自制数据集及应用
本次使用mnist的图片做一个自制的数据集,其中在文件夹中存放需要用到的数据,包含了训练的60000张28 * 28的图片,和测试的10000张28 * 28图片。每个图片对应的有自己的标签。
直接上代码:
import tensorflow as tf
from PIL import Image
import numpy as np
import os
train_path = './mnist_image_label/mnist_train_jpg_60000/' # 训练集图片路径
train_txt = './mnist_image_label/mnist_train_jpg_60000.txt' # 训练集标签文件
x_train_savepath = './mnist_image_label/mnist_x_train.npy' # 训练集输入特征存储文件
y_train_savepath = './mnist_image_label/mnist_y_train.npy' # 训练集标签存储文件
test_path = './mnist_image_label/mnist_test_jpg_10000/' # 测试集图片路径
test_txt = './mnist_image_label/mnist_test_jpg_10000.txt' # 测试集标签文件
x_test_savepath = './mnist_image_label/mnist_x_test.npy' # 测试集特征存储文件
y_test_savepath = './mnist_image_label/mnist_y_test.npy' # 测试集标签存储文件
# 函数功能:返回输入特征和标签
# 函数参数:输入图片的路径,和标签文件
def generateds(path, txt):
f = open(txt, 'r') # 以只读形式打开txt文件
contents = f.readlines() # 读取文件中所有行
f.close() # 关闭txt文件
x, y_ = [], [] # 建立空列表
for content in contents: # 逐行取出
value = content.split() # 以空格分开,图片路径为value[0] , 标签为value[1] , 存入列表
img_path = path + value[0] # 拼出图片路径和文件名得到索引路径
img = Image.open(img_path) # 读入图片
img = np.array(img.convert('L')) # 图片变为8位宽灰度值的np.array格式
img = img / 255. # 数据归一化 (实现预处理)
x.append(img) # 归一化后的数据,贴到列表x
y_.append(value[1]) # 标签贴到列表y_
print('loading : ' + content) # 打印状态提示
x = np.array(x) # 变为np.array格式
y_ = np.array(y_) # 变为np.array格式
y_ = y_.astype(np.int64) # 变为64位整型
return x, y_ # 返回输入特征x,返回标签y_
# 判断所需要用到的参数是否已经存在了,如果存在了直接读取,如果不存在调用刚才的函数制作数据集。
if os.path.exists(x_train_savepath) and os.path.exists(y_train_savepath) and os.path.exists(
x_test_savepath) and os.path.exists(y_test_savepath):
print('-------------Load Datasets-----------------')
x_train_save = np.load(x_train_savepath)
y_train = np.load(y_train_savepath)
x_test_save = np.load(x_test_savepath)
y_test = np.load(y_test_savepath)
x_train = np.reshape(x_train_save, (len(x_train_save), 28, 28))
x_test = np.reshape(x_test_save, (len(x_test_save), 28, 28))
else:
print('-------------Generate Datasets-----------------')
x_train, y_train = generateds(train_path, train_txt)
x_test, y_test = generateds(test_path, test_txt)
# 保存数据
print('-------------Save Datasets-----------------')
x_train_save = np.reshape(x_train, (len(x_train), -1))
x_test_save = np.reshape(x_test, (len(x_test), -1))
np.save(x_train_savepath, x_train_save)
np.save(y_train_savepath, y_train)
np.save(x_test_savepath, x_test_save)
np.save(y_test_savepath, y_test)
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dense(10, activation='softmax')
])
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
metrics=['sparse_categorical_accuracy'])
model.fit(x_train, y_train, batch_size=32, epochs=5, validation_data=(x_test, y_test), validation_freq=1)
model.summary()