TensorFlow 各优化器在鸢尾花分类任务中的应用
目录
1.SGD
2.SGDM
3.Adagrad
4.RMSProp
5.Adam
优化器是引导神经网络更新参数的工具
：待优化参数
：损失函数
：学习率
更新参数的步骤：
1.计算t时刻损失函数关于当前参数的梯度
2.计算t时刻一阶动量和二阶动量
3.计算t时刻下降梯度
4.计算t+1时刻参数
一阶动量：与梯度相关的参数
二阶动量：与梯度平方相关的参数
1.SGD常用的梯度下降法
import tensorflow as tf
from sklearn import datasets
from matplotlib import pyplot as plt
import numpy as np
import time
x_data = datasets.load_iris().data
y_data = datasets.load_iris().target
np.random.seed(116)
np.random.shuffle(x_data)
np.random.seed(116)
np.random.shuffle(y_data)
tf.random.set_seed(116)
x_train = x_data[:-30]
y_train = y_data[:-30]
x_test = x_data[-30:]
y_test = y_data[-30:]
x_train = tf.cast(x_train, tf.float32)
x_test = tf.cast(x_test, tf.float32)
train_db = tf.data.Dataset.from_tensor_slices((x_train, y_train)).batch(32)
test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)
w1 = tf.Variable(tf.random.truncated_normal([4, 3], stddev=0.1, seed=1))
b1 = tf.Variable(tf.random.truncated_normal([3], stddev=0.1, seed=1))
lr = 0.1
train_loss_results = []
test_acc = []
epoch = 500
loss_all = 0
now_time = time.time()
for epoch in range(epoch):
for step, (x_train, y_train) in enumerate(train_db):
with tf.GradientTape() as tape:
y = tf.matmul(x_train, w1) + b1
y = tf.nn.softmax(y)
y_ = tf.one_hot(y_train, depth=3)
loss = tf.reduce_mean(tf.square(y_ - y))
loss_all += loss.numpy()
grads = tape.gradient(loss, [w1, b1])
w1.assign_sub(lr * grads[0])
b1.assign_sub(lr * grads[1])
print("Epoch {}, loss: {}".format(epoch, loss_all / 4))
train_loss_results.append(loss_all / 4)
loss_all = 0
total_correct, total_number = 0, 0
for x_test, y_test in test_db:
y = tf.matmul(x_test, w1) + b1
y = tf.nn.softmax(y)
pred = tf.argmax(y, axis=1)
pred = tf.cast(pred, dtype=y_test.dtype)
correct = tf.cast(tf.equal(pred, y_test), dtype=tf.int32)
correct = tf.reduce_sum(correct)
total_correct += int(correct)
total_number += x_test.shape[0]
acc = total_correct / total_number
test_acc.append(acc)
print("Test_acc:", acc)
print("--------------------------")
total_time = time.time() - now_time
print("total_time", total_time)
plt.title('Loss Function Curve')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.plot(train_loss_results, label="$Loss$")
plt.legend()
plt.show()
plt.title('Acc Curve')
plt.xlabel('Epoch')
plt.ylabel('Acc')
plt.plot(test_acc, label="$Accuracy$")
plt.legend()
plt.show()
2.SGDM在SGD基础上增加一阶动量
import tensorflow as tf
from sklearn import datasets
from matplotlib import pyplot as plt
import numpy as np
import time
x_data = datasets.load_iris().data
y_data = datasets.load_iris().target
np.random.seed(116)
np.random.shuffle(x_data)
np.random.seed(116)
np.random.shuffle(y_data)
tf.random.set_seed(116)
x_train = x_data[:-30]
y_train = y_data[:-30]
x_test = x_data[-30:]
y_test = y_data[-30:]
x_train = tf.cast(x_train, tf.float32)
x_test = tf.cast(x_test, tf.float32)
train_db = tf.data.Dataset.from_tensor_slices((x_train, y_train)).batch(32)
test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)
w1 = tf.Variable(tf.random.truncated_normal([4, 3], stddev=0.1, seed=1))
