默认 已安装好 python、tensorflow、opencv等环境
一、主程序 AutoEncoder.py
# -*- coding: utf-8 -*-
"""
# _*_ coding:utf-8 _*_
#进行Autoencoder网络测试(3层半网络)
#3层编码 3层解码
#开始日期: 20200909
#开发及测试人:shany 商
"""
from __future__ import division, print_function, absolute_import
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import input_AEdata
import os
import cv2
from PIL import Image
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
#加载AEtest数据集
#with tf.device('/gpu:0'):
# 得到数据集合MNIST
#from tensorflow.examples.tutorials.mnist import input_data
AEdata = input_AEdata.read_data_sets("F:/00AutoencoderTest/tmp/AEtest7", one_hot=True)
inputs_ = tf.placeholder(tf.float32, (None, 800, 800, 1), name='inputs')
targets_ = tf.placeholder(tf.float32, (None, 800, 800, 1), name='targets')
### Encoder
conv1 = tf.layers.conv2d(inputs_, 8, (3,3), padding='same', activation=tf.nn.relu) # 800x800x128
maxpool1 = tf.layers.max_pooling2d(conv1, (2,2), (2,2), padding='same') # 400x400x128
conv2 = tf.layers.conv2d(maxpool1, 4, (3,3), padding='same', activation=tf.nn.relu) # 400x400x64
maxpool2 = tf.layers.max_pooling2d(conv2, (2,2), (2,2), padding='same') # 200x200x64
conv3 = tf.layers.conv2d(maxpool2, 4, (3,3), padding='same', activation=tf.nn.relu) # 200x200x32
#maxpool3 = tf.layers.max_pooling2d(conv3, (2,2), (2,2), padding='same') # 100x100x32
#conv4 = tf.layers.conv2d(maxpool3, 4, (3,3), padding='same', activation=tf.nn.relu) # 100x100x16
encoded = tf.layers.max_pooling2d(conv3, (2,2), (2,2), padding='same') # 50x50x16
### Decoder
upsample1 = tf.image.resize_nearest_neighbor(encoded, (200,200)) # 100x100x16
conv5 = tf.layers.conv2d(upsample1, 4, (3,3), padding='same', activation=tf.nn.relu) # 100x100x16
upsample2 = tf.image.resize_nearest_neighbor(conv5, (400,400)) # 200x200x32
conv6 = tf.layers.conv2d(upsample2, 4, (3,3), padding='same', activation=tf.nn.relu) # 200x200x32
upsample3 = tf.image.resize_nearest_neighbor(conv6, (800,800)) # 400x400x64
conv7 = tf.layers.conv2d(upsample3, 8, (3,3), padding='same', activation=tf.nn.relu) # 400x400x64
#upsample4 = tf.image.resize_nearest_neighbor(conv7, (800,800)) # 800x800x128
#conv8 = tf.layers.conv2d(upsample4, 16, (3,3), padding='same', activation=tf.nn.relu) # 800x800x128
logits = tf.layers.conv2d(conv7, 1, (3,3), padding='same', activation=None) # 800x800x1
decoded = tf.nn.sigmoid(logits, name='decoded') # 800x800x1
### Loss and Optimization:
loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=targets_, logits=logits)
cost = tf.reduce_mean(loss)
opt = tf.train.AdamOptimizer(0.01).minimize(cost)
sess = tf.Session(config=tf.ConfigProto(allow_soft_placement=True,log_device_placement=True))
sess = tf.Session()
epochs = 100
batch_size = 10
sess.run(tf.global_variables_initializer())
for e in range(epochs):
for ii in range(AEdata.train.num_examples//batch_size):
batch = AEdata.train.next_batch(batch_size)
imgs = batch[0].reshape((-1, 800, 800, 1))
batch_cost, _ = sess.run([cost, opt], feed_dict={inputs_: imgs, targets_: imgs})
print("Epoch: {}/{}...".format(e+1, epochs), "Training loss: {:.4f}".format(batch_cost))
