Python read_image Examples

Example #1

import pylab
import tensorflow as tf
from mycode.mnist_all_minish_one_map_9_9 import functions as fs
from mycode.mnist_all_minish_one_map_9_9 import s0_parameter_all as p
from mycode.mnist_all_minish_one_map_9_9.conv_network_simulation import simulation_function as sfc

import matplotlib.image as mpimg

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

# 读取测试数据，并打乱顺序
test_path = "/home/lzs/Documents/my_image_net/mycode/mnist_all_minish_one_map_9_9/adversarial_train_data_test/"
# test_path = "/home/lzs/Documents/my_image_net/mycode/mnist_all_minish_one_map_9_9/adversarial_train_data_train/"

# 读取训练数据及测试数据
test_data, test_label = fs.read_image(test_path)

with tf.Session() as sess:
    # 载入已有模型
    saver = tf.train.import_meta_graph(p.file_base +
                                       'model_9_9/model.ckpt.meta')
    saver.restore(sess, p.file_base + 'model_9_9/model.ckpt')

    graph = tf.get_default_graph()

    x = graph.get_tensor_by_name("x:0")
    y_ = graph.get_tensor_by_name("y_:0")

    # fs.show_image_label(test_data[0], test_label[0])

    # 将输入数据填充进去

Example #2

File: ss3_adversarial_training.py Project: Lzsxx/Conv-Reluplex

import time
import tensorflow as tf
from mycode.mnist_all_minish_one_map_9_9 import functions as fs
from mycode.mnist_all_minish_one_map_9_9 import s0_parameter_all as p
import matplotlib.image as mpimg

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

#mnist数据集中训练数据和测试数据保存地址
train_path = '/home/lzs/Documents/my_image_net/mycode/mnist_all_minish_one_map_9_9/adversarial_train_data_train/'
test_path = "/home/lzs/Documents/my_image_net/mycode/mnist_all_minish_one_map_9_9/adversarial_train_data_test/"

test_original_path = '/home/lzs/Documents/my_image_net/mycode/data_set/mnist_data/test/'

# 读取训练数据及测试数据
train_data, train_label = fs.read_image(train_path)
test_data, test_label = fs.read_image(test_path)
test_original_data, test_original_label = fs.read_image(test_original_path)

# 打乱训练数据及测试数据
train_image_num = len(train_data)
train_image_index = np.arange(train_image_num)
np.random.shuffle(train_image_index)
train_data = train_data[train_image_index]
train_label = train_label[train_image_index]

test_image_num = len(test_data)
test_image_index = np.arange(test_image_num)
np.random.shuffle(test_image_index)
test_data = test_data[test_image_index]
test_label = test_label[test_image_index]