keras訓(xùn)練淺層卷積網(wǎng)絡(luò)并保存和加載模型實(shí)例
這里我們使用keras定義簡(jiǎn)單的神經(jīng)網(wǎng)絡(luò)全連接層訓(xùn)練MNIST數(shù)據(jù)集和cifar10數(shù)據(jù)集:
keras_mnist.py
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 argparse
# 命令行參數(shù)運(yùn)行
ap = argparse.ArgumentParser()
ap.add_argument("-o", "--output", required=True, help="path to the output loss/accuracy plot")
args =vars(ap.parse_args())
# 加載數(shù)據(jù)MNIST,然后歸一化到【0,1】,同時(shí)使用75%做訓(xùn)練,25%做測(cè)試
print("[INFO] loading MNIST (full) dataset")
dataset = datasets.fetch_mldata("MNIST Original", data_home="/home/king/test/python/train/pyimagesearch/nn/data/")
data = dataset.data.astype("float") / 255.0
(trainX, testX, trainY, testY) = train_test_split(data, dataset.target, test_size=0.25)
# 將label進(jìn)行one-hot編碼
lb = LabelBinarizer()
trainY = lb.fit_transform(trainY)
testY = lb.transform(testY)
# keras定義網(wǎng)絡(luò)結(jié)構(gòu)784--256--128--10
model = Sequential()
model.add(Dense(256, input_shape=(784,), activation="relu"))
model.add(Dense(128, activation="relu"))
model.add(Dense(10, activation="softmax"))
# 開(kāi)始訓(xùn)練
print("[INFO] training network...")
# 0.01的學(xué)習(xí)率
sgd = SGD(0.01)
# 交叉驗(yàn)證
model.compile(loss="categorical_crossentropy", optimizer=sgd, metrics=['accuracy'])
H = model.fit(trainX, trainY, validation_data=(testX, testY), epochs=100, batch_size=128)
# 測(cè)試模型和評(píng)估
print("[INFO] evaluating network...")
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_]))
# 保存可視化訓(xùn)練結(jié)果
plt.style.use("ggplot")
plt.figure()
plt.plot(np.arange(0, 100), H.history["loss"], label="train_loss")
plt.plot(np.arange(0, 100), H.history["val_loss"], label="val_loss")
plt.plot(np.arange(0, 100), H.history["acc"], label="train_acc")
plt.plot(np.arange(0, 100), H.history["val_acc"], label="val_acc")
plt.title("Training Loss and Accuracy")
plt.xlabel("# Epoch")
plt.ylabel("Loss/Accuracy")
plt.legend()
plt.savefig(args["output"])
使用relu做激活函數(shù):

使用sigmoid做激活函數(shù):

