def model(X,
Y,
layers,
optimizer,
learning_rate=0.0007,
mini_batch_size=64,
beta=0.9,
beta1=0.9,
beta2=0.999,
epsilon=1e-8,
num_epochs=10000,
print_cost=True):
L = len(layers)
costs = []
t = 0
seed = 10
parameters = initialize_parameters(layers)
if optimizer == 'gd':
pass
elif optimizer == 'momentum':
v = init_velocity(parameters)
elif optimizer == 'adam':
v, s = init_adam(parameters)
for i in range(num_epochs):
seed = seed + 1
minibatches = random_mini_batches(X, Y, mini_batch_size, seed)
for minibatch in minibatches:
(minibatch_X, minibatch_Y) = minibatch
# print(minibatch_Y.shape)
a3, caches = forward_propagation(minibatch_X, parameters)
cost = compute_cost(a3, minibatch_Y)
grads = backward_propagation(minibatch_X, minibatch_Y, caches)
if optimizer == 'gd':
parameters = update_parameters_with_grad(
parameters, grads, learning_rate)
elif optimizer == 'momentum':
parameters = update_parameters_with_momentum(
parameters, grads, v, beta, learning_rate)
elif optimizer == 'adam':
t = t + 1
parameters, v, s = update_parameters_with_adam(
parameters, grads, v, s, t, learning_rate, beta1, beta2,
epsilon)
if print_cost and i % 1000 == 0:
print('cost after epoch %i:%f' % (i, cost))
if print_cost and i % 100 == 0:
costs.append(cost)
plt.plot(costs)
plt.ylabel('cost')
plt.xlabel('epochs (per 100)')
plt.title("Learning rate = " + str(learning_rate))
plt.show()
return parameters
def model(X, Y, layers_dims, optimizer, learning_rate=0.0007, mini_batch_size=64, beta=0.9,
beta1=0.9, beta2=0.999, epsilon=1e-8, num_epochs=10000, print_cost=True):
"""
3-layer neural network model which can be run in different optimizer modes.
Arguments:
X -- input data, of shape (2, number of examples)
Y -- true "label" vector (1 for blue dot / 0 for red dot), of shape (1, number of examples)
layers_dims -- python list, containing the size of each layer
learning_rate -- the learning rate, scalar.
mini_batch_size -- the size of a mini batch
beta -- Momentum hyperparameter
beta1 -- Exponential decay hyperparameter for the past gradients estimates
beta2 -- Exponential decay hyperparameter for the past squared gradients estimates
epsilon -- hyperparameter preventing division by zero in Adam updates
num_epochs -- number of epochs
print_cost -- True to print the cost every 1000 epochs
Returns:
parameters -- python dictionary containing your updated parameters
"""
L = len(layers_dims)
costs = []
t = 0
seed = 10
parameters = initialize_parameters(layers_dims)
if optimizer == 'gd':
pass
elif optimizer == 'momentum':
v = initialize_velocity(parameters)
elif optimizer == 'adam':
v, s = initialize_adam(parameters)
for i in range(num_epochs):
seed = seed + 1
mini_batches = random_mini_batches(X, Y, mini_batch_size, seed)
for mini_batch in mini_batches:
(mini_batch_X, mini_batch_Y) = mini_batch
a3, caches = forward_propagation(mini_batch_X, parameters)
cost = compute_cost(a3, mini_batch_Y)
grads = backward_propagation(mini_batch_X, mini_batch_Y, caches)
#update parameters
if optimizer == 'gd':
parameters = update_parameters_with_gd(parameters, grads, learning_rate)
elif optimizer == 'momentum':
parameters, v = update_parameters_with_momentum(parameters, grads, v, beta, learning_rate)
elif optimizer == 'adam':
t = t + 1
parameters, v, s = update_parameters_with_adam(parameters, grads, v, s, t, learning_rate, beta1, beta2, epsilon)
if print_cost and i % 1000 == 0:
print('Cost after epoch %i: %f'%(i, cost))
if print_cost and i % 100 == 0:
costs.append(cost)
plt.plot(costs)
plt.ylabel('cost')
plt.xlabel('epochs (per 100)')
plt.title('learning rate= ' + str(learning_rate))
plt.show()
return parameters
def model_opt(X, Y, layer_dims, optimizer:str, alpha=0.08, mini_batch_size=64, beta1=0.9, beta2=0.999, epochs=10000):
L = len(layer_dims)
costs = []
t = 0
seed = 1
# initial weights
params = opt_utils.initialize_parameters(layer_dims)
# initial optimizer
if optimizer == 'gd':
pass
elif optimizer == 'momentum':
V = init_momentum(params)
elif optimizer == 'adam':
V, S = init_adam(params)
else:
print('Unexcepted optimizer!')
# train
for i in range(epochs):
## shuffle and get new mini_batches
seed += 1
mini_batches = random_mini_batches(X, Y,mini_batch_size, seed)
for batch in mini_batches:
### get X,Y in batch
mini_X, mini_Y = batch
### forward propagate
A3, cache = opt_utils.forward_propagation(mini_X, params)
### compute loss
cost = opt_utils.compute_cost(A3, mini_Y)
### backward propagate
grads = opt_utils.backward_propagation(mini_X, mini_Y, cache)
### update params
if optimizer == 'gd':
params = update_params_with_gd(params, grads, alpha)
elif optimizer == 'momentum':
params, V = update_params_with_momentum(params, grads, V, beta1, alpha)
elif optimizer == 'adam':
t += 1
params, V, S = update_params_with_adam(params, grads, V, S, t, alpha, beta1, beta2)
else:
print('Unexcepted optimizer!')
