概要
class1 week3的任务是实现单隐层的神经网络代码，而本次任务是实现有L层的多层深度全连接神经网络。关键点跟class3的基本相同，算清各个参数的维度即可。
关键变量：
- m: 训练样本数量
- n[l]：第l层的节点数量，输入认为是第0层
- 方括号上标[l]: 第l层
- 圆括号上标(i): 第i个样本
$$ X = left[ egin{matrix} vdots & vdots & vdots & vdots \ x^{(1)} & x^{(2)} & vdots & x^{(m)} \ vdots & vdots & vdots & vdots \ end{matrix} ight]_{(n[0], m)} $$
$$ W^{[l]} = left[ egin{matrix} cdots & w^{[l] T}_1 & cdots \ cdots & w^{[l] T}_2 & cdots \ cdots & cdots & cdots \ cdots & w^{[l] T}_{n[l]} & cdots \ end{matrix} ight]_{(n[l], n[l-1])} $$
$$ b^{[l]} = left[ egin{matrix} b^{[l]}_1 \ b^{[l]}_2 \ vdots \ b^{[l]}_{n[l]} \ end{matrix} ight]_{(n[l], 1)} $$
$$ A^{[l]}= left[ egin{matrix} vdots & vdots & vdots & vdots \ a^{[l](1)} & a^{[l](2)} & vdots & a^{[l](m)} \ vdots & vdots & vdots & vdots \ end{matrix} ight]_{(n[l], m)} $$
$$ Z^{[l]}= left[ egin{matrix} vdots & vdots & vdots & vdots \ z^{[l](1)} & z^{[l](2)} & vdots & z^{[l](m)} \ vdots & vdots & vdots & vdots \ end{matrix} ight]_{(n[l], m)} $$
***深度神经网络关键公式：
- 前向传播
$$Z^{[l]}=W^{[l]}A^{[l-1]}+b^{[l]}$$ $$A^{[l]}=g^{[l]}(Z^{[l]})$$
当l < L - 1时，(g^{[l]})=relu函数
当l = L时，(g^{[L]})=sigmoid函数
即，输出层激活函数用sigmoid，其他层激活函数用relu函数。
- 反向传播
$$ dZ^{[l]} = dA^{[l]} * g'(Z^{[l]})$$ $$ dW^{[l]} = frac{partial mathcal{L} }{partial W^{[l]}} = frac{1}{m} dZ^{[l]} A^{[l-1] T}$$ $$ db^{[l]} = frac{partial mathcal{L} }{partial b^{[l]}} = frac{1}{m} sum_{i = 1}^{m} dZ^{[l](i)}$$ $$ dA^{[l-1]} = frac{partial mathcal{L} }{partial A^{[l-1]}} = W^{[l] T} dZ^{[l]}$$
初始化dAL:
dAL = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL))
- cost计算
$$-frac{1}{m} sumlimits_{i = 1}^{m} (y^{(i)}logleft(a^{[L] (i)} ight) + (1-y^{(i)})logleft(1- a^{[L](i)} ight))$$
深度全连接神经网代码:
- 关键函数：
# 初始化参数，每一层的权重初始化为随机
# 输入layer_dims是每一层的节点数
# 输出parameters是字典，可以通过parameters['W' + str(l)]，parameters['b' + str(l)]获取每一层的初始参数
parameters = initialize_parameters_deep(layer_dims)
# 线性前向传播函数
# 根据Z = W*A_prev + b计算当前层的Z， linear_cache=(A_prev, W, b)
Z, linear_cache = linear_forward(A_prev, W, b)
# 线性激活前向传播函数
# 根据A = g(Z) = g(W*A_prev + b)计算前向传播函数, 其中linear_activation_cache=(linear_cache, activation_cache)=((A_prev, W, b), (Z))
A, linear_activation_cache = linear_activation_forward(A_prev, W, b, activation = "sigmoid")
# L层完整的前向传输过程，输出的AL是最终输出，caches是每一层的缓存
AL, caches = L_model_forward(X, parameters)
# 线性反向传播函数
# 通过上述反向传播函数，通过dZ推导出dA_prev, dW, db，其中利用了缓存结果
dA_prev, dW, db = linear_backward(dZ, linear_cache)
# 线性激活函数反向传播
# 通过前面的linear_backward和激活函数导数计算dA_prev, dW, db
dA_prev, dW, db = linear_activation_backward(dA, linear_activation_cache, activation = "sigmoid")
# L层反向传播
# grads是每一层的导数，grads["dA" + str(l)]， grads["dW" + str(l)]， grads["db" + str(l)]格式
grads = L_model_backward(AL, Y, caches)
# 根据学习速率跟新参数
parameters = update_parameters(parameters, grads, 0.1)
# 整体模型函数，通过迭代次数循环调用上述前向传播和反向传播函数实现
parameters = L_layer_model(train_x, train_y, layers_dims, learning_rate = 0.0075, num_iterations = 2500, print_cost = True)
- 完整代码：
import numpy as np
import matplotlib.pyplot as plt
import h5py
def sigmoid(Z):
"""
Implements the sigmoid activation in numpy
Arguments:
Z -- numpy array of any shape
Returns:
A -- output of sigmoid(z), same shape as Z
cache -- returns Z as well, useful during backpropagation
"""
A = 1/(1+np.exp(-Z))
cache = Z
return A, cache
def relu(Z):
"""
Implement the RELU function.
