其他分享
首页 > 其他分享> > TensorFlow学习报告

TensorFlow学习报告

作者:互联网

Tensorflow简介

TensorFlow是采用数据流图(data flow graphs)来计算, 所以首先我们得创建一个数据流流图,然后再将我们的数据(数据以张量(tensor)的形式存在)放在数据流图中计算. 节点(Nodes)在图中表示数学操作,图中的边(edges)则表示在节点间相互联系的多维数据数组, 即张量(tensor).训练模型时tensor会不断的从数据流图中的一个节点flow到另一节点, 这就是TensorFlow名字的由来.

备注:

3.TensorFlow的五个主要特征

1.鸢尾花分类问题

#导入相关包
from sklearn.datasets import load_iris#导入数据集
from pandas import DataFrame
import pandas as pd


x_data=load_iris().data #返回iris数据集的所有输入
y_data=load_iris().target #返回iris数据集中所有标签


x_data=DataFrame(x_data,columns=['花萼长度','花萼宽度','花瓣长度','花萼宽度'])
pd.set_option('display.unicode.east_asian_width',True) #设置列名对其

x_data['类别']=y_data #添加一列,列标签为列表

# 导入所需模块
import tensorflow as tf
from sklearn import datasets
from matplotlib import pyplot as plt
%matplotlib inline
import numpy as np

# 导入数据,分别为输入特征和标签
x_data = datasets.load_iris().data
y_data = datasets.load_iris().target

# 随机打乱数据(因为原始数据是顺序的,顺序不打乱会影响准确率)
# seed: 随机数种子,是一个整数,当设置之后,每次生成的随机数都一样(为方便教学,以保每位同学结果一致)
np.random.seed(116) # 使用相同的seed,保证输入特征和标签一一对应
np.random.shuffle(x_data)
np.random.seed(116)
np.random.shuffle(y_data)
tf.random.set_seed(116)

# 将打乱后的数据集分割为训练集和测试集,训练集为前120行,测试集为后30行
x_train = x_data[:-30]
y_train = y_data[:-30]
x_test = x_data[-30:]
y_test = y_data[-30:]

# 转换x的数据类型,否则后面矩阵相乘时会因数据类型不一致报错
x_train = tf.cast(x_train, tf.float32)
x_test = tf.cast(x_test, tf.float32)

# from_tensor_slices函数使输入特征和标签值一一对应。(把数据集分批次,每个批次batch组数据)
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)

# 生成神经网络的参数,4个输入特征故,输入层为4个输入节点;因为3分类,故输出层为3个神经元
# 用tf.Variable()标记参数可训练
# 使用seed使每次生成的随机数相同(方便教学,使大家结果都一致,在现实使用时不写seed)
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))

#定义超参数
lr = 0.1 # 学习率为0.1
train_loss_results = [] # 将每轮的loss记录在此列表中,为后续画loss曲线提供数据
test_acc = [] # 将每轮的acc记录在此列表中,为后续画acc曲线提供数据
epoch = 500 # 循环500轮
loss_all = 0 # 每轮分4个step,loss_all记录四个step生成的4个loss的和

# 训练部分
for epoch in range(epoch): #数据集级别的循环,每个epoch循环一次数据集
for step, (x_train, y_train) in enumerate(train_db): #batch级别的循环 ,每个step循环一个batch
with tf.GradientTape() as tape: # with结构记录梯度信息
y = tf.matmul(x_train, w1) + b1 # 神经网络乘加运算
y = tf.nn.softmax(y) # 使输出y符合概率分布(此操作后与独热码同量级,可相减求loss)
y_ = tf.one_hot(y_train, depth=3) # 将标签值转换为独热码格式,方便计算loss和accuracy
loss = tf.reduce_mean(tf.square(y_ - y)) # 采用均方误差损失函数mse = mean(sum(y-out)^2)
loss_all += loss.numpy() # 将每个step计算出的loss累加,为后续求loss平均值提供数据,这样计算的loss更准确
# 计算loss对各个参数的梯度
grads = tape.gradient(loss, [w1, b1])