if (i+1) % 100 == 0:
costs.append(cost)
print(f'No.{i+1} iteration\'s loss: {cost}')
plt.plot(costs)
plt.xlabel('# iterations per 100')
plt.ylabel('loss')
plt.title(f'{optimizer} loss circle')
plt.show()
return params
def model(X,Y,layers_dims,optimizer,learning_rate = 0.0007,mini_batch_size = 64, beta = 0.9,
beta1 = 0.9, beta2 = 0.999, epsilon = 1e-8, num_epochs = 10000,print_cost = True):
L = len(layers_dims)
costs = []
t = 0
seed = 10
parameters = initialize_parameters(layers_dims)
if optimizer == "gd":
pass
elif optimizer == "momentum":
v = initialize_velocity(parameters)
elif optimizer == "adam":
v,s = initialize_adam(parameters)
for i in range(num_epochs):#{
seed = seed + 1
minibatches = random_mini_batches(X,Y,mini_batch_size,seed)
for minibatch in minibatches:#{
(minibatch_X,minibatch_Y) = minibatch
a3,caches = forward_propagation(minibatch_X,parameters)
cost = compute_cost(a3,minibatch_Y)
grads = backward_propagation(minibatch_X,minibatch_Y,caches)
if optimizer == "gd":
parameters = update_parameters_with_gd(parameters,grads,learning_rate)
elif optimizer == "momentum":
parameters,v == update_parameters_with_momentum(parameters,grads,v,beta,learning_rate)
elif optimizer == "adam":
t = t + 1 #时间量，用于Adam更新参数前，偏差修正
parameters,v,s == update_parameters_with_adam(parameters,grads,v,s,t,learning_rate,beta1,beta2,epsilon)
#}
if print_cost and i%1000 == 0:
print("Cost after epoch %i:%f"%(i,cost))
if print_cost and i%100 == 0 :
costs.append(cost)
#}
# plot the cost
plt.plot(costs)
plt.ylabel('cost')
plt.xlabel('epochs (per 100)')
plt.title("Learning rate = " + str(learning_rate))
plt.show()
return parameters
def model(X,
Y,
layers_dims,
optimizer,
learning_rate=0.0007,
mini_batch_size=64,
beta=0.9,
beta1=0.9,
beta2=0.999,
epsilon=1e-8,
num_epochs=10000,
print_cost=True):
L = len(layers_dims) # number of layers in the neural networks
costs = [] # to keep track of the cost
t = 0 # initializing the counter required for Adam update
seed = 10 # For grading purposes, so that your "random" minibatches are the same as ours
# Initialize parameters
parameters = initialize_parameters(layers_dims)
# Initialize the optimizer
if optimizer == "gd":
pass # no initialization required for gradient descent
elif optimizer == "momentum":
v = initialize_velocity(parameters)
elif optimizer == "adam":
v, s = initialize_adam(parameters)
# Optimization loop
for i in range(num_epochs):
# Define the random minibatches. We increment the seed to reshuffle differently the dataset after each epoch
seed = seed + 1
minibatches = random_mini_batches(X, Y, mini_batch_size, seed)
for minibatch in minibatches:
# Select a minibatch
(minibatch_X, minibatch_Y) = minibatch
# Forward propagation
a3, caches = forward_propagation(minibatch_X, parameters)
# Compute cost
cost = compute_cost(a3, minibatch_Y)
# Backward propagation
grads = backward_propagation(minibatch_X, minibatch_Y, caches)
# Update parameters
if optimizer == "gd":
parameters = update_parameters_with_gd(parameters, grads,
learning_rate)
elif optimizer == "momentum":
parameters, v = update_parameters_with_momentum(
parameters, grads, v, beta, learning_rate)
elif optimizer == "adam":
t = t + 1 # Adam counter
parameters, v, s = update_parameters_with_adam(
parameters, grads, v, s, t, learning_rate, beta1, beta2,
epsilon)
# Print the cost every 1000 epoch
if print_cost and i % 1000 == 0:
print("Cost after epoch %i: %f" % (i, cost))
if print_cost and i % 100 == 0:
costs.append(cost)
# plot the cost
plt.plot(costs)
plt.ylabel('cost')
plt.xlabel('epochs (per 100)')
plt.title("Learning rate = " + str(learning_rate))
plt.show()
return parameters
def model(X,
Y,
layers_dims,
optimizer,
learning_rate=0.0007,
mini_batch_size=64,
beta=0.9,
beta1=0.9,
beta2=0.999,
epsilon=1e-8,
num_epochs=10000,
print_cost=True,
is_plot=True):
"""
可以运行在不同优化器模式下的3层神经网络模型。
:param X:输入数据，维度为（2，输入的数据集里面样本数量）
:param Y:与X对应的标签
:param layers_dims:包含层数和节点数量的列表
:param optimizer:字符串类型的参数，用于选择优化类型，【 "gd" | "momentum" | "adam" 】
:param learning_rate:学习率
mini_batch_size:每个小批量数据集的大小
:param beta:用于动量优化的一个超参数
:param beta1:用于计算平方梯度后的指数衰减的估计的超参数
:param beta2:用于计算梯度后的指数衰减的估计的超参数
:param epsilon:用于在Adam中避免除零操作的超参数，一般不更改
:param num_epochs:整个训练集的遍历次数，（视频2.9学习率衰减，1分55秒处，视频中称作“代”）,相当于之前的num_iteration
:param print_cost:是否打印误差值，每遍历1000次数据集打印一次，但是每100次记录一个误差值，又称每1000代打印一次
:param is_plot:是否绘制出曲线图
:return:
parameters:包含了学习后的参数
"""
L = len(layers_dims)
costs = []
t = 0 # 每学习完一个minibatche就增加1
seed = 10 # 随机种子
parameters = initialize_parameters(layers_dims) # 初始化参数
# 选择优化器
if optimizer == "gd":
pass # 不使用任何优化器，直接使用梯度下降算法
elif optimizer == "momentum":
v = initialize_velocity(parameters) # 使用动量优化
elif optimizer == "adam":
v, s = initialize_adam(parameters) # 使用Adam优化
else:
print("optimizer参数错误")
exit(1)
# 开始学习
for i in range(num_epochs):
# 定义随机minibatches,我们每次遍历数据集之后增加种子以重新排列数据集，是每次数据的顺序不同
seed = seed + 1
minibatches = random_mini_batches(X, Y, mini_batch_size, seed)
for minibatch in minibatches:
# 选择一个minibatch
(minibatch_X, minibatch_Y) = minibatch
# 前向传播
A3, cache = forward_propagation(minibatch_X, parameters)
# 计算误差
cost = compute_cost(A3, minibatch_Y)
# 反向传播
grads = backward_propagation(minibatch_X, minibatch_Y, cache)
# 更新参数
if optimizer == "gd":
parameters = update_parameters_with_gd(parameters, grads,
learning_rate)
elif optimizer == "momentum":
parameters, v = update_parameters_with_momentum(
parameters, grads, v, beta, learning_rate)
elif optimizer == "adam":
t = t + 1 # Adam counter
parameters, v, s = update_parameters_with_adam(
parameters, grads, v, s, t, learning_rate, beta1, beta2,
epsilon)
# 记录误差值
if i % 100 == 0:
costs.append(cost)
# 是否打印误差值
if print_cost and i % 1000 == 0:
print("第" + str(i) + "次遍历整个数据集，当前误差值：" + str(cost))
# 是否绘制曲线图
if is_plot:
plt.plot(costs)
plt.show()
plt.ylabel('cost')
plt.xlabel('epochs (per 100)')
plt.title("Learning rate = " + str(learning_rate))
plt.show()
return parameters
def model(X,
Y,
layers_dims,
optimizer,
learning_rate=0.0007,
mini_batch_size=64,
beta=0.9,
beta1=0.9,
beta2=0.999,
epsilon=1e-8,
num_epochs=10000,
print_cost=True,
is_plot=True):
'''
可以运行在不同优化器模式下的三层神经网络模型.
