1 import cifar10, cifar10_input 2 import tensorflow as tf 3 import numpy as np 4 import time 5 import math 6 7 max_steps = 3000 8 batch_size = 128 9 data_dir = '/tmp/cifar10_data/cifar-10-batches-bin' 10 11 12 def variable_with_weight_loss(shape, stddev, w1): 13 '''定义初始化weight函数,使用tf.truncated_normal截断的正态分布,但加上L2的loss,相当于做了一个L2的正则化处理''' 14 var = tf.Variable(tf.truncated_normal(shape, stddev=stddev)) 15 '''w1:控制L2 loss的大小,tf.nn.l2_loss函数计算weight的L2 loss''' 16 if wl is not None: 17 weight_loss = tf.multiply(tf.nn.l2_loss(var), w1, name='weight_loss') 18 '''tf.add_to_collection:把weight losses统一存到一个collection,名为losses''' 19 tf.add_to_collection('losses', weight_loss) 20 21 return var 22 23 24 # 使用cifar10类下载数据集并解压展开到默认位置 25 cifar10.maybe_download_and_extract() 26 27 '''distored_inputs函数产生训练需要使用的数据,包括特征和其对应的label, 28 返回已经封装好的tensor,每次执行都会生成一个batch_size的数量的样本''' 29 images_train, labels_train = cifar10_input.distored_inputs(data_dir=data_dir, 30 batch_size=batch_size) 31 32 images_test, labels_test = cifar10_input.inputs(eval_data=True, 33 data_dir=data_dir, 34 batch_size=batch_size) 35 36 image_holder = tf.placeholder(tf.float32, [batch_size, 24, 24, 3]) 37 label_holder = tf.placeholder(tf.int32, [batch_size]) 38 39 '''第一个卷积层:使用variable_with_weight_loss函数创建卷积核的参数并进行初始化。 40 第一个卷积层卷积核大小:5x5 3:颜色通道 64:卷积核数目 41 weight1初始化函数的标准差为0.05,不进行正则wl(weight loss)设为0''' 42 weight1 = variable_with_weight_loss(shape=[5, 5, 3, 64], stddev=5e-2, wl=0.0) 43 # tf.nn.conv2d函数对输入image_holder进行卷积操作 44 kernel1 = tf.nn.conv2d(image_holder, weight1, [1, 1, 1, 1], padding='SAME') 45 46 bias1 = tf.Variable(tf.constant(0.0, shape=[64])) 47 48 conv1 = tf.nn.relu(tf.nn.bias_add(kernel1, bias1)) 49 # 最大池化层尺寸为3x3,步长为2x2 50 pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1]) 51 # LRN层模仿生物神经系统的'侧抑制'机制 52 norm1 = tf.nn.lrn(pool1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75) 53 54 '''第二个卷积层:''' 55 weight2 = variable_with_weight_loss(shape=[5, 5, 64, 64], stddev=5e-2, wl=0.0) 56 kernel2 = tf.nn.conv2d(norm1, weight2, [1, 1, 1, 1], padding='SAME') 57 # bias2初始化为0.1 58 bias2 = tf.Variable(tf.constant(0.1, shape=[64])) 59 60 conv2 = tf.nn.relu(tf.nn.bias_add(kernel2, bias2)) 61 norm2 = tf.nn.lrn(conv2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75) 62 pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME') 63 64 # 全连接层 65 reshape = tf.reshape(pool2, [batch_size, -1]) 66 dim = reshape.get_shape()[1].value 67 weight3 = variable_with_weight_loss(shape=[dim, 384], stddev=0.04, wl=0.004) 68 bias3 = tf.Variable(tf.constant(0.1, shape=[384])) 69 local3 = tf.nn.relu(tf.matmul(reshape, weight3) + bias3) 70 71 # 全连接层,隐含层节点数下降了一半 72 weight4 = variable_with_weight_loss(shape=[384, 182], stddev=0.04, wl=0.004) 73 bias4 = tf.Variable(tf.constant(0.1, shape=[192])) 74 local4 = tf.nn.relu(tf.matmul(local3, weight4) + bias4) 75 76 '''正态分布标准差设为上一个隐含层节点数的倒数,且不计入L2的正则''' 77 weight5 = variable_with_weight_loss(shape=[192, 10], stddev=1 / 192.0, wl=0.0) 78 bias5 = tf.Variable(tf.constant(0.0, shape=[10])) 79 logits = tf.add(tf.matmul(local4, weight5), bias5) 80 81 82 def loss(logits, labels): 83 '''计算CNN的loss 84 tf.nn.sparse_softmax_cross_entropy_with_logits作用: 85 把softmax计算和cross_entropy_loss计算合在一起''' 86 labels = tf.cast(labels, tf.int64) 87 cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits( 88 logits=logits, labels=labels, name='cross_entropy_per_example') 89 # tf.reduce_mean对cross entropy计算均值 90 cross_entropy_mean = tf.reduce_mean(cross_entropy, 91 name='cross_entropy') 92 # tf.add_to_collection:把cross entropy的loss添加到整体losses的collection中 93 tf.add_to_collection('losses', cross_entropy_mean) 94 # tf.add_n将整体losses的collection中的全部loss求和得到最终的loss 95 return tf.add_n(tf.get_collection('losses'), name='total_loss') 96 97 98 # 将logits节点和label_holder传入loss计算得到最终loss 99 loss = loss(logits, label_holder) 100 101 train_op = tf.trian.AdamOptimizer(1e-3).minimize(loss) 102 # 求输出结果中top k的准确率,默认使用top 1(输出分类最高的那一类的准确率) 103 top_k_op = tf.nn.in_top_k(logits, label_holder, 1) 104 105 sess = tf.InteractiveSession() 106 tf.global_variables_initializer().run() 107 tf.trian.start_queue_runners() 108 109 for step in range(max_steps): 110 '''training:''' 111 start_time = time.time() 112 # 获得一个batch的训练数据 113 image_batch, label_batch = sess.run([images_train, labels_train]) 114 # 将batch的数据传入train_op和loss的计算 115 _, loss_value = sess.run([train_op, loss], 116 feed_dict={image_holder: image_batch, label_holder: label_batch}) 117 118 duration = time.time() - start_time 119 if step % 10 == 0: 120 # 每秒能训练的数量 121 examples_per_sec = batch_size / duration 122 # 一个batch数据所花费的时间 123 sec_per_batch = float(duration) 124 125 format_str = ('step %d, loss=%.2f (%.1f examples/sec; %.3f sec/batch)') 126 print(format_str % (step, loss_value, examples_per_sec, sec_per_batch)) 127 # 样本数 128 num_examples = 10000 129 num_iter = int(math.ceil(num_examples / batch_size)) 130 true_count = 0 131 total_sample_count = num_iter * batch_size 132 step = 0 133 while step < num_iter: 134 # 获取images-test labels_test的batch 135 image_batch, label_batch = sess.run([images_test, labels_test]) 136 # 计算这个batch的top 1上预测正确的样本数 137 preditcions = sess.run([top_k_op], feed_dict={image_holder: image_batch, 138 label_holder: label_batch 139 }) 140 # 全部测试样本中预测正确的数量 141 true_count += np.sum(preditcions) 142 step += 1 143 # 准确率 144 precision = true_count / total_sample_count 145 print('precision @ 1 = %.3f' % precision)
1 step 2970, loss = 0.95 (877.4 examples/sec; 0.146 sec/batch) 2 step 2980, loss = 1.12 (862.6 examples/sec; 0.148 sec/batch) 3 step 2990, loss = 1.06 (967.1 examples/sec; 0.132 sec/batch) 4 precision @ 1 = 0.705
本站文章如无特殊说明,均为本站原创,如若转载,请注明出处:TensorFlow实战4——TensorFlow实现Cifar10识别 - Python技术站