2021-03-09

Deep Learning for Computer Vision with Python

---

前言

使用NN检测MNIST数据集。

---

一、NN是什么？

NN是神经网络，多层感知机构成。

二、使用步骤

1.引入库

代码如下（示例）：

from sklearn.preprocessing import LabelBinarizer
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from keras.models import Sequential
from keras.layers.core import Dense
from keras.optimizers import SGD
from sklearn import datasets
import matplotlib.pyplot as plt
import numpy as np
import os
import argparse

2.代码

网络为4层，每层分别含有64，32，16，10个神经元。
代码如下（示例）：

parser = argparse.ArgumentParser()
parser.add_argument("--out", default = "./mnist_res", help="输出路径")
args = parser.parse_args()

if not os.path.exists(args.out):
    os.makedirs(args.out)

# load the MNIST dataset and apply min/max scaling to scale the
# pixel intensity values to the range [0, 1] (each image is represented by an 28 x 28 = 784-dim feature vector)
# scale the raw pixel intensities to the range  [0, 1.0] then
dataset = datasets.fetch_mldata("MNIST-original", data_home="./mnist_res/")
data = dataset.data.astype("float")/255.0


(trainx, testx, trainy, testy) = train_test_split(data, dataset.target, test_size=0.25)
lb = LabelBinarizer()
trainy = lb.fit_transform(trainy)
testy = lb.fit_transform(testy)

print(data.shape)
model = Sequential()
model.add(Dense(64,input_shape = (784,),activation = "sigmoid"))
model.add(Dense(32,activation="sigmoid"))
model.add(Dense(16,activation="sigmoid"))
model.add(Dense(10,activation="softmax"))
model.compile(loss="categorical_crossentropy" , optimizer= SGD(0.01), metrics=["accuracy"])
model.fit(trainx, trainy, validation_data=(testx, testy), epochs=100,batch_size=128)
predictions = model.predict(testx, batch_size=128)
print(classification_report(testy.argmax(axis=1), predictions.argmax(axis=1), target_names=[str(x) for x in lb.classes_]))

---

总结

就这样啦