深度学习之cifar-10②——二分类

import tensorflow as tf
import os
import pickle
import numpy as np

# 文件路径
CIFAR_DIR = "../../datas/cifar-10-batches-py"
print(os.listdir(CIFAR_DIR))

def load_data(filename):
    """从数据文件中读取数据"""
    with open(filename, 'rb') as f:
        data = pickle.load(f, encoding='bytes')
        return data[b'data'], data[b'labels']


# tensorflow.Dataset.
class CifarData:
    # 构造方法
    def __init__(self, filenames, need_shuffle):
        all_data = []
        all_labels = []
        for filename in filenames:
            data, labels = load_data(filename)
            for item, label in zip(data, labels):
                if label in [0, 1]:
                    all_data.append(item)
                    all_labels.append(label)
        self._data = np.vstack(all_data)
        self._data = self._data / 127.5 - 1         #数据【-1,1】化
        self._labels = np.hstack(all_labels)
        print(self._data.shape)
        print(self._labels.shape)

        self._num_examples = self._data.shape[0]
        self._need_shuffle = need_shuffle
        self._indicator = 0
        if self._need_shuffle:
            self._shuffle_data()

    # 随机洗牌
    def _shuffle_data(self):
        # [0,1,2,3,4,5] -> [5,3,2,4,0,1]
        p = np.random.permutation(self._num_examples)
        self._data = self._data[p]
        self._labels = self._labels[p]

    def next_batch(self, batch_size):
        # 将batch_size示例作为批返回
        end_indicator = self._indicator + batch_size
        if end_indicator > self._num_examples:
            if self._need_shuffle:
                self._shuffle_data()
                self._indicator = 0
                end_indicator = batch_size
            else:
                raise Exception("have no more examples")
        if end_indicator > self._num_examples:
            raise Exception("batch size is larger than all examples")
        batch_data = self._data[self._indicator: end_indicator]
        batch_labels = self._labels[self._indicator: end_indicator]
        self._indicator = end_indicator
        return batch_data, batch_labels

# 拼接路径
train_filenames = [os.path.join(CIFAR_DIR, 'data_batch_%d' % i) for i in range(1, 6)]
test_filenames = [os.path.join(CIFAR_DIR, 'test_batch')]

# 实例化对象
train_data = CifarData(train_filenames, True)
test_data = CifarData(test_filenames, False)

# model
x = tf.placeholder(tf.float32, [None, 3072])
# [None]
y = tf.placeholder(tf.int64, [None])

# (3072, 1)
w = tf.get_variable('w', [x.get_shape()[-1], 1],
                   initializer=tf.random_normal_initializer(0, 1))
# (1, )
b = tf.get_variable('b', [1],
                   initializer=tf.constant_initializer(0.0))

# [None, 3072] * [3072, 1] = [None, 1]
y_ = tf.matmul(x, w) + b

# [None, 1]
p_y_1 = tf.nn.sigmoid(y_)
# [None, 1]
y_reshaped = tf.reshape(y, (-1, 1))
y_reshaped_float = tf.cast(y_reshaped, tf.float32)
loss = tf.reduce_mean(tf.square(y_reshaped_float - p_y_1))
# loss = tf.reduce_mean(- y_reshaped_float * tf.log(p_y_1) - (1 - y_reshaped_float) * tf.log(1 - p_y_1))

# bool
predict = p_y_1 > 0.5
# [1,0,1,1,1,0,0,0]
correct_prediction = tf.equal(tf.cast(predict, tf.int64), y_reshaped)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float64))

with tf.name_scope('train_op'):
    train_op = tf.train.AdamOptimizer(1e-3).minimize(loss)

#trainning
init = tf.global_variables_initializer()
batch_size = 20
train_steps = 10000
test_steps = 100

with tf.Session() as sess:
    sess.run(init)
    for i in range(train_steps):
        batch_data, batch_labels = train_data.next_batch(batch_size)
        loss_val, acc_val, _ = sess.run([loss, accuracy, train_op],feed_dict={x: batch_data,y: batch_labels})
        if (i+1) % 500 == 0:
            print('[Train] Step: %d, loss: %4.5f, acc: %4.5f' % (i+1, loss_val, acc_val))
        if (i+1) % 5000 == 0:
            test_data = CifarData(test_filenames, False)
            all_test_acc_val = []
            for j in range(test_steps):
                test_batch_data, test_batch_labels \
                    = test_data.next_batch(batch_size)
                test_acc_val = sess.run(
                    [accuracy],
                    feed_dict = {
                        x: test_batch_data,
                        y: test_batch_labels
                    })
                all_test_acc_val.append(test_acc_val)
            test_acc = np.mean(all_test_acc_val)
            print('[Test ] Step: %d, acc: %4.5f' % (i+1, test_acc))

---

效果展示

['batches.meta', 'data_batch_1', 'data_batch_2', 'data_batch_3', 'data_batch_4', 'data_batch_5', 'readme.html', 'test_batch']
(10000, 3072)
(10000,)
(2000, 3072)
(2000,)

[Train] Step: 500, loss: 0.24983, acc: 0.75000
[Train] Step: 1000, loss: 0.29999, acc: 0.70000
[Train] Step: 1500, loss: 0.24381, acc: 0.75000
[Train] Step: 2000, loss: 0.06619, acc: 0.90000
[Train] Step: 2500, loss: 0.15084, acc: 0.85000
[Train] Step: 3000, loss: 0.24045, acc: 0.75000
[Train] Step: 3500, loss: 0.20078, acc: 0.80000
[Train] Step: 4000, loss: 0.10000, acc: 0.90000
[Train] Step: 4500, loss: 0.25345, acc: 0.75000
[Train] Step: 5000, loss: 0.26305, acc: 0.75000
(2000, 3072)
(2000,)
[Test ] Step: 5000, acc: 0.80550
[Train] Step: 5500, loss: 0.21956, acc: 0.75000
[Train] Step: 6000, loss: 0.19340, acc: 0.80000
[Train] Step: 6500, loss: 0.15935, acc: 0.85000
[Train] Step: 7000, loss: 0.15000, acc: 0.85000
[Train] Step: 7500, loss: 0.15005, acc: 0.85000
[Train] Step: 8000, loss: 0.14595, acc: 0.85000
[Train] Step: 8500, loss: 0.14996, acc: 0.85000
[Train] Step: 9000, loss: 0.24979, acc: 0.75000
[Train] Step: 9500, loss: 0.15000, acc: 0.85000
[Train] Step: 10000, loss: 0.39803, acc: 0.60000
(2000, 3072)
(2000,)
[Test ] Step: 10000, acc: 0.81100