:param X: 输入数据,维度为(2,输入数据集里面样本数量))
:param Y: 与X对应的标签
:param layers_dims: 包含层数和节点数量的列表
:param optimizer: 字符出类型的参数,用于选择优化类型,['gd'|'momentum'|'adam']
:param learning_rate: 学习率
:param mini_batch_size: 每个小批量数据集的大小
:param beta: 用于动量优化的一个超参数
:param beta1:用于计算梯度后的指数衰减的估计的超参数
:param beta2: 用于计算平方梯度后的指数衰减的估计的超参数
:param epsilon: 用于在Adam中避免除零操作的超参数,一般不更改
:param num_epochs: 整个训练集的遍历次数
:param print_cost: 是否打印误差值,每遍历1000次数据打印一次,但是每100次记录一个误差值,又称每1000代打印一次
:param is_plot: 是否会制出曲线图
:return:
parameters - 包含了学习后的参数
'''
L = len(layers_dims)
costs = []
t = 0 #每学习完一个minibatch就增加1
seed = 10 #随机种子
#初始化参数
parameters = opt_utils.initialize_parameters(layers_dims)
#选择优化器
if optimizer == 'gd':
pass #不使用任何优化器,直接使用梯度下降算法
elif optimizer == 'momentum':
v = initialize_velocity(parameters) #使用动量
elif optimizer == 'adam':
v, s = initialize_adam(parameters) #使用adam优化
else:
print('optimizer参数错误,程序退出')
exit(1)
#开始学习
for i in range(num_epochs):
#定义随机minibatches,我们每次便利数据集之后增加种子以重新排列数据,使每次数据的顺序都不同
seed = seed + 1
minibatches = random_mini_batches(X, Y, mini_batch_size, seed)
for minibatch in minibatches:
#选择一个minibatch
(minibatch_X, minibatch_Y) = minibatch
#前向传播
A3, cache = opt_utils.forward_propagation(minibatch_X, parameters)
#计算误差
cost = opt_utils.compute_cost(A3, minibatch_Y)
#反向传播
grads = opt_utils.backward_propagation(minibatch_X, minibatch_Y,
cache)
#更新参数
if optimizer == 'gd':
parameters = update_parameters_with_gd(parameters, grads,
learning_rate)
elif optimizer == 'momentum':
parameters, v = update_parameters_with_momentun(
parameters, grads, v, beta, learning_rate)
elif optimizer == 'adam':
t = t + 1
parameters, v, s = update_parameters_with_adam(
parameters, grads, v, s, t, learning_rate, beta1, beta2,
epsilon)
#记录误差值
if i % 100 == 0:
costs.append(cost)
#是否打印误差值
if print_cost and i % 1000 == 0:
print('第' + str(i) + '次遍历整个数据集,当前误差值:' + str(cost))
#是否绘制曲线图
if is_plot:
plt.plot(costs)
plt.xlabel('epochs(per 100)')
plt.ylabel('cost')
plt.title('Learning rate = ' + str(learning_rate))
plt.show()
return parameters
def model(X,
Y,
layers_dims,
optimizer,
learning_rate=0.007,
mini_batch_size=64,
beta=0.9,
beta1=0.9,
beta2=0.999,
epsilon=1e-8,
num_epochs=10000,
print_cost=True,
is_plot=True):
L = len(layers_dims)
costs = []
t = 0
seed = 10
parameters = opt_utils.initialize_parameters(layers_dims)
if optimizer == 'gd':
pass
elif optimizer == 'momentum':
v = initialize_velocity(parameters)
elif optimizer == 'adam':
v, s = initialize_adam(parameters)
for i in range(num_epochs):
seed = seed + 1
minibatches = random_mini_batches(X, Y, mini_batch_size, seed)
for minibatch in minibatches:
minibatch_X, minibatch_Y = minibatch
A3, cache = opt_utils.forward_propagation(minibatch_X, parameters)
# 计算误差
cost = opt_utils.compute_cost(A3, minibatch_Y)
# 反向传播
grads = opt_utils.backward_propagation(minibatch_X, minibatch_Y,
cache)
if optimizer == "gd":
parameters = update_parameters_with_gd(parameters, grads,
learning_rate)
elif optimizer == "momentum":
parameters, v = update_parameters_with_momentum(
parameters, grads, v, beta, learning_rate)
elif optimizer == "adam":
t = t + 1
parameters, v, s = update_parameters_with_adam(
parameters, grads, v, s, t, learning_rate, beta1, beta2,
epsilon)
# 记录误差值
if i % 100 == 0:
costs.append(cost)
# 是否打印误差值
if print_cost and i % 1000 == 0:
print("第" + str(i) + "次遍历整个数据集，当前误差值：" + str(cost))
# 是否绘制曲线图
if is_plot:
plt.plot(costs)
plt.ylabel('cost')
plt.xlabel('epochs (per 100)')
plt.title("Learning rate = " + str(learning_rate))
plt.show()
return parameters
L = len(parameters) // 2 # number of layers in the neural networks
# Update rule for each parameter
for l in range(L):
### START CODE HERE ### (approx. 2 lines)
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
# Batch Gradient Descent
X = data_input
Y = labels
parameters = initialize_parameters(layers_dims)
for i in range(0, num_iterations):
# Forward propagation
a, caches = forward_propagation(X, parameters)
