我正在尝试构建一个简单的神经网络来将产品图像分类为不同的标签（产品类型）。即，给定一个新的产品图像，告诉它属于哪个产品类别类型（书籍、玩具、电子产品等）。
我在每个产品编号下都有几个产品图像，每个产品编号在 Excel 表中都有一个标签（即产品类型）。
下面是我的代码：
from sklearn.preprocessing import LabelEncoder
from sklearn.cross_validation import train_test_split
from keras.models import Sequential
from keras.layers import Activation
from keras.optimizers import SGD
from keras.layers import Dense
from keras.utils import np_utils
from imutils import paths
import numpy as np
import argparse
import cv2
import os
import xlwt
import xlrd
import glob2
import pickle
def image_to_feature_vector(image, size=(32,32)):
return cv2.resize(image, size).flatten()
def read_data(xls = "/Desktop/num_to_product_type.xlsx"):
book = xlrd.open_workbook(xls)
sheet = book.sheet_by_index(0)
d = {}
for row_index in xrange(1, sheet.nrows): # skip heading row
prod_type, prod_num = sheet.row_values(row_index, end_colx=2)
prod_type = unicode(prod_type).encode('UTF8')
produ_num = unicode(prod_num).encode('UTF8')
d[prod_num] = prod_type
return d
def main():
try:
imagePaths=[]
print("[INFO] describing images...")
for path, subdirs, files in os.walk(r'/Desktop/data'):
for filename in files:
imagePaths.append(os.path.join(path, filename))
files = glob2.glob('/Desktop/data/**/.DS_Store')
for i in files:
imagePaths.remove(i)
except:
pass
dd = read_data()
# initialize the data matrix and labels list
data = []
labels1 = []
for (i, imagePath) in enumerate(imagePaths):
image = cv2.imread(imagePath)
#print(image.shape)
subdir = imagePath.split('/')[-2]
for k, v in dd.items():
if k == subdir:
label = v
break
features = image_to_feature_vector(image)
data.append(features)
labels1.append(label)
# show an update every 1,000 images
if i > 0 and i % 1000 == 0:
print("[INFO] processed {}/{}".format(i, len(imagePaths)))
print("String Labels")
print(labels1)
# encode the labels, converting them from strings to integers
le = LabelEncoder()
labels = le.fit_transform(labels1)
print(labels)
d={}
d[labels[0]] = labels1[0]
for i in range(1,len(labels)-1):
if labels[i-1] != labels[i] and labels[i] == labels[i+1]:
d[labels[i]] = labels1[i]
data = np.array(data) / 255.0
labels = np_utils.to_categorical(labels, 51)
print("To_Categorical")
print(labels)
print("[INFO] constructing training/testing split...")
(trainData, testData, trainLabels, testLabels) = train_test_split(
data, labels, test_size=0.25, random_state=42)
model = Sequential()
model.add(Dense(768, input_dim=3072, init="uniform",
activation="relu"))
model.add(Dense(384, init="uniform", activation="relu"))
model.add(Dense(51))
model.add(Activation("softmax"))
print("[INFO] compiling model...")
sgd = SGD(lr=0.125
)
model.compile(loss="categorical_crossentropy", optimizer=sgd,
metrics=["accuracy"])
model.fit(trainData, trainLabels, nb_epoch=50, batch_size=750)
# #Test the model
#show the accuracy on the testing set
print("[INFO] evaluating on testing set...")
(loss, accuracy) = model.evaluate(testData, testLabels,
batch_size=128, verbose=1)
print("[INFO] loss={:.4f}, accuracy: {:.4f}%".format(loss,
accuracy * 100))
if __name__ == '__main__':
main()
神经网络是一个 3-2-3-51 前馈神经网络。第 0 层包含 3 个输入。第 1 层和第 2 层是包含 2 和 3 个节点的隐藏层。第 3 层是具有 51 个节点的输出层（即，用于 51 个产品类别类型）。但是，这样我得到的准确率非常低，只有大约 45-50%。
我做错了什么吗？如何提高神经网络的准确性？我在某处读到它可以通过“ crossvalidation and hyperparameter tuning”完成，但它是如何完成的？对不起，我对神经网络很陌生，只是尝试一些新的东西。谢谢。