#fig, axes = plt.subplots(nrows=2, ncols=6, sharex=True, sharey=True, figsize=(10,10))
#, figsize=(20,10)
#
saver = tf.train.Saver(max_to_keep=1)
#模型保存:
saver.save(sess, 'F:/00AutoencoderTest/tmp/AEtest7/AEtest7100.ckpt')
##模型导入:
saver.restore(sess,'F:/00AutoencoderTest/tmp/AEtest7/AEtest7100.ckpt')
# 数据路径也必须指定到具体某个模型的数据,但创建这个路径的方法很多,比如调用最后一个保存的模型tf.train.latest_checkpoint('./checkpoint_dir'),也可以是xx.ckpt-500.data,并且这两个是等效的,如果是xx.ckpt-0.data,就是第一个模型的数据
in_imgs = AEdata.test.images[:10]
reconstructed, compressed = sess.run([decoded,encoded], feed_dict={inputs_: in_imgs.reshape((10, 800, 800, 1))})
# plot
count_row=0
#for images, row in zip([in_imgs, reconstructed], axes):
row=0
#in_imgs.reshape((6,800, 800))
#reconstructed.reshape((6,800, 800))
for images,row in zip([in_imgs, reconstructed],[1,2]):
count_row+=1
# images.reshape((800, 800))
# for img, ax in zip(images, row):
count_col=0
for img,col in zip(images,[1,2,3,4,5,6,7,8,9,10]):
count_col+=1
# plt.imshow(img.reshape((800, 800)), cmap='Greys_r')
# plt.axis('off')
img1=img.reshape((800, 800))
CVimg=np.array(img1)
plt.imshow(CVimg, cmap='Greys_r')
# img.flags.writeable = True # 将数组改为读写模式
# CVimg=Image.fromarray(CVimg0)
# plt.imshow(outimg, cmap='Greys_r')
# cv2.cvtColor(img, outimage, CV_BGR2GRAY);
# plt.savefig('F:/00AutoencoderTest/tmp/AEtest6/out101/'+str(count_row)+'_'+str(count_col)+'.jpg')
cv2.imwrite('F:/00AutoencoderTest/tmp/AEtest7/out100/'+str(count_row)+'_'+str(count_col)+'.jpg',CVimg*255)
# cv2.imwrite('F:/00AutoencoderTest/tmp/AEtest5/out/2.jpg',img)
# ax.get_xaxis().set_visible(False)
# ax.get_yaxis().set_visible(False)
dir(cv2)
#fig.tight_layout(pad=0.1)
count_row=0
for imagesin,inx in zip(in_imgs, [1,2,3,4,5,6,7,8,9,10]):
count_row+=1
count_col=0
for imagesout,outx in zip(reconstructed, [1,2,3,4,5,6,7,8,9,10]):
count_col+=1
if count_col == count_row:
CVimgIn1=imagesin.reshape((800, 800))
CVimgOut1=imagesout.reshape((800, 800))
CVimgIn=np.array(CVimgIn1)
CVimgOut=np.array(CVimgOut1)
CVSubImg=CVimgIn-CVimgOut
plt.imshow(CVSubImg, cmap='Greys_r')
# img.flags.writeable = True # 将数组改为读写模式
# CVimg=Image.fromarray(CVimg0)
# plt.imshow(outimg, cmap='Greys_r')
# cv2.cvtColor(img, outimage, CV_BGR2GRAY);
# plt.savefig('F:/00AutoencoderTest/tmp/AEtest6/out101/'+str(count_row)+'_'+str(count_col)+'.jpg')
cv2.imwrite('F:/00AutoencoderTest/tmp/AEtest7/out100/sub/'+str(count_row)+'.jpg',CVSubImg*255)
sess.close()
二、input_AEdata.py
"""Functions for downloading and reading MNIST data."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
# pylint: disable=unused-import
import gzip
import os
import tempfile
import numpy
from six.moves import urllib
from six.moves import xrange # pylint: disable=redefined-builtin
import tensorflow as tf
from AEdata import read_data_sets
#from tensorflow.contrib.learn.python.learn.datasets.mnist import read_data_sets
# pylint: enable=unused-import
三、AEdata.py
# ==============================================================================
"""Functions for downloading and reading AE data (deprecated).