# Compute cost.
cost = compute_cost(a, Y)
# Backward propagation.
grads = backward_propagation(a, caches, parameters)
# Update parameters.
parameters = update_parameters(parameters, grads)
# Stochastic Gradient Descent
X = data_input
Y = labels
parameters = initialize_parameters(layers_dims)
for i in range(0, num_iterations):
def model(X, Y, learning_rate = 0.3, num_iterations = 30000, print_cost = True, lambd = 0, keep_prob = 1):
"""
Implements a three-layer neural network: LINEAR->RELU->LINEAR->RELU->LINEAR->SIGMOID.
Arguments:
X -- input data, of shape (input size, number of examples)
Y -- true "label" vector (1 for blue dot / 0 for red dot), of shape (output size, number of examples)
learning_rate -- learning rate of the optimization
num_iterations -- number of iterations of the optimization loop
print_cost -- If True, print the cost every 10000 iterations
lambd -- regularization hyperparameter, scalar
keep_prob - probability of keeping a neuron active during drop-out, scalar.
Returns:
parameters -- parameters learned by the model. They can then be used to predict.
"""
grads = {}
costs = [] # to keep track of the cost
m = X.shape[1] # number of examples
layers_dims = [X.shape[0], 20, 3, 1]
# Initialize parameters dictionary.
parameters = initialize_parameters(layers_dims)
# Loop (gradient descent)
for i in range(0, num_iterations):
# Forward propagation: LINEAR -> RELU -> LINEAR -> RELU -> LINEAR -> SIGMOID.
if keep_prob == 1:
a3, cache = forward_propagation(X, parameters)
elif keep_prob < 1:
a3, cache = forward_propagation_with_dropout(X, parameters, keep_prob)
# Cost function
if lambd == 0:
cost = compute_cost(a3, Y)
else:
cost = compute_cost_with_regularization(a3, Y, parameters, lambd)
# Backward propagation.
assert(lambd==0 or keep_prob==1) # it is possible to use both L2 regularization and dropout,
# but this assignment will only explore one at a time
if lambd == 0 and keep_prob == 1:
grads = backward_propagation(X, Y, cache)
elif lambd != 0:
grads = backward_propagation_with_regularization(X, Y, cache, lambd)
elif keep_prob < 1:
grads = backward_propagation_with_dropout(X, Y, cache, keep_prob)
# Update parameters.
parameters = update_parameters(parameters, grads, learning_rate)
# Print the loss every 10000 iterations
if print_cost and i % 10000 == 0:
print("Cost after iteration {}: {}".format(i, cost))
if print_cost and i % 1000 == 0:
costs.append(cost)
# plot the cost
plt.plot(costs)
plt.ylabel('cost')
plt.xlabel('iterations (x1,000)')
plt.title("Learning rate =" + str(learning_rate))
plt.show()
return parameters
def model(X, Y, layers_dims, optimizer, learning_rate=0.0007,
mini_batch_size=64, beta=0.9, beta1=0.9, beta2=0.999,
epsilon=1e-8, num_epochs=10000, print_cost=True, is_plot=True):
L = len(layers_dims)
costs = []
t = 0 # 每学习完一个minibatch就增加1
seed = 10 # 随机种子
# 初始化参数
parameters = opt_utils.initialize_parameters(layers_dims)
# 选择优化器
if optimizer == "gd":
pass # 不使用任何优化器，直接使用梯度下降法
elif optimizer == "momentum":
v = initialize_velocity(parameters) # 使用动量
elif optimizer == "adam":
v, s = initialize_adam(parameters) # 使用Adam优化
else:
print("optimizer参数错误，程序退出。")
exit(1)
# 开始学习
for i in range(num_epochs):
# 定义随机 minibatches,我们在每次遍历数据集之后增加种子以重新排列数据集，使每次数据的顺序都不同
seed = seed + 1
minibatches = random_mini_batches(X, Y, mini_batch_size, seed)
for minibatch in minibatches:
# 选择一个minibatch
(minibatch_X, minibatch_Y) = minibatch
# 前向传播
A3, cache = opt_utils.forward_propagation(minibatch_X, parameters)
# 计算误差
cost = opt_utils.compute_cost(A3, minibatch_Y)
# 反向传播
grads = opt_utils.backward_propagation(minibatch_X, minibatch_Y, cache)
# 更新参数
if optimizer == "gd":
parameters = update_parameters_with_gd(parameters, grads, learning_rate)
elif optimizer == "momentum":
parameters, v = update_parameters_with_momentun(parameters, grads, v, beta, learning_rate)
elif optimizer == "adam":
t = t + 1
parameters, v, s = update_parameters_with_adam(parameters, grads, v, s, t, learning_rate, beta1, beta2,
epsilon)
# 记录误差值
if i % 100 == 0:
costs.append(cost)
# 是否打印误差值
if print_cost and i % 1000 == 0:
print("第" + str(i) + "次遍历整个数据集，当前误差值：" + str(cost))
# 是否绘制曲线图
if is_plot:
plt.plot(costs)
plt.ylabel('cost')
plt.xlabel('epochs (per 100)')
plt.title("Learning rate = " + str(learning_rate))
plt.show()
return parameters
return parameters
parameters, grads, learning_rate = update_parameters_with_gd_test_case()
parameters = update_parameters_with_gd(parameters, grads, learning_rate)
print("W1 = " + str(parameters["W1"]))
print("b1 = " + str(parameters["b1"]))
print("W2 = " + str(parameters["W2"]))
print("b2 = " + str(parameters["b2"]))
# Batch vs Stochastic
X = data_input
Y = labels
parameters = initialize_parameters(layers_dims)
# -- (Batch)
for i in range(0, num_iterations):
# Forward propagation
a, caches = forward_propagation(X, parameters)