Arguments:
Z -- Output of the linear layer, of any shape
Returns:
A -- Post-activation parameter, of the same shape as Z
cache -- a python dictionary containing "A" ; stored for computing the backward pass efficiently
"""
A = np.maximum(0,Z)
assert(A.shape == Z.shape)
cache = Z
return A, cache
def relu_backward(dA, cache):
"""
Implement the backward propagation for a single RELU unit.
Arguments:
dA -- post-activation gradient, of any shape
cache -- 'Z' where we store for computing backward propagation efficiently
Returns:
dZ -- Gradient of the cost with respect to Z
"""
Z = cache
dZ = np.array(dA, copy=True) # just converting dz to a correct object.
# When z <= 0, you should set dz to 0 as well.
dZ[Z <= 0] = 0
assert (dZ.shape == Z.shape)
return dZ
def sigmoid_backward(dA, cache):
"""
Implement the backward propagation for a single SIGMOID unit.
Arguments:
dA -- post-activation gradient, of any shape
cache -- 'Z' where we store for computing backward propagation efficiently
Returns:
dZ -- Gradient of the cost with respect to Z
"""
Z = cache
s = 1/(1+np.exp(-Z))
dZ = dA * s * (1-s)
assert (dZ.shape == Z.shape)
return dZ
def load_data():
train_dataset = h5py.File('datasets/train_catvnoncat.h5', "r")
train_set_x_orig = np.array(train_dataset["train_set_x"][:]) # your train set features
train_set_y_orig = np.array(train_dataset["train_set_y"][:]) # your train set labels
test_dataset = h5py.File('datasets/test_catvnoncat.h5', "r")
test_set_x_orig = np.array(test_dataset["test_set_x"][:]) # your test set features
test_set_y_orig = np.array(test_dataset["test_set_y"][:]) # your test set labels
classes = np.array(test_dataset["list_classes"][:]) # the list of classes
train_set_y_orig = train_set_y_orig.reshape((1, train_set_y_orig.shape[0]))
test_set_y_orig = test_set_y_orig.reshape((1, test_set_y_orig.shape[0]))
return train_set_x_orig, train_set_y_orig, test_set_x_orig, test_set_y_orig, classes
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(1)
parameters = {}
L = len(layer_dims) # number of layers in the network
for l in range(1, L):
parameters['W' + str(l)] = np.random.randn(layer_dims[l], layer_dims[l-1]) / np.sqrt(layer_dims[l-1]) #*0.01
parameters['b' + str(l)] = np.zeros((layer_dims[l], 1))
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
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
"""
Z = W.dot(A) + b
assert(Z.shape == (W.shape[0], A.shape[1]))
cache = (A, W, b)
return Z, cache
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".
Z, linear_cache = linear_forward(A_prev, W, b)
A, activation_cache = sigmoid(Z)
elif activation == "relu":
# Inputs: "A_prev, W, b". Outputs: "A, activation_cache".
Z, linear_cache = linear_forward(A_prev, W, b)
A, activation_cache = relu(Z)
assert (A.shape == (W.shape[0], A_prev.shape[1]))
cache = (linear_cache, activation_cache)
return A, cache
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
A, cache = linear_activation_forward(A_prev, parameters['W' + str(l)], parameters['b' + str(l)], activation = "relu")
caches.append(cache)
# Implement LINEAR -> SIGMOID. Add "cache" to the "caches" list.
AL, cache = linear_activation_forward(A, parameters['W' + str(L)], parameters['b' + str(L)], activation = "sigmoid")
caches.append(cache)
assert(AL.shape == (1,X.shape[1]))
return AL, caches
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.
cost = (1./m) * (-np.dot(Y,np.log(AL).T) - np.dot(1-Y, np.log(1-AL).T))
cost = np.squeeze(cost) # To make sure your cost's shape is what we expect (e.g. this turns [[17]] into 17).
