内容参考大神猫狗大战视频,推荐大家先观看视频
本文为参考http://i.youku.com/deeplearning101 这位大神的视频所写的一些笔记
大神的代码
https://github.com/kevin28520/My-TensorFlow-tutorials
跑完视频中的代码,发现视频中在猫狗大战中并没有制作tf官方数据文件,tfrecords数据
作者在后面有视频讲解tfrecords数据集介绍,废话不多说,直接上代码
首先建立一个create_records.py文件,内容如下
#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Tue Jul 25 00:12:41 2017
@author: hjxu
"""
import cv2
import tensorflow as tf
import numpy as np
import os
import matplotlib.pyplot as plt
import skimage.io as io
from skimage import transform
#%%
def get_files(file_dir):
'''
Args:
file_dir: file directory
Returns:
list of images and labels
'''
cats = []
label_cats = []
dogs = []
label_dogs = []
for file in os.listdir(file_dir):
name = file.split('.')
if name[0]=='cat':
cats.append(file_dir + file)
label_cats.append(0)
else:
dogs.append(file_dir + file)
label_dogs.append(1)
print('There are %d cats\nThere are %d dogs' %(len(cats), len(dogs)))
image_list = np.hstack((cats, dogs))
label_list = np.hstack((label_cats, label_dogs))
temp = np.array([image_list, label_list])
temp = temp.transpose()
np.random.shuffle(temp)
image_list = list(temp[:, 0])
label_list = list(temp[:, 1])
label_list = [int(i) for i in label_list]
return image_list, label_list
#%%
def int64_feature(value):
"""Wrapper for inserting int64 features into Example proto."""
if not isinstance(value, list):
value = [value]
return tf.train.Feature(int64_list=tf.train.Int64List(value=value))
def bytes_feature(value):
return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
#%%
def convert_to_tfrecord(images, labels, save_dir, name):
'''convert all images and labels to one tfrecord file.
Args:
images: list of image directories, string type
labels: list of labels, int type
save_dir: the directory to save tfrecord file, e.g.: '/home/folder1/'
name: the name of tfrecord file, string type, e.g.: 'train'
Return:
no return
Note:
converting needs some time, be patient...
'''
filename = (save_dir + name + '.tfrecords')
n_samples = len(labels)
if np.shape(images)[0] != n_samples:
raise ValueError('Images size %d does not match label size %d.' %(images.shape[0], n_samples))
# wait some time here, transforming need some time based on the size of your data.
writer = tf.python_io.TFRecordWriter(filename)
print('\nTransform start......')
for i in np.arange(0, n_samples):
try:
image = cv2.imread(images[i])
image = cv2.resize(image, (208, 208))
b,g,r = cv2.split(image)
rgb_image = cv2.merge([r,g,b]) # this is suitable
# image = rgb_image.astype(np.float32)
# image = io.imread(images[i]) # type(image) must be array! #这边是两种读取图像的方法
# image = transform.resize(image, (208, 208))
# image = np.asarray(image)
image_raw = rgb_image.tostring()
label = int(labels[i])
example = tf.train.Example(features=tf.train.Features(feature={
'label':int64_feature(label),
'image_raw': bytes_feature(image_raw)}))
writer.write(example.SerializeToString())
except IOError as e:
print('Could not read:', images[i])
print('error: %s' %e)
print('Skip it!\n')
writer.close()
print('Transform done!')