# 实现梯度更新 w1 = w1 - lr * w1_grad b = b - lr * b_grad
w1.assign_sub(lr * grads[0]) # 参数w1自更新
b1.assign_sub(lr * grads[1]) # 参数b自更新

# 每个epoch,打印loss信息
print("Epoch {}, loss: {}".format(epoch, loss_all/4))
train_loss_results.append(loss_all / 4) # 将4个step的loss求平均记录在此变量中
loss_all = 0 # loss_all归零,为记录下一个epoch的loss做准备

# 测试部分
# total_correct为预测对的样本个数, total_number为测试的总样本数,将这两个变量都初始化为0
total_correct, total_number = 0, 0
for x_test, y_test in test_db:
# 使用更新后的参数进行预测
y = tf.matmul(x_test, w1) + b1#计算前向传播预测结果
y = tf.nn.softmax(y)#变为概率分布
pred = tf.argmax(y, axis=1) # 返回y中最大值的索引,即预测的分类
# 将pred转换为y_test的数据类型
pred = tf.cast(pred, dtype=y_test.dtype)
# 若分类正确,则correct=1,否则为0,将bool型的结果转换为int型
correct = tf.cast(tf.equal(pred, y_test), dtype=tf.int32)
# 将每个batch的correct数加起来
correct = tf.reduce_sum(correct)
# 将所有batch中的correct数加起来
total_correct += int(correct)
# total_number为测试的总样本数,也就是x_test的行数,shape[0]返回变量的行数
total_number += x_test.shape[0]
# 总的准确率等于total_correct/total_number
acc = total_correct / total_number
test_acc.append(acc)
print("Test_acc:", acc)
print("--------------------------")

# 绘制 loss 曲线
plt.title('Loss Function Curve') # 图片标题
plt.xlabel('Epoch') # x轴变量名称
plt.ylabel('Loss') # y轴变量名称
plt.plot(train_loss_results, label="$Loss$") # 逐点画出trian_loss_results值并连线,连线图标是Loss
plt.legend() # 画出曲线图标
plt.show() # 画出图像

# 绘制 Accuracy 曲线
plt.title('Acc Curve') # 图片标题
plt.xlabel('Epoch') # x轴变量名称
plt.ylabel('Acc') # y轴变量名称
plt.plot(test_acc, label="$Accuracy$") # 逐点画出test_acc值并连线,连线图标是Accuracy
plt.legend()
plt.show()

2.低阶API实现线性回归

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
input_x=np.float32(np.linspace(-1,1,100))#在区间[-1,1)内产生100个数的等差数列,作为输入
input_y=2*input_x+np.random.randn(*input_x.shape)*0.3#y=2x+随机噪声
weight=tf.Variable(1.,dtype=tf.float32,name='weight')
bias=tf.Variable(1.,dtype=tf.float32,name='bias')
def model(x):          #定义了线性模型y=weight*x+bias
    pred=tf.multiply(x, weight)+bias
    return pred
step=0
opt=tf.optimizers.Adam(1e-1) #选择优化器,是一种梯度下降的方法
for x,y in zip(input_x,input_y):
    x=np.reshape(x,[1])
    y=np.reshape(y,[1])
    step=step+1
    with tf.GradientTape()as tape:
        loss=tf.losses.MeanSquaredError()(model(x),y)#连续数据的预测,损失函数用MSE
    grads=tape.gradient(loss,[weight,bias])#计算梯度
    opt.apply_gradients(zip(grads,[weight,bias]))#更新参数weight和bias
    print("Step:",step,"Traing Loss:",loss.numpy())
    #用Matplotlib可视化原始数据和预测的模型
    plt.plot(input_x,input_y,'ro',label='original data')
    plt.plot(input_x, model(input_x),label='predicted value')
    plt.plot(input_x,2*input_x,label='y=2x')
    plt.legend()
    plt.show()
    print(weight)
    print(bias)

