本文實例為大家分享了Tensorflow實現AlexNet卷積神經網絡的具體實現代碼，供大家參考，具體內容如下
之前已經介紹過了AlexNet的網絡構建了，這次主要不是為了訓練數據，而是為了對每個batch的前饋（Forward）和反饋（backward）的平均耗時進行計算。在設計網絡的過程中，分類的結果很重要，但是運算速率也相當重要。尤其是在跟蹤（Tracking）的任務中，如果使用的網絡太深，那么也會導致實時性不好。
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
|
from datetime import datetimeimport mathimport timeimport tensorflow as tfbatch_size = 32num_batches = 100def print_activations(t): print(t.op.name, '', t.get_shape().as_list())def inference(images): parameters = [] with tf.name_scope('conv1') as scope: kernel = tf.Variable(tf.truncated_normal([11, 11, 3, 64], dtype = tf.float32, stddev = 1e-1), name = 'weights') conv = tf.nn.conv2d(images, kernel, [1, 4, 4, 1], padding = 'SAME') biases = tf.Variable(tf.constant(0.0, shape = [64], dtype = tf.float32), trainable = True, name = 'biases') bias = tf.nn.bias_add(conv, biases) conv1 = tf.nn.relu(bias, name = scope) print_activations(conv1) parameters += [kernel, biases] lrn1 = tf.nn.lrn(conv1, 4, bias = 1.0, alpha = 0.001 / 9, beta = 0.75, name = 'lrn1') pool1 = tf.nn.max_pool(lrn1, ksize = [1, 3, 3, 1], strides = [1, 2, 2, 1], padding = 'VALID', name = 'pool1') print_activations(pool1) with tf.name_scope('conv2') as scope: kernel = tf.Variable(tf.truncated_normal([5, 5, 64, 192], dtype = tf.float32, stddev = 1e-1), name = 'weights') conv = tf.nn.conv2d(pool1, kernel, [1, 1, 1, 1], padding = 'SAME') biases = tf.Variable(tf.constant(0.0, shape = [192], dtype = tf.float32), trainable = True, name = 'biases') bias = tf.nn.bias_add(conv, biases) conv2 = tf.nn.relu(bias, name = scope) parameters += [kernel, biases] print_activations(conv2) lrn2 = tf.nn.lrn(conv2, 4, bias = 1.0, alpha = 0.001 / 9, beta = 0.75, name = 'lrn2') pool2 = tf.nn.max_pool(lrn2, ksize = [1, 3, 3, 1], strides = [1, 2, 2, 1], padding = 'VALID', name = 'pool2') print_activations(pool2) with tf.name_scope('conv3') as scope: kernel = tf.Variable(tf.truncated_normal([3, 3, 192, 384], dtype = tf.float32, stddev = 1e-1), name = 'weights') conv = tf.nn.conv2d(pool2, kernel, [1, 1, 1, 1], padding = 'SAME') biases = tf.Variable(tf.constant(0.0, shape = [384], dtype = tf.float32), trainable = True, name = 'biases') bias = tf.nn.bias_add(conv, biases) conv3 = tf.nn.relu(bias, name = scope) parameters += [kernel, biases] print_activations(conv3) with tf.name_scope('conv4') as scope: kernel = tf.Variable(tf.truncated_normal([3, 3, 384, 256], dtype = tf.float32, stddev = 1e-1), name = 'weights') conv = tf.nn.conv2d(conv3, kernel, [1, 1, 1, 1], padding = 'SAME') biases = tf.Variable(tf.constant(0.0, shape = [256], dtype = tf.float32), trainable = True, name = 'biases') bias = tf.nn.bias_add(conv, biases) conv4 = tf.nn.relu(bias, name = scope) parameters += [kernel, biases] print_activations(conv4) with tf.name_scope('conv5') as scope: kernel = tf.Variable(tf.truncated_normal([3, 3, 256, 256], dtype = tf.float32, stddev = 1e-1), name = 'weights') conv = tf.nn.conv2d(conv4, kernel, [1, 1, 1, 1], padding = 'SAME') biases = tf.Variable(tf.constant(0.0, shape = [256], dtype = tf.float32), trainable = True, name = 'biases') bias = tf.nn.bias_add(conv, biases) conv5 = tf.nn.relu(bias, name = scope) parameters += [kernel, biases] print_activations(conv5) pool5 = tf.nn.max_pool(conv5, ksize = [1, 3, 3, 1], strides = [1, 2, 2, 1], padding = 'VALID', name = 'pool5') print_activations(pool5) return pool5, parametersdef time_tensorflow_run(session, target, info_string): num_steps_burn_in = 10 total_duration = 0.0 total_duration_squared = 0.0 for i in range(num_batches + num_steps_burn_in): start_time = time.time() _ = session.run(target) duration = time.time() - start_time if i >= num_steps_burn_in: if not i % 10: print('%s: step %d, duration = %.3f' %(datetime.now(), i - num_steps_burn_in, duration)) total_duration += duration total_duration_squared += duration * duration mn = total_duration / num_batches vr = total_duration_squared / num_batches - mn * mn sd = math.sqrt(vr) print('%s: %s across %d steps, %.3f +/- %.3f sec / batch' %(datetime.now(), info_string, num_batches, mn, sd))def run_benchmark(): with tf.Graph().as_default(): image_size = 224 images = tf.Variable(tf.random_normal([batch_size, image_size, image_size, 3], dtype = tf.float32, stddev = 1e-1)) pool5, parameters = inference(images) init = tf.global_variables_initializer() sess = tf.Session() sess.run(init) time_tensorflow_run(sess, pool5, "Forward") objective = tf.nn.l2_loss(pool5) grad = tf.gradients(objective, parameters) time_tensorflow_run(sess, grad, "Forward-backward")run_benchmark() |
這里的代碼都是之前講過的，只是加了一個計算時間和現實網絡的卷積核的函數，應該很容易就看懂了，就不多贅述了。我在GTX TITAN X上前饋大概需要0.024s, 反饋大概需要0.079s。哈哈，自己動手試一試哦。
以上就是本文的全部內容，希望對大家的學習有所幫助，也希望大家多多支持服務器之家。
原文鏈接：https://blog.csdn.net/Felaim/article/details/68923725
