本篇文章给人人带来的内容是关于Tensorflow分类器项目自定义数据读入的要领引见（代码示例），有肯定的参考价值，有须要的朋侪能够参考一下，愿望对你有所协助。
Tensorflow分类器项目自定义数据读入
在照着Tensorflow官网的demo敲了一遍分类器项目的代码后，运转却是胜利了，效果也不错。然则终究照样要练习本身的数据，所以尝试预备加载自定义的数据，但是demo中只是涌现了fashion_mnist.load_data()并没有细致的读取历程，随后我又找了些材料，把读取的历程纪录在这里。
起首提一下须要用到的模块：
import os import keras import matplotlib.pyplot as plt from PIL import Image from keras.preprocessing.image import ImageDataGenerator from sklearn.model_selection import train_test_split
图片分类器项目，起首肯定你要处置惩罚的图片分辨率将是若干，这里的例子为30像素：
IMG_SIZE_X = 30 IMG_SIZE_Y = 30
其次肯定你图片的体式格局目次：
image_path = r'D:\Projects\ImageClassifier\data\set' path = ".\data" # 你也能够运用相对路径的体式格局 # image_path =os.path.join(path, "set")
目次下的构造以下：
响应的label.txt以下：
动漫 景致 玉人 物语 樱花
接下来是接在labels.txt，以下：
label_name = "labels.txt"
label_path = os.path.join(path, label_name)
class_names = np.loadtxt(label_path, type(""))
这里轻便起见，直接应用了numpy的loadtxt函数直接加载。
以后就是正式处置惩罚图片数据了，解释就写在内里了：
re_load = False
re_build = False
# re_load = True
re_build = True
data_name = "data.npz"
data_path = os.path.join(path, data_name)
model_name = "model.h5"
model_path = os.path.join(path, model_name)
count = 0
# 这里推断是不是存在序列化以后的数据，re_load是一个开关，是不是强迫重新处置惩罚，测试用，能够去除。
if not os.path.exists(data_path) or re_load:
labels = []
images = []
print('Handle images')
# 因为label.txt是和图片防备目次的分类目次一一对应的，即每一个子目次的目次名就是labels.txt里的一个label，所以这里能够经由过程读取class_names的每一项去拼接path后读取
for index, name in enumerate(class_names):
# 这里是拼接后的子目次path
classpath = os.path.join(image_path, name)
# 先推断一下是不是是目次
if not os.path.isdir(classpath):
continue
# limit是测试时刻用的这里能够去除
limit = 0
for image_name in os.listdir(classpath):
if limit >= max_size:
break
# 这里是拼接后的待处置惩罚的图片path
imagepath = os.path.join(classpath, image_name)
count = count + 1
limit = limit + 1
# 应用Image翻开图片
img = Image.open(imagepath)
# 缩放到你最初肯定要处置惩罚的图片分辨率大小
img = img.resize((IMG_SIZE_X, IMG_SIZE_Y))
# 转为灰度图片，这里彩色通道会滋扰效果，并且会加大盘算量
img = img.convert("L")
# 转为numpy数组
img = np.array(img)
# 由（30，30）转为（1，30，30）（即`channels_first`），固然你也能够转换为（30，30，1）（即`channels_last`）但为了以后预览处置惩罚后的图片轻易这里采用了（1，30，30）的花样寄存
img = np.reshape(img, (1, IMG_SIZE_X, IMG_SIZE_Y))
# 这里应用轮回生成labels数据，个中寄存的现实是class_names中对应元素的索引
labels.append([index])
# 添加到images中，末了一致处置惩罚
images.append(img)
# 轮回中一些状况的输出，能够去除
print("{} class: {} {} limit: {} {}"
.format(count, index + 1, class_names[index], limit, imagepath))
# 末了一次性将images和labels都转换成numpy数组
npy_data = np.array(images)
npy_labels = np.array(labels)
# 处置惩罚数据只须要一次，所以我们挑选在这里应用numpy自带的要领将处置惩罚以后的数据序列化存储
np.savez(data_path, x=npy_data, y=npy_labels)
print("Save images by npz")
else:
# 假如存在序列化号的数据，便直接读取，进步速率
npy_data = np.load(data_path)["x"]
npy_labels = np.load(data_path)["y"]
print("Load images by npz")
image_data = npy_data
labels_data = npy_labels
到了这里原始数据的加工预处置惩罚便已完成，只须要末了一步，就和demo中fashion_mnist.load_data()返回的效果一样了。代码以下：
# 末了一步就是将原始数据分红练习数据和测试数据
train_images, test_images, train_labels, test_labels = \
train_test_split(image_data, labels_data, test_size=0.2, random_state=6)
这里将相干信息打印的要领也附上：
print("_________________________________________________________________")
print("%-28s %-s" % ("Name", "Shape"))
print("=================================================================")
print("%-28s %-s" % ("Image Data", image_data.shape))
print("%-28s %-s" % ("Labels Data", labels_data.shape))
print("=================================================================")
print('Split train and test data,p=%')
print("_________________________________________________________________")
print("%-28s %-s" % ("Name", "Shape"))
print("=================================================================")
print("%-28s %-s" % ("Train Images", train_images.shape))
print("%-28s %-s" % ("Test Images", test_images.shape))
print("%-28s %-s" % ("Train Labels", train_labels.shape))