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import gzip
import numpy
from six.moves import xrange # pylint: disable=redefined-builtin
from tensorflow.contrib.learn.python.learn.datasets import base
from tensorflow.python.framework import dtypes
from tensorflow.python.framework import random_seed
from tensorflow.python.platform import gfile
from tensorflow.python.util.deprecation import deprecated
# CVDF mirror of http://yann.lecun.com/exdb/mnist/
DEFAULT_SOURCE_URL = 'https://storage.googleapis.com/cvdf-datasets/mnist/'
def _read32(bytestream):
dt = numpy.dtype(numpy.uint32).newbyteorder('>')
return numpy.frombuffer(bytestream.read(4), dtype=dt)[0]
@deprecated(None, 'Please use tf.data to implement this functionality.')
def extract_images(f):
"""Extract the images into a 4D uint8 numpy array [index, y, x, depth].
Args:
f: A file object that can be passed into a gzip reader.
Returns:
data: A 4D uint8 numpy array [index, y, x, depth].
Raises:
ValueError: If the bytestream does not start with 2051.
"""
print('Extracting', f.name)
with gzip.GzipFile(fileobj=f) as bytestream:
magic = _read32(bytestream)
if magic != 2051:
raise ValueError('Invalid magic number %d in MNIST image file: %s' %
(magic, f.name))
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
@deprecated(None, 'Please use tf.one_hot on tensors.')
def dense_to_one_hot(labels_dense, num_classes):
"""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
@deprecated(None, 'Please use tf.data to implement this functionality.')
def extract_labels(f, one_hot=False, num_classes=10):
"""Extract the labels into a 1D uint8 numpy array [index].
Args:
f: A file object that can be passed into a gzip reader.
one_hot: Does one hot encoding for the result.
num_classes: Number of classes for the one hot encoding.
Returns:
labels: a 1D uint8 numpy array.
Raises:
ValueError: If the bystream doesn't start with 2049.
"""
print('Extracting', f.name)
with gzip.GzipFile(fileobj=f) as bytestream:
magic = _read32(bytestream)
if magic != 2049:
raise ValueError('Invalid magic number %d in MNIST label file: %s' %
(magic, f.name))
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, num_classes)
return labels
class DataSet(object):
"""Container class for a dataset (deprecated).
THIS CLASS IS DEPRECATED. See
[contrib/learn/README.md](https://www.tensorflow.org/code/tensorflow/contrib/learn/README.md)
for general migration instructions.
"""
@deprecated(None, 'Please use alternatives such as official/mnist/dataset.py'
' from tensorflow/models.')
def __init__(self,
images,
labels,
fake_data=False,
one_hot=False,
dtype=dtypes.float32,
reshape=True,
seed=None):
"""Construct a DataSet.
one_hot arg is used only if fake_data is true. `dtype` can be either
`uint8` to leave the input as `[0, 255]`, or `float32` to rescale into
`[0, 1]`. Seed arg provides for convenient deterministic testing.