3.服装图像分类

# TensorFlow and tf.keras
import tensorflow as tf
from tensorflow import keras

# Helper libraries
import numpy as np
import matplotlib.pyplot as plt

print(tf.__version__)
fashion_mnist = keras.datasets.fashion_mnist

(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()
class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
plt.figure()
plt.imshow(train_images[0])
plt.colorbar()
plt.grid(False)
plt.show()
train_images = train_images / 255.0

test_images = test_images / 255.0
plt.figure(figsize=(10,10))
for i in range(25):
    plt.subplot(5,5,i+1)
    plt.xticks([])
    plt.yticks([])
    plt.grid(False)
    plt.imshow(train_images[i], cmap=plt.cm.binary)
    plt.xlabel(class_names[train_labels[i]])
plt.show()
model = keras.Sequential([
    keras.layers.Flatten(input_shape=(28, 28)),
    keras.layers.Dense(128, activation='relu'),
    keras.layers.Dense(10)
])
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])
model.fit(train_images, train_labels, epochs=10)
test_loss, test_acc = model.evaluate(test_images,  test_labels, verbose=2)

print('\nTest accuracy:', test_acc)
probability_model = tf.keras.Sequential([model,
                                         tf.keras.layers.Softmax()])
predictions = probability_model.predict(test_images)
np.argmax(predictions[0])
def plot_image(i, predictions_array, true_label, img):
  predictions_array, true_label, img = predictions_array, true_label[i], img[i]
  plt.grid(False)
  plt.xticks([])
  plt.yticks([])

  plt.imshow(img, cmap=plt.cm.binary)

  predicted_label = np.argmax(predictions_array)
  if predicted_label == true_label:
    color = 'blue'
  else:
    color = 'red'

  plt.xlabel("{} {:2.0f}% ({})".format(class_names[predicted_label],
                                100*np.max(predictions_array),
                                class_names[true_label]),
                                color=color)

def plot_value_array(i, predictions_array, true_label):
  predictions_array, true_label = predictions_array, true_label[i]
  plt.grid(False)
  plt.xticks(range(10))
  plt.yticks([])
  thisplot = plt.bar(range(10), predictions_array, color="#777777")
  plt.ylim([0, 1])
  predicted_label = np.argmax(predictions_array)

  thisplot[predicted_label].set_color('red')
  thisplot[true_label].set_color('blue')
i = 0
plt.figure(figsize=(6, 3))
plt.subplot(1, 2, 1)
plot_image(i, predictions[i], test_labels, test_images)
plt.subplot(1, 2, 2)
plot_value_array(i, predictions[i], test_labels)
plt.show()
i = 12
plt.figure(figsize=(6, 3))
plt.subplot(1, 2, 1)
plot_image(i, predictions[i], test_labels, test_images)
plt.subplot(1, 2, 2)
plot_value_array(i, predictions[i], test_labels)
plt.show()
# Plot the first X test images, their predicted labels, and the true labels.
# Color correct predictions in blue and incorrect predictions in red.
num_rows = 5
num_cols = 3
num_images = num_rows * num_cols
plt.figure(figsize=(2 * 2 * num_cols, 2 * num_rows))
for i in range(num_images):
    plt.subplot(num_rows, 2 * num_cols, 2 * i + 1)
    plot_image(i, predictions[i], test_labels, test_images)
    plt.subplot(num_rows, 2 * num_cols, 2 * i + 2)
    plot_value_array(i, predictions[i], test_labels)
plt.tight_layout()
plt.show()
# Grab an image from the test dataset.
img = test_images[1]

print(img.shape)
# Add the image to a batch where it's the only member.
img = (np.expand_dims(img, 0))

print(img.shape)
predictions_single = probability_model.predict(img)

print(predictions_single)
plot_value_array(1, predictions_single[0], test_labels)
_ = plt.xticks(range(10), class_names, rotation=45)
np.argmax(predictions_single[0])

结果如下:

 

 

   

标签:loss,plt,报告,predictions,学习,test,train,tf,TensorFlow
来源: https://www.cnblogs.com/rwc5397/p/16191538.html