准了。
- 可能只是通过判断是否具有某种轮廓,判断是否是cat