b1 = tf.Variable(tf.random.truncated_normal([3], stddev=0.1, seed=1))
lr = 0.1
train_loss_results = []
test_acc = []
epoch = 500
loss_all = 0
m_w, m_b = 0, 0
beta = 0.9
now_time = time.time()
for epoch in range(epoch):
for step, (x_train, y_train) in enumerate(train_db):
with tf.GradientTape() as tape:
y = tf.matmul(x_train, w1) + b1
y = tf.nn.softmax(y)
y_ = tf.one_hot(y_train, depth=3)
loss = tf.reduce_mean(tf.square(y_ - y))
loss_all += loss.numpy()
grads = tape.gradient(loss, [w1, b1])
m_w = beta * m_w + (1 - beta) * grads[0]
m_b = beta * m_b + (1 - beta) * grads[1]
w1.assign_sub(lr * m_w)
b1.assign_sub(lr * m_b)
print("Epoch {}, loss: {}".format(epoch, loss_all / 4))
train_loss_results.append(loss_all / 4)
loss_all = 0
total_correct, total_number = 0, 0
for x_test, y_test in test_db:
y = tf.matmul(x_test, w1) + b1
y = tf.nn.softmax(y)
pred = tf.argmax(y, axis=1)
pred = tf.cast(pred, dtype=y_test.dtype)
correct = tf.cast(tf.equal(pred, y_test), dtype=tf.int32)
correct = tf.reduce_sum(correct)
total_correct += int(correct)
total_number += x_test.shape[0]
acc = total_correct / total_number
test_acc.append(acc)
print("Test_acc:", acc)
print("--------------------------")
total_time = time.time() - now_time
print("total_time", total_time)
plt.title('Loss Function Curve')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.plot(train_loss_results, label="$Loss$")
plt.legend()
plt.show()
plt.title('Acc Curve')
plt.xlabel('Epoch')
plt.ylabel('Acc')
plt.plot(test_acc, label="$Accuracy$")
plt.legend()
plt.show()
3.Adagrad在SGD基础上增加二阶动量
import tensorflow as tf
from sklearn import datasets
from matplotlib import pyplot as plt
import numpy as np
import time
x_data = datasets.load_iris().data
y_data = datasets.load_iris().target
np.random.seed(116)
np.random.shuffle(x_data)
np.random.seed(116)
np.random.shuffle(y_data)
tf.random.set_seed(116)
x_train = x_data[:-30]
y_train = y_data[:-30]
x_test = x_data[-30:]
y_test = y_data[-30:]
x_train = tf.cast(x_train, tf.float32)
x_test = tf.cast(x_test, tf.float32)
train_db = tf.data.Dataset.from_tensor_slices((x_train, y_train)).batch(32)
test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)
w1 = tf.Variable(tf.random.truncated_normal([4, 3], stddev=0.1, seed=1))
b1 = tf.Variable(tf.random.truncated_normal([3], stddev=0.1, seed=1))
lr = 0.1
train_loss_results = []
test_acc = []
epoch = 500
loss_all = 0
v_w, v_b = 0, 0
now_time = time.time()
for epoch in range(epoch):
for step, (x_train, y_train) in enumerate(train_db):
with tf.GradientTape() as tape:
y = tf.matmul(x_train, w1) + b1
y = tf.nn.softmax(y)
y_ = tf.one_hot(y_train, depth=3)
loss = tf.reduce_mean(tf.square(y_ - y))
loss_all += loss.numpy()
grads = tape.gradient(loss, [w1, b1])
v_w += tf.square(grads[0])
v_b += tf.square(grads[1])
w1.assign_sub(lr * grads[0] / tf.sqrt(v_w))
b1.assign_sub(lr * grads[1] / tf.sqrt(v_b))
print("Epoch {}, loss: {}".format(epoch, loss_all / 4))
train_loss_results.append(loss_all / 4)
loss_all = 0
total_correct, total_number = 0, 0
for x_test, y_test in test_db:
y = tf.matmul(x_test, w1) + b1
y = tf.nn.softmax(y)