# Compute cost.
cost = compute_cost(a, Y)
# Backward propagation.
grads = backward_propagation(a, caches, parameters)
# Update parameters.
parameters = update_parameters(parameters, grads)
# -- (Stochastic)
for i in range(0, num_iterations):
for j in range(0, m):
# Forward propagation
a, caches = forward_propagation(X[:,j], parameters)
def model(X,
Y,
layers_dims,
optimizer,
learning_rate=0.0007,
mini_batch_size=64,
beta=0.9,
beta1=0.9,
beta2=0.999,
epsilon=1e-8,
num_epochs=20000,
print_cost=True,
is_plot=True):
# 那就来看看哪个梯度下降算法号
L = len(layers_dims)
costs = []
t = 0 # 每学完一个就增加1
seed = 10
# 初始化参数
parameters = opt_utils.initialize_parameters(layers_dims)
# print(str(type(parameters)), "1")
# 选择优化器
if optimizer == "gd":
pass # 不用任何优化器，批量梯度下降算法
elif optimizer == "momentum":
v = initialize_velocity(parameters) # 使用动量优化算法
elif optimizer == "adam":
v, s = initialize_adam(parameters) # 使用adam优化算法
else:
print("optimizer参数错误，程序退出")
exit(1)
# 开始学习
for i in range(num_epochs):
seed = seed + 1
minibatches = random_mini_batches(X, Y, mini_batch_size, seed)
for minibatch in minibatches:
# print(len(minibatches))
# 选择一个minibatch
# (minibatch_X, minibatch_Y) = minibatch
(minibatch_X, minibatch_Y) = minibatch
# 前向传播
A3, cache = opt_utils.forward_propagation(minibatch_X, parameters)
# 计算误差
cost = opt_utils.compute_cost(A3, minibatch_Y)
# 反向传播
grads = opt_utils.backward_propagation(minibatch_X, minibatch_Y,
cache)
# 更新参数
if optimizer == "gd":
parameters = update_parameters_with_gd(parameters, grads,
learning_rate)
elif optimizer == "momentum":
# 这里少了一个数，导致parameters格式输出错误。。，变成元组了
parameters, v = update_parameters_with_momentun(
parameters, grads, v, beta, learning_rate)
elif optimizer == "adam":
t = t + 1
parameters, v, s = update_parameters_with_adam(
parameters, grads, v, s, t, learning_rate, beta1, beta2,
epsilon)
if i % 100 == 0:
costs.append(cost)
if print_cost and i % 1000 == 0:
print("第" + str(i) + "次遍历整个数据集，误差值为：" + str(cost))
if is_plot:
plt.plot(costs)
plt.ylabel('cost')
plt.xlabel('dai_shu(100)')
plt.title("learning_rate = " + str(learning_rate))
plt.show()
return parameters
def model(X,
Y,
layers_dims,
optimizer,
learning_rate=0.0007,
mini_batch_size=64,
beta=0.9,
beta1=0.9,
beta2=0.999,
epsilon=1e-8,
num_epochs=10000,
print_cost=True,
is_plot=True):
"""
可以运行在不同优化器模式下的3层神经网络模型。
参数：
X - 输入数据，维度为（2，输入的数据集里面样本数量）
Y - 与X对应的标签
layers_dims - 包含层数和节点数量的列表
optimizer - 字符串类型的参数，用于选择优化类型，【 "gd" | "momentum" | "adam" 】
learning_rate - 学习率
mini_batch_size - 每个小批量数据集的大小
beta - 用于动量优化的一个超参数
beta1 - 用于计算梯度后的指数衰减的估计的超参数
beta1 - 用于计算平方梯度后的指数衰减的估计的超参数
epsilon - 用于在Adam中避免除零操作的超参数，一般不更改
num_epochs - 整个训练集的遍历次数，（视频2.9学习率衰减，1分55秒处，视频中称作“代”）,相当于之前的num_iteration
print_cost - 是否打印误差值，每遍历1000次数据集打印一次，但是每100次记录一个误差值，又称每1000代打印一次
is_plot - 是否绘制出曲线图
返回：
parameters - 包含了学习后的参数
"""
L = len(layers_dims)
costs = []
t = 0 # 每学习完一个minibatch就增加1
seed = 10
# 初始化参数
parameters = opt_utils.initialize_parameters(layers_dims)
if optimizer == "gd":
pass
elif optimizer == "momentum":
v = initialize_velocity(parameters)
elif optimizer == "adam":
v, s = initialize_adam(parameters)
else:
print("optimizer 参数错误， 程序退出。")
exit(1)
# 开始学习
for i in range(num_epochs):
#定义随机 minibatches,我们在每次遍历数据集之后增加种子以重新排列数据集，使每次数据的顺序都不同
seed = seed + 1
minibatches = random_mini_batches(X, Y, mini_batch_size, seed)
for minibatch in minibatches:
# 选择一个minibatch
(minibatch_X, minibatch_Y) = minibatch
# 前向传播
A3, cache = opt_utils.forward_propagation(minibatch_X, parameters)
# 计算误差
cost = opt_utils.compute_cost(A3, minibatch_Y)
# 反向传播
grads = opt_utils.backward_propagation(minibatch_X, minibatch_Y,
cache)
# 更新参数
if optimizer == "gd":
parameters = update_parameters_with_gd(parameters, grads,
learning_rate)
elif optimizer == "momentum":
parameters, v = update_parameters_with_momentun(
parameters, grads, v, beta, learning_rate)
elif optimizer == "adam":
t = t + 1
parameters, v, s = update_parameters_with_adam(
parameters, grads, v, s, t, learning_rate, beta1, beta2,
epsilon)
if i % 100 == 0:
costs.append(cost)
if print_cost and i % 1000 == 0:
print("第" + str(i) + "次遍历整个数据集，当前误差值: " + str(cost))
if is_plot:
plt.plot(costs)
plt.ylabel("cost")
plt.xlabel("epochs (per 100)")
plt.title("Learning rate = " + str(learning_rate))
plt.show()
return parameters
def model(X_train, Y_train, X_test, Y_test, learning_rate = 0.009,
num_epochs = 100, minibatch_size = 64, print_cost = True):
"""
Implements a three-layer ConvNet in Tensorflow:
CONV2D -> RELU -> MAXPOOL -> CONV2D -> RELU -> MAXPOOL -> FLATTEN -> FULLYCONNECTED
Arguments:
X_train -- training set, of shape (None, 64, 64, 3)
Y_train -- test set, of shape (None, n_y = 6)
X_test -- training set, of shape (None, 64, 64, 3)
Y_test -- test set, of shape (None, n_y = 6)
learning_rate -- learning rate of the optimization
num_epochs -- number of epochs of the optimization loop
minibatch_size -- size of a minibatch
print_cost -- True to print the cost every 100 epochs
Returns:
train_accuracy -- real number, accuracy on the train set (X_train)
test_accuracy -- real number, testing accuracy on the test set (X_test)
parameters -- parameters learnt by the model. They can then be used to predict.