#%%
def read_and_decode(tfrecords_file, batch_size):
'''read and decode tfrecord file, generate (image, label) batches
Args:
tfrecords_file: the directory of tfrecord file
batch_size: number of images in each batch
Returns:
image: 4D tensor - [batch_size, width, height, channel]
label: 1D tensor - [batch_size]
'''
# make an input queue from the tfrecord file
filename_queue = tf.train.string_input_producer([tfrecords_file])
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
img_features = tf.parse_single_example(
serialized_example,
features={
'label': tf.FixedLenFeature([], tf.int64),
'image_raw': tf.FixedLenFeature([], tf.string),
})
image = tf.decode_raw(img_features['image_raw'], tf.uint8)
##########################################################
# you can put data augmentation here, I didn't use it
##########################################################
# all the images of notMNIST are 28*28, you need to change the image size if you use other dataset.
image = tf.reshape(image, [208, 208,3])
label = tf.cast(img_features['label'], tf.float32)
image = tf.image.per_image_standardization(image)
image_batch, label_batch = tf.train.batch([image, label],
batch_size= batch_size,
num_threads= 64,
capacity = 2000)
return image_batch, tf.reshape(label_batch, [batch_size])
上述代码中 def get_file(file_dir)
返回的是文件中保存图片的路径和对应的label
制作数据需要用writer = tf.python_io.TFRecordWriter(SAVE_PATH)
之后就需要将图片和标签转换成二进制文件保存到records文件中,这时候需要
image_raw = rgb_image.tostring()
函数来转换图片格式,注意,opencv和pIL读取进来的图片通道是不一样的,在转换的时候也要注意下,label只需要int一下转换格式就可以了
制作好tfrecords文件之后,该怎么解码这里面的二进制文件呢?这里面讲解的很全面http://www.2cto.com/kf/201611/561584.html
http://wiki.jikexueyuan.com/project/tensorflow-zh/how_tos/reading_data.html
tf提供解码函数
首先需要利用tf.train.string_input_producer()这个函数建立一个队列,利用tf.RecoderReader()和tf.parse_single_example()来将example协议内存块解析为张量
filename_queue = tf.train.string_input_producer([tfrecords_file])
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
img_features = tf.parse_single_example(
serialized_example,
features={
'label': tf.FixedLenFeature([], tf.int64),
'image_raw': tf.FixedLenFeature([], tf.string),
})
image = tf.decode_raw(img_features['image_raw'], tf.uint8)
tf.decode_raw()是将bytes转化成一个数字向量表示,下面就是训练了
建立一个model.py文件,模型和视频中的模型是一样的,
#%%
import tensorflow as tf
#%%
def inference(images, batch_size, n_classes):
'''Build the model
Args:
images: image batch, 4D tensor, tf.float32, [batch_size, width, height, channels]
Returns:
output tensor with the computed logits, float, [batch_size, n_classes]
'''
#conv1, shape = [kernel size, kernel size, channels, kernel numbers]
with tf.variable_scope('conv1') as scope:
weights = tf.get_variable('weights',
shape = [3,3,3, 16],
dtype = tf.float32,
initializer=tf.truncated_normal_initializer(stddev=0.1,dtype=tf.float32))
biases = tf.get_variable('biases',
shape=[16],
dtype=tf.float32,
initializer=tf.constant_initializer(0.1))
conv = tf.nn.conv2d(images, weights, strides=[1,1,1,1], padding='SAME')
pre_activation = tf.nn.bias_add(conv, biases)
conv1 = tf.nn.relu(pre_activation, name= scope.name)
#pool1 and norm1
with tf.variable_scope('pooling1_lrn') as scope:
pool1 = tf.nn.max_pool(conv1, ksize=[1,3,3,1],strides=[1,2,2,1],
padding='SAME', name='pooling1')
norm1 = tf.nn.lrn(pool1, depth_radius=4, bias=1.0, alpha=0.001/9.0,
beta=0.75,name='norm1')
#conv2
with tf.variable_scope('conv2') as scope:
weights = tf.get_variable('weights',
shape=[3,3,16,16],
dtype=tf.float32,
initializer=tf.truncated_normal_initializer(stddev=0.1,dtype=tf.float32))
biases = tf.get_variable('biases',
shape=[16],
dtype=tf.float32,
initializer=tf.constant_initializer(0.1))