接著我們自己定義一些modules去實(shí)現(xiàn)一個(gè)簡(jiǎn)單的卷基層去訓(xùn)練cifar10數(shù)據(jù)集:
imagetoarraypreprocessor.py
''' 該函數(shù)主要是實(shí)現(xiàn)keras的一個(gè)細(xì)節(jié)轉(zhuǎn)換,因?yàn)橛?xùn)練的圖像時(shí)RGB三顏色通道,讀取進(jìn)來(lái)的數(shù)據(jù)是有depth的,keras為了兼容一些后臺(tái),默認(rèn)是按照(height, width, depth)讀取,但有時(shí)候就要改變成(depth, height, width) ''' from keras.preprocessing.image import img_to_array class ImageToArrayPreprocessor: def __init__(self, dataFormat=None): self.dataFormat = dataFormat def preprocess(self, image): return img_to_array(image, data_format=self.dataFormat)
shallownet.py
'''
定義一個(gè)簡(jiǎn)單的卷基層:
input->conv->Relu->FC
'''
from keras.models import Sequential
from keras.layers.convolutional import Conv2D
from keras.layers.core import Activation, Flatten, Dense
from keras import backend as K
class ShallowNet:
@staticmethod
def build(width, height, depth, classes):
model = Sequential()
inputShape = (height, width, depth)
if K.image_data_format() == "channels_first":
inputShape = (depth, height, width)
model.add(Conv2D(32, (3, 3), padding="same", input_shape=inputShape))
model.add(Activation("relu"))
model.add(Flatten())
model.add(Dense(classes))
model.add(Activation("softmax"))
return model
然后就是訓(xùn)練代碼:
keras_cifar10.py
from sklearn.preprocessing import LabelBinarizer
from sklearn.metrics import classification_report
from shallownet import ShallowNet
from keras.optimizers import SGD
from keras.datasets import cifar10
import matplotlib.pyplot as plt
import numpy as np
import argparse
ap = argparse.ArgumentParser()
ap.add_argument("-o", "--output", required=True, help="path to the output loss/accuracy plot")
args = vars(ap.parse_args())
print("[INFO] loading CIFAR-10 dataset")
((trainX, trainY), (testX, testY)) = cifar10.load_data()
trainX = trainX.astype("float") / 255.0
testX = testX.astype("float") / 255.0
lb = LabelBinarizer()
trainY = lb.fit_transform(trainY)
testY = lb.transform(testY)
# 標(biāo)簽0-9代表的類(lèi)別string
labelNames = ['airplane', 'automobile', 'bird', 'cat',
'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
print("[INFO] compiling model...")
opt = SGD(lr=0.0001)
model = ShallowNet.build(width=32, height=32, depth=3, classes=10)
model.compile(loss="categorical_crossentropy", optimizer=opt, metrics=["accuracy"])
print("[INFO] training network...")
H = model.fit(trainX, trainY, validation_data=(testX, testY), batch_size=32, epochs=1000, verbose=1)
print("[INFO] evaluating network...")
predictions = model.predict(testX, batch_size=32)
print(classification_report(testY.argmax(axis=1), predictions.argmax(axis=1),
target_names=labelNames))
# 保存可視化訓(xùn)練結(jié)果
plt.style.use("ggplot")
plt.figure()
plt.plot(np.arange(0, 1000), H.history["loss"], label="train_loss")
plt.plot(np.arange(0, 1000), H.history["val_loss"], label="val_loss")
plt.plot(np.arange(0, 1000), H.history["acc"], label="train_acc")
plt.plot(np.arange(0, 1000), H.history["val_acc"], label="val_acc")
plt.title("Training Loss and Accuracy")
plt.xlabel("# Epoch")
plt.ylabel("Loss/Accuracy")
plt.legend()
plt.savefig(args["output"])
代碼中可以對(duì)訓(xùn)練的learning rate進(jìn)行微調(diào),大概可以接近60%的準(zhǔn)確率。


然后修改下代碼可以保存訓(xùn)練模型:
from sklearn.preprocessing import LabelBinarizer
from sklearn.metrics import classification_report
from shallownet import ShallowNet
from keras.optimizers import SGD
from keras.datasets import cifar10
import matplotlib.pyplot as plt
import numpy as np
import argparse
ap = argparse.ArgumentParser()
ap.add_argument("-o", "--output", required=True, help="path to the output loss/accuracy plot")
ap.add_argument("-m", "--model", required=True, help="path to save train model")
args = vars(ap.parse_args())
print("[INFO] loading CIFAR-10 dataset")
((trainX, trainY), (testX, testY)) = cifar10.load_data()
trainX = trainX.astype("float") / 255.0
testX = testX.astype("float") / 255.0
lb = LabelBinarizer()
trainY = lb.fit_transform(trainY)
testY = lb.transform(testY)
# 標(biāo)簽0-9代表的類(lèi)別string
labelNames = ['airplane', 'automobile', 'bird', 'cat',
'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
print("[INFO] compiling model...")
opt = SGD(lr=0.005)
model = ShallowNet.build(width=32, height=32, depth=3, classes=10)
model.compile(loss="categorical_crossentropy", optimizer=opt, metrics=["accuracy"])
print("[INFO] training network...")
H = model.fit(trainX, trainY, validation_data=(testX, testY), batch_size=32, epochs=50, verbose=1)
model.save(args["model"])
print("[INFO] evaluating network...")
predictions = model.predict(testX, batch_size=32)
print(classification_report(testY.argmax(axis=1), predictions.argmax(axis=1),
target_names=labelNames))
# 保存可視化訓(xùn)練結(jié)果
plt.style.use("ggplot")
plt.figure()
plt.plot(np.arange(0, 5), H.history["loss"], label="train_loss")
plt.plot(np.arange(0, 5), H.history["val_loss"], label="val_loss")
plt.plot(np.arange(0, 5), H.history["acc"], label="train_acc")
plt.plot(np.arange(0, 5), H.history["val_acc"], label="val_acc")
plt.title("Training Loss and Accuracy")
plt.xlabel("# Epoch")
plt.ylabel("Loss/Accuracy")
plt.legend()
plt.savefig(args["output"])
命令行運(yùn)行:

