일단 클라이언트까지 결과 전송됨

FlaskApi/cps/checkpoint

@@ -0,0 +1,2 @@
+model_checkpoint_path: "cps/model.ckpt"
+all_model_checkpoint_paths: "cps/model.ckpt"

FlaskApi/input_data.py

@@ -0,0 +1,144 @@
+"""Functions for downloading and reading MNIST data."""
+from __future__ import print_function
+import gzip
+import os
+import urllib
+import numpy
+SOURCE_URL = 'http://yann.lecun.com/exdb/mnist/'
+def maybe_download(filename, work_directory):
+  """Download the data from Yann's website, unless it's already here."""
+  if not os.path.exists(work_directory):
+    os.mkdir(work_directory)
+  filepath = os.path.join(work_directory, filename)
+  if not os.path.exists(filepath):
+    filepath, _ = urllib.urlretrieve(SOURCE_URL + filename, filepath)
+    statinfo = os.stat(filepath)
+    print('Succesfully downloaded', filename, statinfo.st_size, 'bytes.')
+  return filepath
+def _read32(bytestream):
+  dt = numpy.dtype(numpy.uint32).newbyteorder('>')
+  return numpy.frombuffer(bytestream.read(4), dtype=dt)
+def extract_images(filename):
+  """Extract the images into a 4D uint8 numpy array [index, y, x, depth]."""
+  print('Extracting', filename)
+  with gzip.open(filename) as bytestream:
+    magic = _read32(bytestream)
+    if magic != 2051:
+      raise ValueError(
+          'Invalid magic number %d in MNIST image file: %s' %
+          (magic, filename))
+    num_images = _read32(bytestream)
+    rows = _read32(bytestream)
+    cols = _read32(bytestream)
+    buf = bytestream.read(rows * cols * num_images)
+    data = numpy.frombuffer(buf, dtype=numpy.uint8)
+    data = data.reshape(num_images, rows, cols, 1)
+    return data
+def dense_to_one_hot(labels_dense, num_classes=10):
+  """Convert class labels from scalars to one-hot vectors."""
+  num_labels = labels_dense.shape[0]
+  index_offset = numpy.arange(num_labels) * num_classes
+  labels_one_hot = numpy.zeros((num_labels, num_classes))
+  labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1
+  return labels_one_hot
+def extract_labels(filename, one_hot=False):
+  """Extract the labels into a 1D uint8 numpy array [index]."""
+  print('Extracting', filename)
+  with gzip.open(filename) as bytestream:
+    magic = _read32(bytestream)
+    if magic != 2049:
+      raise ValueError(
+          'Invalid magic number %d in MNIST label file: %s' %
+          (magic, filename))
+    num_items = _read32(bytestream)
+    buf = bytestream.read(num_items)
+    labels = numpy.frombuffer(buf, dtype=numpy.uint8)
+    if one_hot:
+      return dense_to_one_hot(labels)
+    return labels
+class DataSet(object):
+  def __init__(self, images, labels, fake_data=False):
+    if fake_data:
+      self._num_examples = 10000
+    else:
+      assert images.shape[0] == labels.shape[0], (
+          "images.shape: %s labels.shape: %s" % (images.shape,
+                                                 labels.shape))
+      self._num_examples = images.shape[0]
+      # Convert shape from [num examples, rows, columns, depth]