conv = tf.nn.conv2d(norm1, weights, strides=[1,1,1,1],padding='SAME')
pre_activation = tf.nn.bias_add(conv, biases)
conv2 = tf.nn.relu(pre_activation, name='conv2')
#pool2 and norm2
with tf.variable_scope('pooling2_lrn') as scope:
norm2 = tf.nn.lrn(conv2, depth_radius=4, bias=1.0, alpha=0.001/9.0,
beta=0.75,name='norm2')
pool2 = tf.nn.max_pool(norm2, ksize=[1,3,3,1], strides=[1,1,1,1],
padding='SAME',name='pooling2')
#local3
with tf.variable_scope('local3') as scope:
reshape = tf.reshape(pool2, shape=[batch_size, -1])
dim = reshape.get_shape()[1].value
weights = tf.get_variable('weights',
shape=[dim,128],
dtype=tf.float32,
initializer=tf.truncated_normal_initializer(stddev=0.005,dtype=tf.float32))
biases = tf.get_variable('biases',
shape=[128],
dtype=tf.float32,
initializer=tf.constant_initializer(0.1))
local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name)
#local4
with tf.variable_scope('local4') as scope:
weights = tf.get_variable('weights',
shape=[128,128],
dtype=tf.float32,
initializer=tf.truncated_normal_initializer(stddev=0.005,dtype=tf.float32))
biases = tf.get_variable('biases',
shape=[128],
dtype=tf.float32,
initializer=tf.constant_initializer(0.1))
local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name='local4')
# softmax
with tf.variable_scope('softmax_linear') as scope:
weights = tf.get_variable('softmax_linear',
shape=[128, n_classes],
dtype=tf.float32,
initializer=tf.truncated_normal_initializer(stddev=0.005,dtype=tf.float32))
biases = tf.get_variable('biases',
shape=[n_classes],
dtype=tf.float32,
initializer=tf.constant_initializer(0.1))
softmax_linear = tf.add(tf.matmul(local4, weights), biases, name='softmax_linear')
return softmax_linear
#%%
def losses(logits, labels):
'''Compute loss from logits and labels
Args:
logits: logits tensor, float, [batch_size, n_classes]
labels: label tensor, tf.int32, [batch_size]
Returns:
loss tensor of float type
'''
with tf.variable_scope('loss') as scope:
cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits\
(logits=logits, labels=labels, name='xentropy_per_example')
loss = tf.reduce_mean(cross_entropy, name='loss')
tf.summary.scalar(scope.name+'/loss', loss)
return loss
#%%
def trainning(loss, learning_rate):
'''Training ops, the Op returned by this function is what must be passed to
'sess.run()' call to cause the model to train.
Args:
loss: loss tensor, from losses()
Returns:
train_op: The op for trainning
'''
with tf.name_scope('optimizer'):
optimizer = tf.train.AdamOptimizer(learning_rate= learning_rate)
global_step = tf.Variable(0, name='global_step', trainable=False)
train_op = optimizer.minimize(loss, global_step= global_step)
return train_op
#%%
def evaluation(logits, labels):
"""Evaluate the quality of the logits at predicting the label.
Args:
logits: Logits tensor, float - [batch_size, NUM_CLASSES].
labels: Labels tensor, int32 - [batch_size], with values in the
range [0, NUM_CLASSES).
Returns:
A scalar int32 tensor with the number of examples (out of batch_size)
that were predicted correctly.
"""
with tf.variable_scope('accuracy') as scope:
correct = tf.nn.in_top_k(logits, labels, 1)
correct = tf.cast(correct, tf.float16)
accuracy = tf.reduce_mean(correct)
tf.summary.scalar(scope.name+'/accuracy', accuracy)
return accuracy
#%%
然后调用建立一个train_records.py函数,调用tfrecords数据,来训练
#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Wed Jul 26 18:17:37 2017
@author: hjxu
"""
#%%
import os
import numpy as np
import tensorflow as tf
#import input_data
import model
import create_records as cr
#%%
N_CLASSES = 2
IMG_W = 208 # resize the image, if the input image is too large, training will be very slow.
