存储图和训练好的权重
来源:互联网 发布:天猫淘宝白菜群 编辑:程序博客网 时间:2024/06/04 22:40
(1)tensorflow存储图和训练好的权重
from __future__ import absolute_import, unicode_literalsimport input_dataimport tensorflow as tfimport shutilimport os.pathexport_dir = './tmp/expert-export'if os.path.exists(export_dir): shutil.rmtree(export_dir)def weight_variable(shape): initial = tf.truncated_normal(shape, stddev=0.1) return tf.Variable(initial)def bias_variable(shape): initial = tf.constant(0.1, shape=shape) return tf.Variable(initial)def conv2d(x, W): return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')def max_pool_2x2(x): return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')mnist = input_data.read_data_sets("./tmp/data/", one_hot=True)g = tf.Graph()with g.as_default(): x = tf.placeholder("float", shape=[None, 784]) y_ = tf.placeholder("float", shape=[None, 10]) W_conv1 = weight_variable([5, 5, 1, 32]) b_conv1 = bias_variable([32]) x_image = tf.reshape(x, [-1, 28, 28, 1]) h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1) h_pool1 = max_pool_2x2(h_conv1) W_conv2 = weight_variable([5, 5, 32, 64]) b_conv2 = bias_variable([64]) h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2) h_pool2 = max_pool_2x2(h_conv2) W_fc1 = weight_variable([7 * 7 * 64, 1024]) b_fc1 = bias_variable([1024]) h_pool2_flat = tf.reshape(h_pool2, [-1, 7 * 7 * 64]) h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1) keep_prob = tf.placeholder("float") h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) W_fc2 = weight_variable([1024, 10]) b_fc2 = bias_variable([10]) y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv)) train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy) correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) sess = tf.Session() sess.run(tf.initialize_all_variables()) for i in range(201): batch = mnist.train.next_batch(50) if i % 100 == 0: train_accuracy = accuracy.eval( {x: batch[0], y_: batch[1], keep_prob: 1.0}, sess) print "step %d, training accuracy %g" % (i, train_accuracy) train_step.run( {x: batch[0], y_: batch[1], keep_prob: 0.5}, sess) print "test accuracy %g" % accuracy.eval( {x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}, sess)# Store variable_W_conv1 = W_conv1.eval(sess)_b_conv1 = b_conv1.eval(sess)_W_conv2 = W_conv2.eval(sess)_b_conv2 = b_conv2.eval(sess)_W_fc1 = W_fc1.eval(sess)_b_fc1 = b_fc1.eval(sess)_W_fc2 = W_fc2.eval(sess)_b_fc2 = b_fc2.eval(sess)sess.close()# Create new graph for exportingg_2 = tf.Graph()with g_2.as_default(): x_2 = tf.placeholder("float", shape=[None, 784], name="input") W_conv1_2 = tf.constant(_W_conv1, name="constant_W_conv1") b_conv1_2 = tf.constant(_b_conv1, name="constant_b_conv1") x_image_2 = tf.reshape(x_2, [-1, 28, 28, 1]) h_conv1_2 = tf.nn.relu(conv2d(x_image_2, W_conv1_2) + b_conv1_2) h_pool1_2 = max_pool_2x2(h_conv1_2) W_conv2_2 = tf.constant(_W_conv2, name="constant_W_conv2") b_conv2_2 = tf.constant(_b_conv2, name="constant_b_conv2") h_conv2_2 = tf.nn.relu(conv2d(h_pool1_2, W_conv2_2) + b_conv2_2) h_pool2_2 = max_pool_2x2(h_conv2_2) W_fc1_2 = tf.constant(_W_fc1, name="constant_W_fc1") b_fc1_2 = tf.constant(_b_fc1, name="constant_b_fc1") h_pool2_flat_2 = tf.reshape(h_pool2_2, [-1, 7 * 7 * 64]) h_fc1_2 = tf.nn.relu(tf.matmul(h_pool2_flat_2, W_fc1_2) + b_fc1_2) W_fc2_2 = tf.constant(_W_fc2, name="constant_W_fc2") b_fc2_2 = tf.constant(_b_fc2, name="constant_b_fc2") # DropOut is skipped for exported graph. y_conv_2 = tf.nn.softmax(tf.matmul(h_fc1_2, W_fc2_2) + b_fc2_2, name="output") sess_2 = tf.Session() init_2 = tf.initialize_all_variables(); sess_2.run(init_2) graph_def = g_2.as_graph_def() tf.train.write_graph(graph_def, export_dir, 'expert-graph.pb', as_text=False) # Test trained model y__2 = tf.placeholder("float", [None, 10]) correct_prediction_2 = tf.equal(tf.argmax(y_conv_2, 1), tf.argmax(y__2, 1)) accuracy_2 = tf.reduce_mean(tf.cast(correct_prediction_2, "float")) print "check accuracy %g" % accuracy_2.eval( {x_2: mnist.test.images, y__2: mnist.test.labels}, sess_2)运行结果/usr/bin/python2.7 /home/acer/PycharmProjects/trainer-script-minist/expert.pyExtracting ./tmp/data/train-images-idx3-ubyte.gzExtracting ./tmp/data/train-labels-idx1-ubyte.gzExtracting ./tmp/data/t10k-images-idx3-ubyte.gzExtracting ./tmp/data/t10k-labels-idx1-ubyte.gzstep 0, training accuracy 0.1step 100, training accuracy 0.84step 200, training accuracy 0.94test accuracy 0.8998check accuracy 0.8998Process finished with exit code 0
