TensorFlow基础笔记(14) 网络模型的保存与恢复_mnist数据实例
http://blog.csdn.net/huachao1001/article/details/78502910
http://blog.csdn.net/u014432647/article/details/75276718
https://zhuanlan.zhihu.com/p/32887066
#coding:utf-8 #http://blog.csdn.net/zhuiqiuk/article/details/53376283 #http://blog.csdn.net/gan_player/article/details/77586489 from __future__ import absolute_import, unicode_literals from tensorflow.examples.tutorials.mnist import input_data import tensorflow as tf import shutil import os.path from tensorflow.python.framework import graph_util 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') def inference(input_image, keep_prob): W_conv1 = weight_variable([5, 5, 1, 32]) b_conv1 = bias_variable([32]) x_image = tf.reshape(input_image, [-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]) logits = tf.matmul(h_fc1_drop, W_fc2) + b_fc2 return logits def train(export_dir): mnist = input_data.read_data_sets("datasets", one_hot=True) g = tf.Graph() with g.as_default(): x = tf.placeholder("float", shape=[None, 784]) y_ = tf.placeholder("float", shape=[None, 10]) keep_prob = tf.placeholder("float") logits = inference(x, keep_prob) y_conv = tf.nn.softmax(logits) 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) saver = tf.train.Saver() step = 200 checkpoint_file = os.path.join(export_dir, 'model.ckpt') saver.save(sess, checkpoint_file, global_step=step) checkpoint_file = os.path.join(export_dir, 'model.ckpt') def export_pb_model(model_name): graph = tf.Graph() with graph.as_default(): input_image = tf.placeholder("float", shape=[None,28*28], name='inputdata') keep_prob = tf.placeholder("float", name = 'keep_probdata') logits = inference(input_image, keep_prob) y_conv = tf.nn.softmax(logits,name='outputdata') restore_saver = tf.train.Saver() with tf.Session(graph=graph) as sess: sess.run(tf.global_variables_initializer()) latest_ckpt = tf.train.latest_checkpoint('log') restore_saver.restore(sess, latest_ckpt) output_graph_def = tf.graph_util.convert_variables_to_constants( sess, graph.as_graph_def(), ['outputdata']) # tf.train.write_graph(output_graph_def, 'log', model_name, as_text=False) with tf.gfile.GFile(model_name, "wb") as f: f.write(output_graph_def.SerializeToString()) def test_pb_model(model_name): mnist = input_data.read_data_sets("datasets", one_hot=True) with tf.Graph().as_default(): output_graph_def = tf.GraphDef() output_graph_path = model_name # 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("inputdata:0") output = sess.graph.get_tensor_by_name("outputdata:0") keep_prob = sess.graph.get_tensor_by_name("keep_probdata:0") y_conv_2 = sess.run(output,{input_x:mnist.test.images, keep_prob: 1.0}) 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()) if __name__ == '__main__': export_dir = './log' if os.path.exists(export_dir): shutil.rmtree(export_dir) #训练并保存模型ckpt train(export_dir) model_name = os.path.join(export_dir, 'mnist.pb') #ckpt模型转换为pb模型 export_pb_model(model_name) #测试pb模型 test_pb_model(model_name)
$ python mymain.py
#训练并保存模型ckpt
Extracting datasets/train-images-idx3-ubyte.gz
Extracting datasets/train-labels-idx1-ubyte.gz
Extracting datasets/t10k-images-idx3-ubyte.gz
Extracting datasets/t10k-labels-idx1-ubyte.gz
2018-03-19 18:11:27.046638: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2018-03-19 18:11:27.169530: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:892] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-03-19 18:11:27.170178: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties:
name: GeForce GTX 1080 major: 6 minor: 1 memoryClockRate(GHz): 1.7335
pciBusID: 0000:01:00.0
totalMemory: 7.92GiB freeMemory: 5.51GiB
2018-03-19 18:11:27.170196: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1080, pci bus id: 0000:01:00.0, compute capability: 6.1)
WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/tensorflow/python/util/tf_should_use.py:107: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use `tf.global_variables_initializer` instead.
step 0, training accuracy 0.08
step 100, training accuracy 0.86
step 200, training accuracy 0.96
2018-03-19 18:11:29.100338: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.32GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
test accuracy 0.9137
#ckpt模型转换为pb模型
2018-03-19 18:11:30.655025: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1080, pci bus id: 0000:01:00.0, compute capability: 6.1)
Converted 8 variables to const ops.
#测试pb模型
Extracting datasets/train-images-idx3-ubyte.gz
Extracting datasets/train-labels-idx1-ubyte.gz
Extracting datasets/t10k-images-idx3-ubyte.gz
Extracting datasets/t10k-labels-idx1-ubyte.gz
2018-03-19 18:11:32.419375: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: GeForce GTX 1080, pci bus id: 0000:01:00.0, compute capability: 6.1)
(u'y_conv_2', array([[ 3.83061661e-06, 2.25869144e-06, 6.98342774e-05, ...,
9.99720514e-01, 5.38732929e-05, 6.28733032e-05],
[ 1.85461645e-03, 3.86392418e-03, 9.55442667e-01, ...,
1.31935649e-05, 2.71034874e-02, 4.14738406e-06],
[ 2.61329369e-05, 9.94501710e-01, 1.34233199e-03, ...,
8.23311449e-04, 1.73626456e-03, 3.27934940e-05],
...,
[ 1.58834242e-04, 1.02327869e-03, 9.29224771e-04, ...,
9.04104114e-03, 1.03222862e-01, 1.16873145e-01],
[ 9.86627676e-03, 1.02333550e-03, 2.13368423e-03, ...,
2.72160349e-03, 3.91508579e-01, 4.37955791e-03],
[ 1.95508893e-03, 2.17417346e-06, 1.18497398e-03, ...,
5.04385412e-07, 3.14567442e-05, 4.29990359e-06]], dtype=float32))
(u'correct_prediction_2', <tf.Tensor 'Equal:0' shape=(10000,) dtype=bool>)
(u'accuracy_2', <tf.Tensor 'Mean:0' shape=() dtype=float32>)
check accuracy 0.9137
