tensorflow34《TensorFlow实战》笔记-06-02 TensorFlow实现VGGNet code
来源:互联网 发布:淘宝千牛店铺名怎么改 编辑:程序博客网 时间:2024/06/05 20:47
# 《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:sz06.02.py # TensorFlow实现VGGNet# 参考 https://github.com/machrisaa/tensorflow-vggfrom datetime import datetimeimport mathimport timeimport tensorflow as tfdef conv_op(input_op, name, kh, kw, n_out, dh, dw, p): n_in = input_op.get_shape()[-1].value with tf.name_scope(name) as scope: kernel = tf.get_variable(scope + "w", shape = [kh, kw, n_in, n_out], dtype=tf.float32, initializer = tf.contrib.layers.xavier_initializer_conv2d()) conv = tf.nn.conv2d(input_op, kernel, (1, dh, dw, 1), padding='SAME') bias_init_val = tf.constant(0.0, shape=[n_out], dtype=tf.float32) biases = tf.Variable(bias_init_val, trainable=True, name='b') z = tf.nn.bias_add(conv, biases) activation = tf.nn.relu(z, name=scope) p += [kernel, biases] return activationdef fc_op(input_op, name, n_out, p): n_in = input_op.get_shape()[-1].value with tf.name_scope(name) as scope: kernel = tf.get_variable(scope + "w", shape=[n_in, n_out], dtype=tf.float32, initializer=tf.contrib.layers.xavier_initializer()) biases = tf.Variable(tf.constant(0.1, shape=[n_out], dtype=tf.float32), name='b') activation = tf.nn.relu_layer(input_op, kernel, biases, name=scope) p += [kernel, biases] return activationdef mpool_op(input_op, name, kh, kw, dh, dw): return tf.nn.max_pool(input_op, ksize=[1, kh, kw, 1], strides=[1, dh, dw, 1], padding='SAME', name=name)def inference_op(input_op, keep_prob): p = [] conv1_1 = conv_op(input_op, name="conv1_1", kh=3, kw=3, n_out=64, dh=1, dw=1, p=p) conv1_2 = conv_op(conv1_1, name="conv1_2", kh=3, kw=3, n_out=64, dh=1, dw=1, p=p) pool1 = mpool_op(conv1_2, name="pool1", kh=2, kw=2, dh=2, dw=2) conv2_1 = conv_op(pool1, name="conv2_1", kh=3, kw=3, n_out=128, dh=1, dw=1, p=p) conv2_2 = conv_op(conv2_1, name="conv2_2", kh=3, kw=3, n_out=128, dh=1, dw=1, p=p) pool2 = mpool_op(conv2_2, name="pool2", kh=2, kw=2, dh=2, dw=2) conv3_1 = conv_op(pool2, name="conv3_1", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p) conv3_2 = conv_op(conv3_1, name="conv3_2", kh=3, kw=3, n_out=256, dh=1, dw=1, p=p) conv3_3 = conv_op(conv3_2, name="conv3_3", kh=3, kw=3, n_out=256, dh=1,dw=1, p=p) pool3 = mpool_op(conv3_3, name="pool3", kh=2, kw=2, dh=2, dw=2) conv4_1 = conv_op(pool3, name="conv4_1", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p) conv4_2 = conv_op(conv4_1, name="conv4_2", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p) conv4_3 = conv_op(conv4_2, name="conv4_3", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p) pool4 = mpool_op(conv4_3, name="pool4", kh=2, kw=2, dh=2, dw=2) conv5_1 = conv_op(pool4, name="conv5_1", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p) conv5_2 = conv_op(conv5_1, name="conv5_2", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p) conv5_3 = conv_op(conv5_2, name="conv5_3", kh=3, kw=3, n_out=512, dh=1, dw=1, p=p) pool5 = mpool_op(conv5_3, name="pool5", kh=2, kw=2, dh=2, dw=2) shp = pool5.get_shape() flattened_shape = shp[1].value * shp[2].value * shp[3].value resh1 = tf.reshape(pool5, [-1, flattened_shape], name="resh1") fc6 = fc_op(resh1, name="fc6", n_out=4096, p=p) fc6_drop = tf.nn.dropout(fc6, keep_prob, name="fc6_drop") fc7 = fc_op(fc6_drop, name="fc7", n_out=4096, p=p) fc7_drop = tf.nn.dropout(fc7, keep_prob, name="fc7_drop") fc8 = fc_op(fc7_drop, name="fc8", n_out=1000, p=p) softmax = tf.nn.softmax(fc8) predictions = tf.argmax(softmax, 1) return predictions, softmax, fc8, pdef time_tensorflow_run(session, target, feed, 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, feed_dict=feed) 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(): images_size = 224 images = tf.Variable(tf.random_normal([batch_size, images_size, images_size, 3], dtype = tf.float32, stddev = 1e-1)) keep_prob = tf.placeholder(tf.float32) predictions, softmax, fc8, p = inference_op(images, keep_prob) init = tf.global_variables_initializer() sess = tf.Session() sess.run(init) time_tensorflow_run(sess, predictions, {keep_prob: 1.0}, "Forward") objective = tf.nn.l2_loss(fc8) grad = tf.gradients(objective, p) time_tensorflow_run(sess, grad, {keep_prob: 0.5}, "Forward-backward")batch_size = 32num_batches = 100run_benchmark()'''2017-04-13 20:46:38.301421: step 0, duration = 0.8762017-04-13 20:46:47.062714: step 10, duration = 0.8762017-04-13 20:46:55.825010: step 20, duration = 0.8762017-04-13 20:47:04.586824: step 30, duration = 0.8762017-04-13 20:47:13.350110: step 40, duration = 0.8762017-04-13 20:47:22.112488: step 50, duration = 0.8762017-04-13 20:47:30.879796: step 60, duration = 0.8762017-04-13 20:47:39.645100: step 70, duration = 0.8772017-04-13 20:47:48.409402: step 80, duration = 0.8762017-04-13 20:47:57.172700: step 90, duration = 0.8762017-04-13 20:48:05.061676: Forward across 100 steps, 0.876 +/- 0.000 sec / batch2017-04-13 20:48:48.393882: step 0, duration = 3.4342017-04-13 20:49:22.706495: step 10, duration = 3.4122017-04-13 20:49:57.018747: step 20, duration = 3.4322017-04-13 20:50:31.359640: step 30, duration = 3.4272017-04-13 20:51:05.571630: step 40, duration = 3.4192017-04-13 20:51:39.908891: step 50, duration = 3.4592017-04-13 20:52:14.316013: step 60, duration = 3.4232017-04-13 20:52:48.706655: step 70, duration = 3.4282017-04-13 20:53:23.171285: step 80, duration = 3.4552017-04-13 20:53:57.729194: step 90, duration = 3.4602017-04-13 20:54:28.629420: Forward-backward across 100 steps, 3.437 +/- 0.020 sec / batch'''
0 1
- tensorflow34《TensorFlow实战》笔记-06-02 TensorFlow实现VGGNet code
- tensorflow33《TensorFlow实战》笔记-06-01 TensorFlow实现AlexNet code
- tensorflow35《TensorFlow实战》笔记-06-03 TensorFlow实现 GoogleInceptionV3 code
- tensorflow36《TensorFlow实战》笔记-06-04 TensorFlow实现 ResNet code
- 【深度学习】VGGNet的tensorflow实现code
- Tensorflow实战学习(三十一)【实现VGGNet】
- Tensorflow实现VGGNet
- Tensorflow实现VGGNet
- tensorflow32《TensorFlow实战》笔记-05 TensorFlow实现卷积神经网络 code
- tensorflow37《TensorFlow实战》笔记-07-01 TensorFlow实现Word2Vec code
- Tensorflow实战8:VGGNet实现及时间测评
- tensorflow38《TensorFlow实战》笔记-07-02 TensorFlow实现基于LSTM的语言模型 code
- tensorflow41《TensorFlow实战》笔记-08-02 TensorFlow实现深度强化学习-估值网络 code
- VGGNet原理及Tensorflow实现
- tensorflow31《TensorFlow实战》笔记-04 TensorFlow实现自编码器及多层感知机 code
- tensorflow39《TensorFlow实战》笔记-07-03 TensorFlow实现Bidirectional LSTM Classifier code
- tensorflow40《TensorFlow实战》笔记-08-01 TensorFlow实现深度强化学习-策略网络 code
- tensorflow30《TensorFlow实战》笔记-03 TensorFlow第一步 code
- jQuery检查DOM元素是否绑定某些事件
- strspn()函数
- TLD算法
- POJ
- 重温HTML
- tensorflow34《TensorFlow实战》笔记-06-02 TensorFlow实现VGGNet code
- java getParameter方法
- 44. Wildcard Matching
- Linux安装redis时报gcc:未找到命令错误
- C++求“四位水仙花数”
- 背包六问
- 【Java基础知识】IO流 详解
- 并查集(模板&典型例题整理)
- UML类图中箭头和线条的含义和用法