读取存储的.pb并使用
#encoding:uft-8#读取存储的图,可运行from __future__ import absolute_import, unicode_literalsimport input_dataimport tensorflow as tfimport shutilimport os.pathmnist = input_data.read_data_sets("./tmp/data/", one_hot=True)# produces the expected result.x_2 = tf.placeholder("float", shape=[None, 784], name="input")y__2 = tf.placeholder("float", [None, 10])with tf.Graph().as_default(): output_graph_def = tf.GraphDef() output_graph_path = './tmp/expert-export/expert-graph.pb' #sess.graph.add_to_collection("input", mnist.test.images) with open(output_graph_path, "rb") as f: output_graph_def.ParseFromString(f.read()) _ = tf.import_graph_def(output_graph_def, name="") with tf.Session() as sess: tf.initialize_all_variables().run() input_x = sess.graph.get_tensor_by_name("input:0") print input_x output = sess.graph.get_tensor_by_name("output:0") print output y_conv_2 = sess.run(output,{input_x:mnist.test.images}) print "y_conv_2", y_conv_2 # Test trained model #y__2 = tf.placeholder("float", [None, 10]) y__2 = mnist.test.labels; correct_prediction_2 = tf.equal(tf.argmax(y_conv_2, 1), tf.argmax(y__2, 1)) print "correct_prediction_2", correct_prediction_2 accuracy_2 = tf.reduce_mean(tf.cast(correct_prediction_2, "float")) print "accuracy_2", accuracy_2 print "check accuracy %g" % accuracy_2.eval()运行结果:/usr/bin/python2.7 /home/acer/PycharmProjects/trainer-script-minist/testexpert.py
Extracting ./tmp/data/train-images-idx3-ubyte.gz
Extracting ./tmp/data/train-labels-idx1-ubyte.gz
Extracting ./tmp/data/t10k-images-idx3-ubyte.gz
Extracting ./tmp/data/t10k-labels-idx1-ubyte.gz
Tensor("input:0", dtype=float32)
Tensor("output:0", shape=(?, 10), dtype=float32)
y_conv_2 [[ 1.37317020e-05 2.21044629e-05 7.19948293e-05 ..., 9.98878419e-01
2.16295721e-05 5.87339920e-04]
[ 5.59040019e-03 1.49921319e-02 7.76712596e-01 ..., 2.77250329e-05
7.95767531e-02 1.50265405e-04]
[ 1.17397300e-04 9.85014021e-01 5.27875684e-03 ..., 1.45449198e-03
2.34977412e-03 2.11255602e-03]
...,
[ 1.45151716e-04 4.11947171e-04 1.44378588e-04 ..., 1.72489304e-02
7.79939666e-02 1.54636368e-01]
[ 6.98981108e-03 1.21029736e-02 1.06854215e-02 ..., 1.07497610e-02
3.34680617e-01 1.42563693e-02]
[ 8.54243699e-04 7.11486928e-06 4.57449147e-04 ..., 3.66224917e-08
3.96781206e-06 8.27823987e-06]]
correct_prediction_2 Tensor("Equal:0", shape=(10000,), dtype=bool)
accuracy_2 Tensor("Mean:0", shape=(), dtype=float32)
check accuracy 0.899
阅读全文
0 0
- 存储图和训练好的权重
- tensorflow存储图和训练的权重为.pb,然后读取.pb并使用
- tensorflow训练权重的保存和读取
- tensorflow将训练好的模型freeze,即将权重固化到图里面,并使用该模型进行预测
- tensorflow将训练好的模型freeze,即将权重固化到图里面,并使用该模型进行预测
- tensorflow将训练好的模型freeze,即将权重固化到图里面,并使用该模型进行预测
- tensorflow将训练好的模型freeze,即将权重固化到图里面,并使用该模型进行预测
- 使用libsvm得到训练出的权重和偏差
- 使用libsvm得到训练出的权重和偏差
- caffe调用之前的权重和接着断点继续训练
- tensorflow从已经训练好的模型中,恢复(指定)权重(构建新变量、网络)并继续训练(finetuning)
- tensorflow将训练好的模型freeze,即将权重固化到图里面,并使用该模型进行预测(tf.graph_util.convert_variables_to_constants函数)
- CNN的权重更新方法-训练过程
- 计算汉明权重的好方法~
- tensorflow1.1/保存和提取训练好的参数
- TensorFlow 训练好模型参数的保存和恢复代码
- 将tf训练的权重保存为CKPT,PB ,CKPT 转换成 PB格式。并将权重固化到图里面,并使用该模型进行预测
- tensorflow在训练的时候权重是nan,如何解决
- mysql获取前一天|前一月|前一年(开始结束时间)
- 日常做一题:随机分组
- jqgrid saveRow方法报错 Cannot read property 'multiple' of undefined的原因
- C# MFC项目实录
- java判断数字类型(小数和整数)
- 存储图和训练好的权重
- 7---LeetCode【tag: Array】【Stock I】|C语言|总结
- 隐藏系统返回按钮,保留系统滑动返回
- 前端初学学习进程V
- KINECT2.0开发实践_1:简单介绍
- 指定TreeNode排序
- Java NIO
- 拆红包特效
- 调用一个脚本