"""
seed1, seed2 = random_seed.get_seed(seed)
# If op level seed is not set, use whatever graph level seed is returned
numpy.random.seed(seed1 if seed is None else seed2)
dtype = dtypes.as_dtype(dtype).base_dtype
if dtype not in (dtypes.uint8, dtypes.float32):
raise TypeError(
'Invalid image dtype %r, expected uint8 or float32' % dtype)
if fake_data:
self._num_examples = 10000
self.one_hot = one_hot
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)
if reshape:
assert images.shape[3] == 1
images = images.reshape(images.shape[0],
images.shape[1] * images.shape[2])
if dtype == dtypes.float32:
# 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, shuffle=True):
"""Return the next `batch_size` examples from this data set."""
if fake_data:
fake_image = [1] * 640000
if self.one_hot:
fake_label = [1] + [0] * 9
else:
fake_label = 0
return [fake_image for _ in xrange(batch_size)], [
fake_label for _ in xrange(batch_size)
]
start = self._index_in_epoch
# Shuffle for the first epoch
if self._epochs_completed == 0 and start == 0 and shuffle:
perm0 = numpy.arange(self._num_examples)
numpy.random.shuffle(perm0)
self._images = self.images[perm0]
self._labels = self.labels[perm0]
# Go to the next epoch
if start + batch_size > self._num_examples:
# Finished epoch
self._epochs_completed += 1
# Get the rest examples in this epoch
rest_num_examples = self._num_examples - start
images_rest_part = self._images[start:self._num_examples]
labels_rest_part = self._labels[start:self._num_examples]
# Shuffle the data
if shuffle:
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 - rest_num_examples
end = self._index_in_epoch
images_new_part = self._images[start:end]
labels_new_part = self._labels[start:end]
return numpy.concatenate(
(images_rest_part, images_new_part), axis=0), numpy.concatenate(
(labels_rest_part, labels_new_part), axis=0)
else:
self._index_in_epoch += batch_size
end = self._index_in_epoch
return self._images[start:end], self._labels[start:end]
@deprecated(None, 'Please use alternatives such as official/mnist/dataset.py'
' from tensorflow/models.')
def read_data_sets(train_dir,
fake_data=False,
one_hot=False,
dtype=dtypes.float32,
reshape=True,
validation_size=50,
seed=None,
source_url=DEFAULT_SOURCE_URL):
if fake_data:
def fake():
return DataSet(
[], [], fake_data=True, one_hot=one_hot, dtype=dtype, seed=seed)
train = fake()
validation = fake()
test = fake()
return base.Datasets(train=train, validation=validation, test=test)
if not source_url: # empty string check
source_url = DEFAULT_SOURCE_URL
# source_url = True
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'
local_file = base.maybe_download(TRAIN_IMAGES, train_dir,
source_url + TRAIN_IMAGES)
with gfile.Open(local_file, 'rb') as f:
train_images = extract_images(f)
local_file = base.maybe_download(TRAIN_LABELS, train_dir,
source_url + TRAIN_LABELS)
with gfile.Open(local_file, 'rb') as f:
train_labels = extract_labels(f, one_hot=one_hot)
local_file = base.maybe_download(TEST_IMAGES, train_dir,
source_url + TEST_IMAGES)
with gfile.Open(local_file, 'rb') as f:
test_images = extract_images(f)
local_file = base.maybe_download(TEST_LABELS, train_dir,
source_url + TEST_LABELS)
with gfile.Open(local_file, 'rb') as f:
test_labels = extract_labels(f, one_hot=one_hot)
if not 0 <= validation_size <= len(train_images):
raise ValueError('Validation size should be between 0 and {}. Received: {}.'
.format(len(train_images), validation_size))
validation_images = train_images[:validation_size]
validation_labels = train_labels[:validation_size]
train_images = train_images[validation_size:]
train_labels = train_labels[validation_size:]
options = dict(dtype=dtype, reshape=reshape, seed=seed)
train = DataSet(train_images, train_labels, **options)
validation = DataSet(validation_images, validation_labels, **options)
test = DataSet(test_images, test_labels, **options)
return base.Datasets(train=train, validation=validation, test=test)
@deprecated(None, 'Please use alternatives such as official/mnist/dataset.py'
' from tensorflow/models.')
def load_mnist(train_dir='MNIST-data'):
return read_data_sets(train_dir)