import pickle
import numpy as np
import os
CIFAR_DIR = r'./data/cifar-10-batches-py'
print(os.listdir(CIFAR_DIR))
with open(os.path.join(CIFAR_DIR, 'data_batch_1'), 'rb') as f:
data = pickle.load(f,encoding='latin1')
print(type(data))
print(type(data['data']))
print(data['data'].shape)
image_arr = data['data'][100]
image_arr = image_arr.reshape((3,32,32)) # 32,32,33
image_arr = image_arr.transpose((1,2,0)) # numpy转换维度
import matplotlib.pyplot as plt
from matplotlib.pyplot import imshow
imshow(image_arr)
plt.show()
# tensorlow model
import tensorflow as tf
import os
import numpy as np
def load_data(filename):
""" read data from data file."""
with open(filename, 'rb') as f:
data = pickle.load(f,encoding='latin1')
return data['data'],data['labels']
class CifarData():
def __init__(self, filenames, need_shuffle):
all_data = []
all_labels = []
for filename in filenames:
data , labels = load_data(filename)
all_data.append(data)
all_labels.append(labels)
self._data = np.vstack(all_data)
self._data = self._data / 127.5 - 1
self._labels = np.hstack(all_labels)
self._num_examples = self._data.shape[0]
self._need_shuffle = need_shuffle
self._indicator = 0 # 当前数据集定位在什么位置上
if self._need_shuffle:
self._shuffle_data()
def _shuffle_data(self):
# [0,1,2,3,4,5] --> [5,3,2,4,0,1] 混排
p = np.random.permutation(self._num_examples)
self._data = self._data[p]
self._labels= self._labels[p]
def next_batch(self, batch_size):
""" return batch_size examples as a batch. """
end_indicator = self._indicator + batch_size # 其实位置加上 batch
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
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')]
train_data = CifarData(train_filenames,True)
batch_data, batch_labels = train_data.next_batch(10)
# #####################
# 二分类
# 占位符,数据来时把数据出入进去 32*32*3 = 3072
x = tf.placeholder(tf.float32, [None, 3072])
y = tf.placeholder(tf.int64, [None])
# (3072 * 10)
w = tf.get_variable('w', [x.get_shape()[-1], 10],
initializer = tf.random_normal_initializer(0,1))
# (1,)
b = tf.get_variable('b',[10],
initializer=tf.constant_initializer(0.0))
# (None, 3072) * (3072,10) = [None, 10]
# mean square loss
y_ = tf.matmul(x,w) +b
p_y = tf.nn.softmax(y_) # [0.1,0.2,0.01,0.3,.....]
# 5 --> [0,0,0,0,1,0,0,0,0,0]
y_one_hot = tf.one_hot(y,10,dtype=tf.float32)
loss = tf.reduce_mean(tf.square(y_one_hot - p_y))
"""
loss = tf.losses.aparse_softmax_cross_entropy(labels=y, logits=y_)
# y_ --> sofmax
# y --> one_hot
# loss = y log (y)
"""
"""
# [None, 1]
p_y_1 = tf.nn.sigmoid(y_) # 得到概率值
y_reshaped = tf.reshape(y, (-1,1))
y_reshaped_float = tf.cast(y_reshaped, tf.float32)
#平方差
loss = tf.reduce_mean(tf.square(y_reshaped_float - p_y_1))
"""
# predict = p_y_1 > 0.5
# 判断预测中的正确个数
predict = tf.argmax(y_, 1)
correct_prediction = tf.equal(tf.cast(predict,tf.float32),y_)
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)
# 初始化各个变量
init = tf.global_variables_initializer()
batch_size = 20
train_steps = 10000
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, loss_val, acc_val))
if (i+1) % 5000 ==0:
test_data = CifarData(test_filenames, False)
all_test_acc_val = []
for j in ragne(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: %4.5' %(i, test_acc))