pred = tf.argmax(y, axis=1)
pred = tf.cast(pred, dtype=y_test.dtype)
correct = tf.cast(tf.equal(pred, y_test), dtype=tf.int32)
correct = tf.reduce_sum(correct)
total_correct += int(correct)
total_number += x_test.shape[0]
acc = total_correct / total_number
test_acc.append(acc)
print("Test_acc:", acc)
print("--------------------------")
total_time = time.time() - now_time
print("total_time", total_time)
plt.title('Loss Function Curve')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.plot(train_loss_results, label="$Loss$")
plt.legend()
plt.show()
plt.title('Acc Curve')
plt.xlabel('Epoch')
plt.ylabel('Acc')
plt.plot(test_acc, label="$Accuracy$")
plt.legend()
plt.show()
4.RMSProp在SGD基础上增加二阶动量
import tensorflow as tf
from sklearn import datasets
from matplotlib import pyplot as plt
import numpy as np
import time
x_data = datasets.load_iris().data
y_data = datasets.load_iris().target
np.random.seed(116)
np.random.shuffle(x_data)
np.random.seed(116)
np.random.shuffle(y_data)
tf.random.set_seed(116)
x_train = x_data[:-30]
y_train = y_data[:-30]
x_test = x_data[-30:]
y_test = y_data[-30:]
x_train = tf.cast(x_train, tf.float32)
x_test = tf.cast(x_test, tf.float32)
train_db = tf.data.Dataset.from_tensor_slices((x_train, y_train)).batch(32)
test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)
w1 = tf.Variable(tf.random.truncated_normal([4, 3], stddev=0.1, seed=1))
b1 = tf.Variable(tf.random.truncated_normal([3], stddev=0.1, seed=1))
lr = 0.1
train_loss_results = []
test_acc = []
epoch = 500
loss_all = 0
v_w, v_b = 0, 0
beta = 0.9
now_time = time.time()
for epoch in range(epoch):
for step, (x_train, y_train) in enumerate(train_db):
with tf.GradientTape() as tape:
y = tf.matmul(x_train, w1) + b1
y = tf.nn.softmax(y)
y_ = tf.one_hot(y_train, depth=3)
loss = tf.reduce_mean(tf.square(y_ - y))
loss_all += loss.numpy()
grads = tape.gradient(loss, [w1, b1])
v_w = beta * v_w + (1 - beta) * tf.square(grads[0])
v_b = beta * v_b + (1 - beta) * tf.square(grads[1])
w1.assign_sub(lr * grads[0] / tf.sqrt(v_w))
b1.assign_sub(lr * grads[1] / tf.sqrt(v_b))
print("Epoch {}, loss: {}".format(epoch, loss_all / 4))
train_loss_results.append(loss_all / 4)
loss_all = 0
total_correct, total_number = 0, 0
for x_test, y_test in test_db:
y = tf.matmul(x_test, w1) + b1
y = tf.nn.softmax(y)
pred = tf.argmax(y, axis=1)
pred = tf.cast(pred, dtype=y_test.dtype)
correct = tf.cast(tf.equal(pred, y_test), dtype=tf.int32)
correct = tf.reduce_sum(correct)
total_correct += int(correct)
total_number += x_test.shape[0]
acc = total_correct / total_number
test_acc.append(acc)
print("Test_acc:", acc)
print("--------------------------")
total_time = time.time() - now_time
print("total_time", total_time)
plt.title('Loss Function Curve')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.plot(train_loss_results, label="$Loss$")
plt.legend()
plt.show()
plt.title('Acc Curve')
plt.xlabel('Epoch')
plt.ylabel('Acc')
plt.plot(test_acc, label="$Accuracy$")
plt.legend()
plt.show()
5.Adam同时结合SGDM一阶动量和RMSProp二阶动量
import tensorflow as tf
from sklearn import datasets
