tensorflow33《TensorFlow实战》笔记-06-01 TensorFlow实现AlexNet code

# 《TensorFlow实战》06 TensorFlow实现经典卷积神经网络# win10 Tensorflow1.0.1 python3.5.3# CUDA v8.0 cudnn-8.0-windows10-x64-v5.1# filename:sz06.01.py # TensorFlow实现AlexNet# 参考内容# https://github.com/tensorflow/models/blob/master/tutorials/image/alexnet/alexnet_benchmark.py# https://github.com/tensorflow/models.git# tensorflow_models\tutorials\image\alexnet\alexnet_benchmark.pyfrom 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 infrence(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 = infrence(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()'''conv1   [32, 56, 56, 64]pool1   [32, 27, 27, 64]conv2   [32, 27, 27, 192]pool2   [32, 13, 13, 192]conv3   [32, 13, 13, 384]conv4   [32, 13, 13, 256]conv5   [32, 13, 13, 256]pool5   [32, 6, 6, 256]2017-04-13 16:28:25.177867: step 0, duration = 0.0592017-04-13 16:28:25.769441: step 10, duration = 0.0592017-04-13 16:28:26.361012: step 20, duration = 0.0592017-04-13 16:28:26.951583: step 30, duration = 0.0592017-04-13 16:28:27.543156: step 40, duration = 0.0592017-04-13 16:28:28.131719: step 50, duration = 0.0592017-04-13 16:28:28.724311: step 60, duration = 0.0592017-04-13 16:28:29.314866: step 70, duration = 0.0592017-04-13 16:28:29.905437: step 80, duration = 0.0592017-04-13 16:28:30.496006: step 90, duration = 0.0592017-04-13 16:28:31.033435: Forward across 100 steps, 0.059 +/- 0.001 sec / batch2017-04-13 16:28:33.830872: step 0, duration = 0.2042017-04-13 16:28:35.877314: step 10, duration = 0.2032017-04-13 16:28:37.911570: step 20, duration = 0.2042017-04-13 16:28:39.954005: step 30, duration = 0.2052017-04-13 16:28:41.987445: step 40, duration = 0.2052017-04-13 16:28:44.026828: step 50, duration = 0.2032017-04-13 16:28:46.063242: step 60, duration = 0.2042017-04-13 16:28:48.103667: step 70, duration = 0.2042017-04-13 16:28:50.141083: step 80, duration = 0.2022017-04-13 16:28:52.172485: step 90, duration = 0.2032017-04-13 16:28:54.002348: Forward-backward across 100 steps, 0.204 +/- 0.001 sec / batch'''