我們使用另一個(gè)程序來(lái)加載上一次訓(xùn)練保存的模型,然后進(jìn)行測(cè)試:
test.py
from sklearn.preprocessing import LabelBinarizer
from sklearn.metrics import classification_report
from shallownet import ShallowNet
from keras.optimizers import SGD
from keras.datasets import cifar10
from keras.models import load_model
import matplotlib.pyplot as plt
import numpy as np
import argparse
ap = argparse.ArgumentParser()
ap.add_argument("-m", "--model", required=True, help="path to save train model")
args = vars(ap.parse_args())
# 標(biāo)簽0-9代表的類(lèi)別string
labelNames = ['airplane', 'automobile', 'bird', 'cat',
'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
print("[INFO] loading CIFAR-10 dataset")
((trainX, trainY), (testX, testY)) = cifar10.load_data()
idxs = np.random.randint(0, len(testX), size=(10,))
testX = testX[idxs]
testY = testY[idxs]
trainX = trainX.astype("float") / 255.0
testX = testX.astype("float") / 255.0
lb = LabelBinarizer()
trainY = lb.fit_transform(trainY)
testY = lb.transform(testY)
print("[INFO] loading pre-trained network...")
model = load_model(args["model"])
print("[INFO] evaluating network...")
predictions = model.predict(testX, batch_size=32).argmax(axis=1)
print("predictions\n", predictions)
for i in range(len(testY)):
print("label:{}".format(labelNames[predictions[i]]))
trueLabel = []
for i in range(len(testY)):
for j in range(len(testY[i])):
if testY[i][j] != 0:
trueLabel.append(j)
print(trueLabel)
print("ground truth testY:")
for i in range(len(trueLabel)):
print("label:{}".format(labelNames[trueLabel[i]]))
print("TestY\n", testY)

以上這篇keras訓(xùn)練淺層卷積網(wǎng)絡(luò)并保存和加載模型實(shí)例就是小編分享給大家的全部?jī)?nèi)容了,希望能給大家一個(gè)參考,也希望大家多多支持腳本之家。
相關(guān)文章
Python實(shí)現(xiàn)圖像隨機(jī)添加椒鹽噪聲和高斯噪聲
圖像噪聲是指存在于圖像數(shù)據(jù)中的不必要的或多余的干擾信息。在噪聲的概念中,通常采用信噪比(Signal-Noise?Rate,?SNR)衡量圖像噪聲。本文將利用Python實(shí)現(xiàn)對(duì)圖像隨機(jī)添加椒鹽噪聲和高斯噪聲,感興趣的可以了解一下2022-09-09
python 使用元類(lèi)type創(chuàng)建類(lèi)
這篇文章主要介紹了Python 使用元類(lèi)type創(chuàng)建類(lèi),結(jié)合實(shí)例形式詳細(xì)分析了Python元類(lèi)的概念、功能及元類(lèi)type創(chuàng)建類(lèi)對(duì)象的常見(jiàn)應(yīng)用技巧,需要的朋友可以參考一下文章的具體內(nèi)容。希望對(duì)你有所幫助2021-10-10
Django Admin設(shè)置應(yīng)用程序及模型順序方法詳解
這篇文章主要介紹了Django Admin設(shè)置應(yīng)用程序及模型順序方法詳解,文中通過(guò)示例代碼介紹的非常詳細(xì),對(duì)大家的學(xué)習(xí)或者工作具有一定的參考學(xué)習(xí)價(jià)值,需要的朋友可以參考下2020-04-04
Python爬取微信讀書(shū)實(shí)現(xiàn)讀書(shū)免費(fèi)自由
主要跟大家介紹一下,我是如何用Python爬取小說(shuō),再導(dǎo)入微信讀書(shū)的。成功實(shí)現(xiàn)在微信讀書(shū)中各種“白票”付費(fèi)小說(shuō),有需要的朋友可以借鑒參考下2021-09-09
Python操作MySQL數(shù)據(jù)庫(kù)的方法
pymsql是Python中操作MySQL的模塊,其使用方法和MySQLdb幾乎相同。接下來(lái)通過(guò)本文給大家介紹Python操作MySQL數(shù)據(jù)庫(kù)的方法,感興趣的朋友一起看看吧2018-06-06
numpy的sum函數(shù)的axis和keepdim參數(shù)詳解
這篇文章主要介紹了numpy的sum函數(shù)的axis和keepdim參數(shù)詳解,文中通過(guò)示例代碼介紹的非常詳細(xì),對(duì)大家的學(xué)習(xí)或者工作具有一定的參考學(xué)習(xí)價(jià)值,需要的朋友們下面隨著小編來(lái)一起學(xué)習(xí)學(xué)習(xí)吧2021-03-03
python繪制動(dòng)態(tài)曲線(xiàn)教程
今天小編就為大家分享一篇python繪制動(dòng)態(tài)曲線(xiàn)教程,具有很好的參考價(jià)值,希望對(duì)大家有所幫助。一起跟隨小編過(guò)來(lái)看看吧2020-02-02