print("%-28s %-s" % ("Test Labels", test_labels.shape))
print("=================================================================")
以后别忘了归一化哟：
print("Normalize images")
train_images = train_images / 255.0
test_images = test_images / 255.0
末了附上读取自定义数据的完全代码：
import os
import keras
import matplotlib.pyplot as plt
from PIL import Image
from keras.layers import *
from keras.models import *
from keras.optimizers import Adam
from keras.preprocessing.image import ImageDataGenerator
from sklearn.model_selection import train_test_split
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
# 支撑中文
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来一般显现中文标签
plt.rcParams['axes.unicode_minus'] = False # 用来一般显现负号
re_load = False
re_build = False
# re_load = True
re_build = True
epochs = 50
batch_size = 5
count = 0
max_size = 2000000000
IMG_SIZE_X = 30
IMG_SIZE_Y = 30
np.random.seed(9277)
image_path = r'D:\Projects\ImageClassifier\data\set'
path = ".\data"
data_name = "data.npz"
data_path = os.path.join(path, data_name)
model_name = "model.h5"
model_path = os.path.join(path, model_name)
label_name = "labels.txt"
label_path = os.path.join(path, label_name)
class_names = np.loadtxt(label_path, type(""))
print('Load class names')
if not os.path.exists(data_path) or re_load:
labels = []
images = []
print('Handle images')
for index, name in enumerate(class_names):
classpath = os.path.join(image_path, name)
if not os.path.isdir(classpath):
continue
limit = 0
for image_name in os.listdir(classpath):
if limit >= max_size:
break
imagepath = os.path.join(classpath, image_name)
count = count + 1
limit = limit + 1
img = Image.open(imagepath)
img = img.resize((30, 30))
img = img.convert("L")
img = np.array(img)
img = np.reshape(img, (1, 30, 30))
# img = skimage.io.imread(imagepath, as_grey=True)
# if img.shape[2] != 3:
# print("{} shape is {}".format(image_name, img.shape))
# continue
# data = transform.resize(img, (IMG_SIZE_X, IMG_SIZE_Y))
labels.append([index])
images.append(img)
print("{} class: {} {} limit: {} {}"
.format(count, index + 1, class_names[index], limit, imagepath))
npy_data = np.array(images)
npy_labels = np.array(labels)
np.savez(data_path, x=npy_data, y=npy_labels)
print("Save images by npz")
else:
npy_data = np.load(data_path)["x"]
npy_labels = np.load(data_path)["y"]
print("Load images by npz")
image_data = npy_data
labels_data = npy_labels
print("_________________________________________________________________")
print("%-28s %-s" % ("Name", "Shape"))
print("=================================================================")
print("%-28s %-s" % ("Image Data", image_data.shape))
print("%-28s %-s" % ("Labels Data", labels_data.shape))
print("=================================================================")
train_images, test_images, train_labels, test_labels = \
train_test_split(image_data, labels_data, test_size=0.2, random_state=6)
print('Split train and test data,p=%')
print("_________________________________________________________________")
print("%-28s %-s" % ("Name", "Shape"))
print("=================================================================")
print("%-28s %-s" % ("Train Images", train_images.shape))
print("%-28s %-s" % ("Test Images", test_images.shape))
print("%-28s %-s" % ("Train Labels", train_labels.shape))
print("%-28s %-s" % ("Test Labels", test_labels.shape))
print("=================================================================")
# 归一化
# 我们将这些值缩小到 0 到 1 之间，然后将其馈送到神经网络模子。为此，将图象组件的数据类型从整数转换为浮点数，然后除以 255。以下是预处置惩罚图象的函数：
# 务必要以雷同的体式格局对练习集和测试集举行预处置惩罚：
print("Normalize images")
train_images = train_images / 255.0
test_images = test_images / 255.0
以上就是Tensorflow分类器项目自定义数据读入的要领引见（代码示例）的细致内容，更多请关注ki4网别的相干文章！