+      # to [num examples, rows*columns] (assuming depth == 1)
+      assert images.shape[3] == 1
+      images = images.reshape(images.shape[0],
+                              images.shape[1] * images.shape[2])
+      # Convert from [0, 255] -> [0.0, 1.0].
+      images = images.astype(numpy.float32)
+      images = numpy.multiply(images, 1.0 / 255.0)
+    self._images = images
+    self._labels = labels
+    self._epochs_completed = 0
+    self._index_in_epoch = 0
+  @property
+  def images(self):
+    return self._images
+  @property
+  def labels(self):
+    return self._labels
+  @property
+  def num_examples(self):
+    return self._num_examples
+  @property
+  def epochs_completed(self):
+    return self._epochs_completed
+  def next_batch(self, batch_size, fake_data=False):
+    """Return the next `batch_size` examples from this data set."""
+    if fake_data:
+      fake_image = [1.0 for _ in xrange(784)]
+      fake_label = 0
+      return [fake_image for _ in xrange(batch_size)], [
+          fake_label for _ in xrange(batch_size)]
+    start = self._index_in_epoch
+    self._index_in_epoch += batch_size
+    if self._index_in_epoch > self._num_examples:
+      # Finished epoch
+      self._epochs_completed += 1
+      # Shuffle the data
+      perm = numpy.arange(self._num_examples)
+      numpy.random.shuffle(perm)
+      self._images = self._images[perm]
+      self._labels = self._labels[perm]
+      # Start next epoch
+      start = 0
+      self._index_in_epoch = batch_size
+      assert batch_size <= self._num_examples
+    end = self._index_in_epoch
+    return self._images[start:end], self._labels[start:end]
+def read_data_sets(train_dir, fake_data=False, one_hot=False):
+  class DataSets(object):
+    pass
+  data_sets = DataSets()
+  if fake_data:
+    data_sets.train = DataSet([], [], fake_data=True)
+    data_sets.validation = DataSet([], [], fake_data=True)
+    data_sets.test = DataSet([], [], fake_data=True)
+    return data_sets
+  TRAIN_IMAGES = 'train-images-idx3-ubyte.gz'
+  TRAIN_LABELS = 'train-labels-idx1-ubyte.gz'
+  TEST_IMAGES = 't10k-images-idx3-ubyte.gz'
+  TEST_LABELS = 't10k-labels-idx1-ubyte.gz'
+  VALIDATION_SIZE = 5000
+  local_file = maybe_download(TRAIN_IMAGES, train_dir)
+  train_images = extract_images(local_file)
+  local_file = maybe_download(TRAIN_LABELS, train_dir)
+  train_labels = extract_labels(local_file, one_hot=one_hot)
+  local_file = maybe_download(TEST_IMAGES, train_dir)
+  test_images = extract_images(local_file)
+  local_file = maybe_download(TEST_LABELS, train_dir)
+  test_labels = extract_labels(local_file, one_hot=one_hot)
+  validation_images = train_images[:VALIDATION_SIZE]
+  validation_labels = train_labels[:VALIDATION_SIZE]
+  train_images = train_images[VALIDATION_SIZE:]
+  train_labels = train_labels[VALIDATION_SIZE:]
+  data_sets.train = DataSet(train_images, train_labels)
+  data_sets.validation = DataSet(validation_images, validation_labels)
+  data_sets.test = DataSet(test_images, test_labels)
+  return data_sets

