def inputs(eval_data, inner_data_dir, batch_size=FLAGS.batch_size):
"""Construct input for CIFAR evaluation using the Reader ops.
Args:
eval_data: bool, indicating if one should use the train or eval data set.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
Raises:
ValueError: If no data_dir
"""
# if not FLAGS.data_dir:
# raise ValueError('Please supply a data_dir')
# data_dir = os.path.join(FLAGS.data_dir, inner_data_dir)
images, labels = cifar10_input.inputs(eval_data=eval_data,
data_dir=inner_data_dir,
batch_size=batch_size)
# print('images shape:',images.shape,'labels shape:',labels.shape)
if FLAGS.use_fp16:
images = tf.cast(images, tf.float16)
labels = tf.cast(labels, tf.float16)
return images, labels
def inputs(eval_data):
if not FLAGS.data_dir:
raise ValueError('Please supply a data_dir')
data_dir = os.path.join(FLAGS.data_dir, 'cifar-10-batches-bin')
images, labels = cifar10_input.inputs(eval_data, data_dir,
FLAGS.batch_size)
if FLAGS.use_fp16:
images = tf.cast(images, tf.float16)
labels = tf.cast(labels, tf.float16)
return images, labels
def inputs(eval_data):
"""Construct input for CIFAR evaluation using the Reader ops.
Args:
eval_data: bool, indicating if one should use the train or eval data set.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
"""
images, labels = cifar10_input.inputs(eval_data=eval_data,
batch_size=FLAGS.batch_size)
if FLAGS.use_fp16:
images = tf.cast(images, tf.float16)
labels = tf.cast(labels, tf.float16)
return images, labels
'''
1.cnn + maxpool
2.cnn + maxpool
3.cnn + avgpool
4.softmax + crossentropy
5.在卷积后添加Batch Normalization
'''
from cifar10 import cifar10_input
import tensorflow as tf
import numpy as np
from tensorflow.contrib.layers.python.layers import batch_norm
# get data
batch_size = 128
data_dir = "./cifar10"
images_train, labels_train = cifar10_input.inputs(eval_data=False,
batch_size=batch_size)
images_test, labels_test = cifar10_input.inputs(eval_data=True,
batch_size=batch_size)
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
tf.train.start_queue_runners()
image_batch, label_batch = sess.run([images_test, labels_test])
# print(image_batch[0])
# print(label_batch[0])
# pylab.imshow(image_batch[0])
# pylab.show()
def weight_variable(shape):
from cifar10 import cifar10_input, cifar10
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
batch_size = 100
# data_dir='D:\\学习笔记\\ai\\dataSets\\cifar10\\cifar-10-binary.tar'
data_dir = 'D:\\学习笔记\\ai\\dataSets\\cifar10\\cifar-10-batches-bin'
# data_dir='D:\\学习笔记\\ai\\dataSets\\cifar10'
cifar10.maybe_download_and_extract()
images_train, label_train = cifar10_input.distorted_inputs(
data_dir=data_dir, batch_size=batch_size)
images_test, label_test = cifar10_input.inputs(eval_data=True,
data_dir=data_dir,
batch_size=batch_size)
X = tf.placeholder(shape=images_train.get_shape(), dtype=tf.float32)
y = tf.placeholder(shape=label_train.get_shape(), dtype=tf.int32)
w_cnn = tf.Variable(tf.truncated_normal(shape=(4, 4, 3, 24), stddev=0.1))
b_cnn = tf.Variable(tf.ones(shape=24))
cnn = tf.nn.conv2d(X, w_cnn, strides=(1, 1, 1, 1), padding='SAME', name='cnn')
cnn = tf.reshape(cnn, shape=(batch_size, -1))
cnn_shape = cnn.get_shape()
relu_cnn = tf.nn.relu(cnn)
print('cnn shape', cnn_shape)
w_fc = tf.Variable(tf.truncated_normal(shape=(13824, 10), stddev=0.1))
b_fc = tf.Variable(tf.ones(shape=10))
fc = tf.matmul(relu_cnn, w_fc) + b_fc
var = tf.Variable(tf.truncated_normal(shape, stddev=stddev))
if w1 is not None:
weight_loss = tf.multiply(tf.nn.l2_loss(var), w1, name='weight_loss')
tf.add_to_collection('losses', weight_loss)
return var
maybe_download_and_extract() # 下载解压数据
# 使用distorted_inputs 产生训练需要的数据，包括特征及其对应的label, 该方法做了数据增强
images_train, labels_train = distorted_inputs(data_dir=data_dir,
batch_size=batch_size)
# cifar10_input.inputs() 生成测试数据
image_test, labels_test = inputs(eval_data=True,
data_dir=data_dir,
batch_size=batch_size)
image_holder = tf.placeholder(tf.float32,
[batch_size, 24, 24, 3]) # 3表示有RGB三种通道
label_holder = tf.placeholder(tf.int32, [batch_size])
# 创建卷积层，注意LRN的理解
# 使用 5x5的卷积核大小，3个颜色通道，64个卷积核
# ==============
# 卷积层对数据进行特征提取， 全连接层进行组合匹配
weight1 = variable_with_weight_loss(shape=[5, 5, 3, 64], stddev=5e-2, w1=0.0)
kernel1 = tf.nn.conv2d(image_holder, weight1, [1, 1, 1, 1], padding='SAME')
bias1 = tf.Variable(tf.constant(0.0, shape=[64]))
conv1 = tf.nn.relu(tf.nn.bias_add(kernel1, bias1))