"""
ops.reset_default_graph() # to be able to rerun the model without overwriting tf variables
tf.set_random_seed(1) # to keep results consistent (tensorflow seed)
seed = 3 # to keep results consistent (numpy seed)
(m, n_H0, n_W0, n_C0) = X_train.shape
n_y = Y_train.shape[1]
costs = [] # To keep track of the cost
# Create Placeholders of the correct shape
### START CODE HERE ### (1 line)
X, Y = create_placeholders(n_H0, n_W0, n_C0, n_y)
### END CODE HERE ###
# Initialize parameters
### START CODE HERE ### (1 line)
parameters = initialize_parameters()
### END CODE HERE ###
# Forward propagation: Build the forward propagation in the tensorflow graph
### START CODE HERE ### (1 line)
Z3 = forward_propagation(X, parameters)
### END CODE HERE ###
# Cost function: Add cost function to tensorflow graph
### START CODE HERE ### (1 line)
cost = compute_cost(Z3, Y)
### END CODE HERE ###
# Backpropagation: Define the tensorflow optimizer. Use an AdamOptimizer that minimizes the cost.
### START CODE HERE ### (1 line)
optimizer = tf.train.AdamOptimizer(learning_rate = learning_rate).minimize(cost)
### END CODE HERE ###
# Initialize all the variables globally
init = tf.global_variables_initializer()
# Start the session to compute the tensorflow graph
with tf.Session() as sess:
# Run the initialization
sess.run(init)
# Do the training loop
for epoch in range(num_epochs):
minibatch_cost = 0.
num_minibatches = int(m / minibatch_size) # number of minibatches of size minibatch_size in the train set
seed = seed + 1
minibatches = random_mini_batches(X_train, Y_train, minibatch_size, seed)
for minibatch in minibatches:
# Select a minibatch
(minibatch_X, minibatch_Y) = minibatch
# IMPORTANT: The line that runs the graph on a minibatch.
# Run the session to execute the optimizer and the cost, the feedict should contain a minibatch for (X,Y).
### START CODE HERE ### (1 line)
_ , temp_cost = sess.run([optimizer, cost], feed_dict={X: minibatch_X, Y: minibatch_Y})
### END CODE HERE ###
minibatch_cost += temp_cost / num_minibatches
# Print the cost every epoch
if print_cost == True and epoch % 5 == 0:
print ("Cost after epoch %i: %f" % (epoch, minibatch_cost))
if print_cost == True and epoch % 1 == 0:
costs.append(minibatch_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()
# Calculate the correct predictions
predict_op = tf.argmax(Z3, 1)
correct_prediction = tf.equal(predict_op, tf.argmax(Y, 1))
# Calculate accuracy on the test set
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print(accuracy)
train_accuracy = accuracy.eval({X: X_train, Y: Y_train})
test_accuracy = accuracy.eval({X: X_test, Y: Y_test})
print("Train Accuracy:", train_accuracy)
print("Test Accuracy:", test_accuracy)
return train_accuracy, test_accuracy, parameters
def model(X,Y,layers_dims,optimizer,learning_rate = 0.0007,
mini_batch_size = 64,beta = 0.9,beta1 = 0.9,beta2 = 0.999,
epsilon = 1e-8,num_epochs = 10000,print_cost = True,is_plot = True ):
'''
可以运行在不同优化器模式下的三层神经网络模型.