assert(cost.shape == ())
return cost
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]
dW = 1./m * np.dot(dZ,A_prev.T)
db = 1./m * np.sum(dZ, axis = 1, keepdims = True)
dA_prev = np.dot(W.T,dZ)
assert (dA_prev.shape == A_prev.shape)
assert (dW.shape == W.shape)
assert (db.shape == b.shape)
return dA_prev, dW, db
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":
dZ = relu_backward(dA, activation_cache)
dA_prev, dW, db = linear_backward(dZ, linear_cache)
elif activation == "sigmoid":
dZ = sigmoid_backward(dA, activation_cache)
dA_prev, dW, db = linear_backward(dZ, linear_cache)
return dA_prev, dW, db
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" (there are (L-1) or them, indexes from 0 to L-2)
the cache of linear_activation_forward() with "sigmoid" (there is one, index 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
dAL = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL))
# Lth layer (SIGMOID -> LINEAR) gradients. Inputs: "AL, Y, caches". Outputs: "grads["dAL"], grads["dWL"], grads["dbL"]
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")
for l in reversed(range(L-1)):
# lth layer: (RELU -> LINEAR) gradients.
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
return grads
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.
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)]
return parameters
# GRADED FUNCTION: L_layer_model
def L_layer_model(X, Y, layers_dims, learning_rate = 0.0075, num_iterations = 3000, print_cost=False):#lr was 0.009
"""
Implements a L-layer neural network: [LINEAR->RELU]*(L-1)->LINEAR->SIGMOID.
Arguments:
X -- data, numpy array of shape (number of examples, num_px * num_px * 3)
Y -- true "label" vector (containing 0 if cat, 1 if non-cat), of shape (1, number of examples)
layers_dims -- list containing the input size and each layer size, of length (number of layers + 1).
learning_rate -- learning rate of the gradient descent update rule
num_iterations -- number of iterations of the optimization loop
print_cost -- if True, it prints the cost every 100 steps
Returns:
parameters -- parameters learnt by the model. They can then be used to predict.
"""
np.random.seed(1)
costs = [] # keep track of cost
# Parameters initialization.
### START CODE HERE ###
parameters = initialize_parameters_deep(layers_dims)
### END CODE HERE ###
# Loop (gradient descent)
for i in range(0, num_iterations):
# Forward propagation: [LINEAR -> RELU]*(L-1) -> LINEAR -> SIGMOID.
### START CODE HERE ### (≈ 1 line of code)
AL, caches = L_model_forward(X, parameters)
### END CODE HERE ###
# Compute cost.
### START CODE HERE ### (≈ 1 line of code)
cost = compute_cost(AL, Y)
### END CODE HERE ###
# Backward propagation.
### START CODE HERE ### (≈ 1 line of code)
grads = L_model_backward(AL, Y, caches)
### END CODE HERE ###
# Update parameters.
### START CODE HERE ### (≈ 1 line of code)
parameters = update_parameters(parameters, grads, learning_rate)
### END CODE HERE ###
# Print the cost every 100 training example
if print_cost and i % 100 == 0:
print ("Cost after iteration %i: %f" %(i, cost))
if print_cost and i % 100 == 0:
costs.append(cost)
# plot the cost
plt.plot(np.squeeze(costs))
plt.ylabel('cost')
plt.xlabel('iterations (per tens)')
plt.title("Learning rate =" + str(learning_rate))
plt.show()
return parameters
def predict(X, y, parameters):
"""
This function is used to predict the results of a L-layer neural network.
Arguments:
X -- data set of examples you would like to label
parameters -- parameters of the trained model
Returns:
p -- predictions for the given dataset X
"""
m = X.shape[1]
n = len(parameters) // 2 # number of layers in the neural network
p = np.zeros((1,m))
# Forward propagation
probas, caches = L_model_forward(X, parameters)
# convert probas to 0/1 predictions
for i in range(0, probas.shape[1]):
if probas[0,i] > 0.5:
p[0,i] = 1
else:
p[0,i] = 0
#print results
#print ("predictions: " + str(p))
#print ("true labels: " + str(y))
print("Accuracy: " + str(np.sum((p == y)/m)))
return p
train_x_orig, train_y, test_x_orig, test_y, classes = load_data()
# 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.
layers_dims = [12288, 20, 7, 5, 1]
parameters = L_layer_model(train_x, train_y, layers_dims, learning_rate = 0.0075, num_iterations = 2500, print_cost = True)
predictions_train = predict(train_x, train_y, parameters)
pred_test = predict(test_x, test_y, parameters)