from matplotlib import pyplot as plt
import numpy as np
import time
x_data = datasets.load_iris().data
y_data = datasets.load_iris().target
np.random.seed(116)
np.random.shuffle(x_data)
np.random.seed(116)
np.random.shuffle(y_data)
tf.random.set_seed(116)
x_train = x_data[:-30]
y_train = y_data[:-30]
x_test = x_data[-30:]
y_test = y_data[-30:]
x_train = tf.cast(x_train, tf.float32)
x_test = tf.cast(x_test, tf.float32)
train_db = tf.data.Dataset.from_tensor_slices((x_train, y_train)).batch(32)
test_db = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)
w1 = tf.Variable(tf.random.truncated_normal([4, 3], stddev=0.1, seed=1))
b1 = tf.Variable(tf.random.truncated_normal([3], stddev=0.1, seed=1))
lr = 0.1
train_loss_results = []
test_acc = []
epoch = 500
loss_all = 0
m_w, m_b = 0, 0
v_w, v_b = 0, 0
beta1, beta2 = 0.9, 0.999
delta_w, delta_b = 0, 0
global_step = 0
now_time = time.time()
for epoch in range(epoch):
for step, (x_train, y_train) in enumerate(train_db):
global_step += 1
with tf.GradientTape() as tape:
y = tf.matmul(x_train, w1) + b1
y = tf.nn.softmax(y)
y_ = tf.one_hot(y_train, depth=3)
loss = tf.reduce_mean(tf.square(y_ - y))
loss_all += loss.numpy()
grads = tape.gradient(loss, [w1, b1])
m_w = beta1 * m_w + (1 - beta1) * grads[0]
m_b = beta1 * m_b + (1 - beta1) * grads[1]
v_w = beta2 * v_w + (1 - beta2) * tf.square(grads[0])
v_b = beta2 * v_b + (1 - beta2) * tf.square(grads[1])
m_w_correction = m_w / (1 - tf.pow(beta1, int(global_step)))
m_b_correction = m_b / (1 - tf.pow(beta1, int(global_step)))
v_w_correction = v_w / (1 - tf.pow(beta2, int(global_step)))
v_b_correction = v_b / (1 - tf.pow(beta2, int(global_step)))
w1.assign_sub(lr * m_w_correction / tf.sqrt(v_w_correction))
b1.assign_sub(lr * m_b_correction / tf.sqrt(v_b_correction))
print("Epoch {}, loss: {}".format(epoch, loss_all / 4))
train_loss_results.append(loss_all / 4)
loss_all = 0
total_correct, total_number = 0, 0
for x_test, y_test in test_db:
y = tf.matmul(x_test, w1) + b1
y = tf.nn.softmax(y)
pred = tf.argmax(y, axis=1)
pred = tf.cast(pred, dtype=y_test.dtype)
correct = tf.cast(tf.equal(pred, y_test), dtype=tf.int32)
correct = tf.reduce_sum(correct)
total_correct += int(correct)
total_number += x_test.shape[0]
acc = total_correct / total_number
test_acc.append(acc)
print("Test_acc:", acc)
print("--------------------------")
total_time = time.time() - now_time
print("total_time", total_time)
plt.title('Loss Function Curve')
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.plot(train_loss_results, label="$Loss$")
plt.legend()
plt.show()
plt.title('Acc Curve')
plt.xlabel('Epoch')
plt.ylabel('Acc')
plt.plot(test_acc, label="$Accuracy$")
plt.legend()
plt.show()
相关知识
TensorFlow使用BP神经网络实现鸢尾花分类
TensorFlow学习记录（八）
Tensorflow鸢尾花分类（数据加载与特征处理）
深度学习入门——基于TensorFlow的鸢尾花分类实现（TensorFlow
TensorFlow 2建立神经网络分类模型——以iris数据为例
教程：对鸢尾花进行分类
第3章（下）基于Softmax回归完成鸢尾花分类任务
在鸢尾花分类中感受技术“温度”
使用鸢尾花数据集构建神经网络模型
python 使用Tensorflow训练BP神经网络实现鸢尾花分类
网址: TensorFlow 各优化器在鸢尾花分类任务中的应用 https://m.huajiangbk.com/newsview1284135.html
| 上一篇: 优化营商环境｜临武花塘乡：人居环 |
下一篇: 花家红在全市优化营商环境工作推进 |