FlaskApi/main.py

@@ -1,11 +1,13 @@
 from flask import Flask
+import flask
 import os
+import sys
 import base64
 
 from datetime import timedelta
 from flask import make_response, request, current_app
 from functools import update_wrapper
-
+from mnist_javacafe_study import *
 
 def crossdomain(origin=None, methods=None, headers=None,
                 max_age=21600, attach_to_all=True,
@@ -68,14 +70,17 @@ def upload():
 
     # os.system("sh ../mnist/resize-script.sh")
     # return "Hello World!"
-    print os.system("python ../TensorFlow-mnist/mnist_javacafe_study.py")
-    return "11"
+    # print os.system("python ./mnist_javacafe_study.py")
+    result = ocr()
+    print result
+    return flask.jsonify(**result)
+
+    # return "11"
 
 @app.route("/test", methods=['GET', 'POST'])
 def test():
 	return "" + os.system("./test.py")
 
 app.debug = True
-
 if __name__ == "__main__":
-	app.run()
+    app.run()

FlaskApi/mnist.py

@@ -0,0 +1,177 @@
+import tensorflow as tf
+import input_data
+import cv2
+import numpy as np
+import math
+from scipy import ndimage
+
+
+def getBestShift(img):
+    cy,cx = ndimage.measurements.center_of_mass(img)
+
+    rows,cols = img.shape
+    shiftx = np.round(cols/2.0-cx).astype(int)
+    shifty = np.round(rows/2.0-cy).astype(int)
+
+    return shiftx,shifty
+
+
+def shift(img,sx,sy):
+    rows,cols = img.shape
+    M = np.float32([[1,0,sx],[0,1,sy]])
+    shifted = cv2.warpAffine(img,M,(cols,rows))
+    return shifted
+
+
+# create a MNIST_data folder with the MNIST dataset if necessary
+mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
+
+"""
+a placeholder for our image data:
+None stands for an unspecified number of images
+784 = 28*28 pixel
+"""
+x = tf.placeholder("float", [None, 784])
+
+# we need our weights for our neural net
+W = tf.Variable(tf.zeros([784,10]))
+# and the biases
+b = tf.Variable(tf.zeros([10]))
+
+"""
+softmax provides a probability based output
+we need to multiply the image values x and the weights
+and add the biases
+(the normal procedure, explained in previous articles)
+"""
+y = tf.nn.softmax(tf.matmul(x,W) + b)
+
+"""
+y_ will be filled with the real values
+which we want to train (digits 0-9)
+for an undefined number of images
+"""
+y_ = tf.placeholder("float", [None,10])
+
+"""
+we use the cross_entropy function
+which we want to minimize to improve our model
+"""
+cross_entropy = -tf.reduce_sum(y_*tf.log(y))
+
+"""
+use a learning rate of 0.01
+to minimize the cross_entropy error
+"""
+train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
+
+# initialize all variables
+init = tf.initialize_all_variables()
+
+# create a session
+sess = tf.Session()
+sess.run(init)
+
+# use 1000 batches with a size of 100 each to train our net
+for i in range(1000):
+  batch_xs, batch_ys = mnist.train.next_batch(100)
+  # run the train_step function with the given image values (x) and the real output (y_)
+  sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
+
+"""
+Let's get the accuracy of our model:
+our model is correct if the index with the highest y value
+is the same as in the real digit vector
+The mean of the correct_prediction gives us the accuracy.
+We need to run the accuracy function
+with our test set (mnist.test)
+We use the keys "images" and "labels" for x and y_
+"""
+correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
+accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
+print sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels})
+
+# create an an array where we can store our 4 pictures
+images = np.zeros((4,784))
+# and the correct values
+correct_vals = np.zeros((4,10))
+
+# we want to test our images which you saw at the top of this page
+i = 0
+for no in [8,0,4,3]:
+    # read the image
+    gray = cv2.imread("blog/own_"+str(no)+".png", cv2.CV_LOAD_IMAGE_GRAYSCALE)
+
+    # rescale it
+    gray = cv2.resize(255-gray, (28, 28))
+    # better black and white version
+    (thresh, gray) = cv2.threshold(gray, 128, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)
+
+    while np.sum(gray[0]) == 0:
+        gray = gray[1:]
+
+    while np.sum(gray[:,0]) == 0:
+        gray = np.delete(gray,0,1)
+
+    while np.sum(gray[-1]) == 0:
+        gray = gray[:-1]
+
+    while np.sum(gray[:,-1]) == 0:
+        gray = np.delete(gray,-1,1)
+
+    rows,cols = gray.shape
+
+    if rows > cols:
+        factor = 20.0/rows
+        rows = 20
+        cols = int(round(cols*factor))
+        # first cols than rows
+        gray = cv2.resize(gray, (cols,rows))
+    else:
+        factor = 20.0/cols
+        cols = 20
+        rows = int(round(rows*factor))
+        # first cols than rows
+        gray = cv2.resize(gray, (cols, rows))
+
+    colsPadding = (int(math.ceil((28-cols)/2.0)),int(math.floor((28-cols)/2.0)))
+    rowsPadding = (int(math.ceil((28-rows)/2.0)),int(math.floor((28-rows)/2.0)))
+    gray = np.lib.pad(gray,(rowsPadding,colsPadding),'constant')
+
+    shiftx,shifty = getBestShift(gray)
+    shifted = shift(gray,shiftx,shifty)
+    gray = shifted
+
+    # save the processed images
+    cv2.imwrite("pro-img/image_"+str(no)+".png", gray)
+    """
+    all images in the training set have an range from 0-1
+    and not from 0-255 so we divide our flatten images
+    (a one dimensional vector with our 784 pixels)
+    to use the same 0-1 based range
+    """
+    flatten = gray.flatten() / 255.0
+    """
+    we need to store the flatten image and generate
+    the correct_vals array
+    correct_val for the first digit (9) would be
+    [0,0,0,0,0,0,0,0,0,1]
+    """
+    images[i] = flatten
+    correct_val = np.zeros((10))
+    correct_val[no] = 1
+    correct_vals[i] = correct_val
+    i += 1
+
+"""
+the prediction will be an array with four values,
+which show the predicted number
+"""
+prediction = tf.argmax(y,1)
+"""
+we want to run the prediction and the accuracy function
+using our generated arrays (images and correct_vals)
+"""
+print sess.run(prediction, feed_dict={x: images, y_: correct_vals})
+print sess.run(accuracy, feed_dict={x: images, y_: correct_vals})
+