:param X: 输入数据,维度为(2,输入数据集里面样本数量))
:param Y: 与X对应的标签
:param layers_dims: 包含层数和节点数量的列表
:param optimizer: 字符出类型的参数,用于选择优化类型,['gd'|'momentum'|'adam']
:param learning_rate: 学习率
:param mini_batch_size: 每个小批量数据集的大小
:param beta: 用于动量优化的一个超参数
:param beta1:用于计算梯度后的指数衰减的估计的超参数
:param beta2: 用于计算平方梯度后的指数衰减的估计的超参数
:param epsilon: 用于在Adam中避免除零操作的超参数,一般不更改
:param num_epochs: 整个训练集的遍历次数
:param print_cost: 是否打印误差值,每遍历1000次数据打印一次,但是每100次记录一个误差值,又称每1000代打印一次
:param is_plot: 是否会制出曲线图
:return:
parameters - 包含了学习后的参数
'''
L = len(layers_dims)
costs = []
t = 0#每学习完一个minibatch就增加1
seed = 10#随机种子
#初始化参数
parameters = opt_utils.initialize_parameters(layers_dims)
#选择优化器
if optimizer == 'gd':
pass #不使用任何优化器,直接使用梯度下降算法
elif optimizer == 'momentum':
v = initialize_velocity(parameters)#使用动量
elif optimizer == 'adam':
v,s = initialize_adam(parameters)#使用adam优化
else:
print('optimizer参数错误,程序退出')
exit(1)
#开始学习
for i in range(num_epochs):
#定义随机minibatches,我们每次便利数据集之后增加种子以重新排列数据,使每次数据的顺序都不同
seed = seed+1
minibatches = random_mini_batches(X,Y,mini_batch_size,seed)
for minibatch in minibatches:
#选择一个minibatch
(minibatch_X,minibatch_Y) = minibatch
#前向传播
A3,cache = opt_utils.forward_propagation(minibatch_X,parameters)
#计算误差
cost = opt_utils.compute_cost(A3,minibatch_Y)
#反向传播
grads = opt_utils.backward_propagation(minibatch_X,minibatch_Y,cache)
#更新参数
if optimizer == 'gd':
parameters = update_parameters_with_gd(parameters,grads,learning_rate)
elif optimizer=='momentum':
parameters,v = update_parameters_with_momentun(parameters,grads,v,beta,learning_rate)
elif optimizer == 'adam':
t = t+1
parameters,v,s = update_parameters_with_adam(parameters,grads,v,s,t,learning_rate,beta1,beta2,epsilon)
#记录误差值
if i%100 == 0:
costs.append(cost)
#是否打印误差值
if print_cost and i%1000 == 0:
print('第'+str(i)+'次遍历整个数据集,当前误差值:'+str(cost))
#是否绘制曲线图
if is_plot:
plt.plot(costs)
plt.xlabel('epochs(per 100)')
plt.ylabel('cost')
plt.title('Learning rate = '+str(learning_rate))
plt.show()
return parameters
def model(X, Y, layers_dims, optimizer, learning_rate = 0.0007, mini_batch_size = 64, beta = 0.9,
beta1 = 0.9, beta2 = 0.999, epsilon = 1e-8, num_epochs = 10000, print_cost = True):
"""
3-layer neural network model which can be run in different optimizer modes.
Arguments:
X -- input data, of shape (2, number of examples)
Y -- true "label" vector (1 for blue dot / 0 for red dot), of shape (1, number of examples)
layers_dims -- python list, containing the size of each layer
learning_rate -- the learning rate, scalar.
mini_batch_size -- the size of a mini batch
beta -- Momentum hyperparameter
beta1 -- Exponential decay hyperparameter for the past gradients estimates
beta2 -- Exponential decay hyperparameter for the past squared gradients estimates
epsilon -- hyperparameter preventing division by zero in Adam updates
num_epochs -- number of epochs
print_cost -- True to print the cost every 1000 epochs
Returns:
parameters -- python dictionary containing your updated parameters
"""
L = len(layers_dims) # number of layers in the neural networks
costs = [] # to keep track of the cost
t = 0 # initializing the counter required for Adam update
seed = 10 # For grading purposes, so that your "random" minibatches are the same as ours
# Initialize parameters
parameters = initialize_parameters(layers_dims)
# Initialize the optimizer
if optimizer == "gd":
pass # no initialization required for gradient descent
elif optimizer == "momentum":
v = initialize_velocity(parameters)
elif optimizer == "adam":
v, s = initialize_adam(parameters)
# Optimization loop
for i in range(num_epochs):
# Define the random minibatches. We increment the seed to reshuffle differently the dataset after each epoch
seed = seed + 1
minibatches = random_mini_batches(X, Y, mini_batch_size, seed)
for minibatch in minibatches:
# Select a minibatch
(minibatch_X, minibatch_Y) = minibatch
# Forward propagation
a3, caches = forward_propagation(minibatch_X, parameters)
# Compute cost
cost = compute_cost(a3, minibatch_Y)
# Backward propagation
grads = backward_propagation(minibatch_X, minibatch_Y, caches)
# Update parameters
if optimizer == "gd":
parameters = update_parameters_with_gd(parameters, grads, learning_rate)
elif optimizer == "momentum":
parameters, v = update_parameters_with_momentum(parameters, grads, v, beta, learning_rate)
elif optimizer == "adam":
t = t + 1 # Adam counter
parameters, v, s = update_parameters_with_adam(parameters, grads, v, s,
t, learning_rate, beta1, beta2, epsilon)
# Print the cost every 1000 epoch
if print_cost and i % 1000 == 0:
print ("Cost after epoch %i: %f" %(i, cost))
if print_cost and i % 100 == 0:
costs.append(cost)
# plot the cost
plt.plot(costs)
plt.ylabel('cost')
plt.xlabel('epochs (per 100)')
plt.title("Learning rate = " + str(learning_rate))
plt.show()
return parameters
def model(X,
Y,
layer_dims,
optimizer='adam',
learning_rate=0.0007,
beta1=0.9,
beta2=0.999,
epsilon=1e-8,
minibatch_size=64,
epochs=10000,
print_cost=True,
is_plot=True):
'''
:param X:输入图像
:param Y:输入标签
:param layer_dims:输入网络每层神经元的个数
:param optimizer:选择优化器 包括'adam','gd','momentum'
:param learning_rate:学习率
:param beta1:momentum超参数动量
:param beta2:RMSProp超参数动量
:param epsilon:平滑
:param minibatch_size:minibatch的大小
:param epochs:循环多少次
:param print_cost:是否输出Cost
:param is_plot:是否显示可视化结果
:return:参数
'''
costs = []
t = 0
seed = 10
#初始化网络权重
pass
parameters = opt_utils.initialize_parameters(layer_dims)
if optimizer == 'adam':
v, s = initialize_adam(parameters)
elif optimizer == 'momentum':
v = initialize_velocity(parameters)
elif optimizer == 'gd':
pass
else:
print('输入参数出错，程序退出。')
exit(1)
for i in range(epochs):
seed += 1
mini_batches = random_mini_batches(X, Y, minibatch_size, seed)
for j in mini_batches:
(minibatch_X, minibatch_Y) = j
#前向传播
a3, cache = opt_utils.forward_propagation(minibatch_X, parameters)
#计算Cost
Loss = opt_utils.compute_cost(a3, minibatch_Y)
#反向传播
grads = opt_utils.backward_propagation(minibatch_X, minibatch_Y,
cache)
#更新参数
if optimizer == 'adam':
t += 1
parameters, v, s = update_parameters_with_adam(
parameters, grads, v, s, t, learning_rate, beta1, beta2,
epsilon)
elif optimizer == 'momentum':
parameters, v = update_parameters_with_momentum(
parameters, grads, v, beta1, learning_rate)
else:
parameters = update_parameters_with_gd(parameters, grads,
learning_rate)
if i % 100 == 0:
costs.append(Loss)
if print_cost and i % 1000 == 0:
print("第" + str(i) + "次遍历整个数据集，当前误差值：" + str(Loss))
if is_plot:
plt.plot(costs)
plt.ylabel('cost')
plt.xlabel('epochs (per 100)')
plt.title("Learning rate = " + str(learning_rate))
plt.show()
return parameters
def model(X,
Y,
layers_dims,
optimizer,
learning_rate=0.0007,
mini_batch_size=64,
beta=0.9,
beta1=0.9,
beta2=0.999,
epsilon=1e-8,
num_epochs=10000,
print_cost=True):
"""
3-layer neural network model which can be run in different optimizer modes.
