Jacky Tung Wonderland

Downsize model by using freeze graph

Why freezing ?

How to freeze graph ?

bazel build tensorflow/python/tools:freeze_graph && \
bazel-bin/tensorflow/python/tools/freeze_graph \
--input_graph=some_graph_def.pb \
--input_checkpoint=model.ckpt-8361242 \
--output_graph=/tmp/frozen_graph.pb --output_node_names=softmax

bazel build tensorflow/python/tools:freeze_graph && \
bazel-bin/tensorflow/python/tools/freeze_graph \
--input_graph=graph.pb \
--input_checkpoint=model.ckpt \
--output_graph=/tmp/frozen_graph.pb --output_node_names=softmax

How to extract tensors from ckpt file

$ cd tensorflow/tensorflow/python/tools

// list all tensors
$ python inspect_checkpoint.py --file_name=$your_ckpt_file_path

// print the value from specific tensor
$ python inspect_checkpoint.py --file_name=$your_ckpt_file_path  --tensor_name=$specific_tensor

python inspect_checkpoint.py --file_name=$your_ckpt_file_path

python inspect_checkpoint.py --file_name=$your_ckpt_file_path  --tensor_name=$specific_tensor

Requirement

Create Graph

import tensorflow as tf
import time
from tensorflow.examples.tutorials.mnist import input_data
# === prepare tensorflow network === #

#config setting
imageDim = 784
outputDim = 10

mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
# None means that a dimension can be any of any length
x = tf.placeholder(tf.float32, [None, imageDim], name="input")
# 784-dimensional image vectors by it to produce 10-dimensional vectors
W = tf.Variable(tf.zeros([imageDim, outputDim]), dtype=tf.float32, name="Weight")
# a shape of [10]
b = tf.Variable(tf.zeros([outputDim]), dtype=tf.float32, name="bias")
# softmax
y = tf.nn.softmax(tf.matmul(x, W)+b, name="softmax")

....

# Add ops to save and restore all the variables
saver = tf.train.Saver()

with tf.Session() as sess:
 sess.run(tf.initialize_all_variables())
#Training
    for i in range(1000):
        if i % 100 == 0:
            print "iteration num :", i
        batch_xs, batch_ys = mnist.train.next_batch(100)
        sess.run(train_step,feed_dict={x: batch_xs, y_: batch_ys})

    # Save checkpoint, graph.pb and tensorboard
    saver.save(sess, "models/model.ckpt") 
    tf.train.write_graph(sess.graph.as_graph_def(), "models/", "graph.pb")
    tf.train.SummaryWriter("board", sess.graph)
#Testing
.....    

Creating a simple library

cout << "preparing input data..." << endl;
  // config setting
  int imageDim = 784;
  int nTests = 10000;
  
  // Setup inputs and outputs:
  Tensor x(DT_FLOAT, TensorShape({nTests, imageDim}));

  MNIST mnist = MNIST("./MNIST_data/");
  auto dst = x.flat<float>().data();
  for (int i = 0; i < nTests; i++) {
    auto img = mnist.testData.at(i).pixelData;
    std::copy_n(img.begin(), imageDim, dst);
    dst += imageDim;
  }

  cout << "data is ready" << endl;
  vector<pair<string, Tensor>> inputs = {
    { "input", x}
  };

  // The session will initialize the outputs
  vector<Tensor> outputs;
  // Run the session, evaluating our "softmax" operation from the graph
  status = session->Run(inputs, {"softmax"}, {}, &outputs);
  if (!status.ok()) {
    cout << status.ToString() << "\n";
    return 1;
  }else{
   cout << "Success load graph !! " << "\n";
  }

// start compute the accuracy,
  // arg_max is to record which index is the largest value after 
  // computing softmax, and if arg_max is equal to testData.label,
  // means predict correct.
  int nHits = 0;
  for (vector<Tensor>::iterator it = outputs.begin() ; it != outputs.end(); ++it) {
   auto items = it->shaped<float, 2>({nTests, 10}); // 10 represent number of class
 for(int i = 0 ; i < nTests ; i++){
      int arg_max = 0;
            float val_max = items(i, 0);
            for (int j = 0; j < 10; j++) {
         if (items(i, j) > val_max) {
               arg_max = j;
               val_max = items(i, j);
                }
      }
      if (arg_max == mnist.testData.at(i).label) {
          nHits++;
            } 
 }
  }
  float accuracy = (float)nHits/nTests;
  cout << "accuracy is : " << accuracy << ", and Done!!" << 

cc_binary(
    name = "mnistpredict",
    srcs = ["mnist.cc", "MNIST.h"],
    deps = [
        "//tensorflow/core:tensorflow",
    ],
);

Compile and Run

Note and Following tutorial

package URLConnection;


import java.io.IOException;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.select.Elements;

public class test {
 
 public static void getpoint(String urlStr){ 
    
  Document doc = null;
  try {
   doc = Jsoup.connect(urlStr).get();
  } catch (IOException e1) {
   // TODO Auto-generated catch block
   e1.printStackTrace();
  }
  Elements newsHeadlines1 = doc.select("start_location");
  
  System.out.println(newsHeadlines1.size()); // know the tag size
  System.out.println(newsHeadlines1.get(0)); 
  System.out.println(newsHeadlines1.get(0).text()); // get the text
  System.out.println(newsHeadlines1.get(0).tagName()); // print tag name
  System.out.println(newsHeadlines1.get(0).empty()); // empty the text
 }
 
 public static void main(String[] args){
   
  float start_lat = (float) 24.79608;
  float start_lng = (float) 120.98709;
  float end_lat = (float) 24.80237;
  float end_lng = (float) 120.97206;
  link(start_lat,start_lng,end_lat,end_lng);
  
  
 } 
 public static void link(float start_lat,float start_lng,float end_lat,float end_lng)
 {
  System.out.println("http://maps.googleapis.com/maps/api/directions/xml?origin="+start_lat+","+start_lng+"&destination="+end_lat+","+end_lng+"&sensor=false&units=metric&mode=driving");
     getpoint("http://maps.googleapis.com/maps/api/directions/xml?origin="+start_lat+","+start_lng+"&destination="+end_lat+","+end_lng+"&sensor=false&units=metric&mode=driving");
 }
}