Arguments:
X -- input data, of shape (2, number of examples)
Y -- true "label" vector (1 for blue dot / 0 for red dot), of shape (1, number of examples)
layers_dims -- python list, containing the size of each layer
learning_rate -- the learning rate, scalar.
mini_batch_size -- the size of a mini batch
beta -- Momentum hyperparameter
beta1 -- Exponential decay hyperparameter for the past gradients estimates
beta2 -- Exponential decay hyperparameter for the past squared gradients estimates
epsilon -- hyperparameter preventing division by zero in Adam updates
num_epochs -- number of epochs
print_cost -- True to print the cost every 1000 epochs
Returns:
parameters -- python dictionary containing your updated parameters
"""
L = len(layers_dims) # number of layers in the neural networks
costs = [] # to keep track of the cost
t = 0 # initializing the counter required for Adam update
seed = 10 # For grading purposes, so that your "random" minibatches are the same as ours
# Initialize parameters
parameters = initialize_parameters(layers_dims)
# Initialize the optimizer
if optimizer == "gd":
pass # no initialization required for gradient descent
elif optimizer == "momentum":
v = initialize_velocity(parameters)
elif optimizer == "adam":
v, s = initialize_adam(parameters)
# Optimization loop
for i in range(num_epochs):
# Define the random minibatches. We increment the seed to reshuffle differently the dataset after each epoch
seed = seed + 1
minibatches = random_mini_batches(X, Y, mini_batch_size, seed)
for minibatch in minibatches:
# Select a minibatch
(minibatch_X, minibatch_Y) = minibatch
# Forward propagation
a3, caches = forward_propagation(minibatch_X, parameters)
# Compute cost
cost = compute_cost(a3, minibatch_Y)
# Backward propagation
grads = backward_propagation(minibatch_X, minibatch_Y, caches)
# Update parameters
if optimizer == "gd":
parameters = update_parameters_with_gd(parameters, grads,
learning_rate)
elif optimizer == "momentum":
parameters, v = update_parameters_with_momentum(
parameters, grads, v, beta, learning_rate)
elif optimizer == "adam":
t = t + 1 # Adam counter
parameters, v, s = update_parameters_with_adam(
parameters, grads, v, s, t, learning_rate, beta1, beta2,
epsilon)
# Print the cost every 1000 epoch
if print_cost and i % 1000 == 0:
print("Cost after epoch %i: %f" % (i, cost))
if print_cost and i % 100 == 0:
costs.append(cost)
# plot the cost
plt.plot(costs)
plt.ylabel('cost')
plt.xlabel('epochs (per 100)')
plt.title("Learning rate = " + str(learning_rate))
plt.show()
return parameters
def model(X,
Y,
layer_dims,
optimizer,
learning_rate=0.0007,
mini_batch_size=64,
beta=0.9,
beta1=0.9,
beta2=0.999,
epsilon=1e-8,
num_epochs=10000,
print_cost=True,
is_plot=True):
L = len(layer_dims)
costs = []
t = 0
seed = 10
params = opt_utils.initialize_parameters(layer_dims)
# choose optimization method
if optimizer == "gd":
pass
elif optimizer == "momentum":
v = init_velocity(params)
elif optimizer == "adam":
v, s = init_adam(params)
else:
print("Wrong optimizer parameter")
exit(1)
# Learning
for i in range(num_epochs):
seed = seed + 1
mini_batches = random_mini_batches(X, Y, mini_batch_size, seed)
for mini_batch in mini_batches:
(mini_batch_X, mini_batch_Y) = mini_batch
# fp
A3, cache = opt_utils.forward_propagation(mini_batch_X, params)
# compute cost
cost = opt_utils.compute_cost(A3, mini_batch_Y)
# bp
grads = opt_utils.backward_propagation(mini_batch_X, mini_batch_Y,
cache)
# upgrade params
if optimizer == "gd":
params = update_params_with_gd(params, grads, learning_rate)
elif optimizer == "momentum":
params, v = update_params_with_momentum(
params, grads, v, beta, learning_rate)
elif optimizer == "adam":
t = t + 1
params, v, s = update_params_with_adam(params, grads, v, s, t,
learning_rate, beta1,
beta2, epsilon)
if i % 100 == 0:
costs.append(cost)
if print_cost and i % 1000 == 0:
print("Epoch " + str(i) + " Cost:" + str(cost))
if is_plot:
plt.plot(costs)
plt.ylabel("cost")
plt.xlabel("#epochs")
plt.title("Learning rate = " + str(learning_rate))
plt.show()
return params