IMG_H = 208
BATCH_SIZE = 16
CAPACITY = 2000
MAX_STEP = 10000 # with current parameters, it is suggested to use MAX_STEP>10k
learning_rate = 0.0001 # with current parameters, it is suggested to use learning rate<0.0001
#%%
def run_training1():
# you need to change the directories to yours.
# train_dir = '/home/hjxu/PycharmProjects/01_cats_vs_dogs/data/train/'
logs_train_dir = '/home/hjxu/PycharmProjects/01_cats_vs_dogs/logs/recordstrain/'
#
# train, train_label = input_data.get_files(train_dir)
tfrecords_file = '/home/hjxu/PycharmProjects/01_cats_vs_dogs/tfrecords/test.tfrecords'
train_batch, train_label_batch = cr.read_and_decode(tfrecords_file, batch_size=BATCH_SIZE)
train_batch = tf.cast(train_batch,dtype=tf.float32)
train_label_batch = tf.cast(train_label_batch,dtype=tf.int64)
train_logits = model.inference(train_batch, BATCH_SIZE, N_CLASSES)
train_loss = model.losses(train_logits, train_label_batch)
train_op = model.trainning(train_loss, learning_rate)
train__acc = model.evaluation(train_logits, train_label_batch)
summary_op = tf.summary.merge_all()
sess = tf.Session()
train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph)
saver = tf.train.Saver()
sess.run(tf.global_variables_initializer())
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
for step in np.arange(MAX_STEP):
if coord.should_stop():
break
_, tra_loss, tra_acc = sess.run([train_op, train_loss, train__acc])
if step % 50 == 0:
print('Step %d, train loss = %.2f, train accuracy = %.2f%%' %(step, tra_loss, tra_acc*100.0))
summary_str = sess.run(summary_op)
train_writer.add_summary(summary_str, step)
if step % 2000 == 0 or (step + 1) == MAX_STEP:
checkpoint_path = os.path.join(logs_train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
except tf.errors.OutOfRangeError:
print('Done training -- epoch limit reached')
finally:
coord.request_stop()
coord.join(threads)
sess.close()
run_training1()
#%% Evaluate one image
# when training, comment the following codes.
#from PIL import Image
#import matplotlib.pyplot as plt
#
#def get_one_image(train):
# '''Randomly pick one image from training data
# Return: ndarray
# '''
# n = len(train)
# ind = np.random.randint(0, n)
# img_dir = train[ind]
#
# image = Image.open(img_dir)
# plt.imshow(image)
# image = image.resize([208, 208])
# image = np.array(image)
# return image
#
#def evaluate_one_image():
# '''Test one image against the saved models and parameters
# '''
#
# # you need to change the directories to yours.
# train_dir = '/home/kevin/tensorflow/cats_vs_dogs/data/train/'
# train, train_label = input_data.get_files(train_dir)
# image_array = get_one_image(train)
#
# with tf.Graph().as_default():
# BATCH_SIZE = 1
# N_CLASSES = 2
#
# image = tf.cast(image_array, tf.float32)
# image = tf.image.per_image_standardization(image)
# image = tf.reshape(image, [1, 208, 208, 3])
# logit = model.inference(image, BATCH_SIZE, N_CLASSES)
#
# logit = tf.nn.softmax(logit)
#
# x = tf.placeholder(tf.float32, shape=[208, 208, 3])
#
# # you need to change the directories to yours.
# logs_train_dir = '/home/kevin/tensorflow/cats_vs_dogs/logs/train/'
#
# saver = tf.train.Saver()
#
# with tf.Session() as sess:
#
# print("Reading checkpoints...")
# ckpt = tf.train.get_checkpoint_state(logs_train_dir)
# if ckpt and ckpt.model_checkpoint_path:
# global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
# saver.restore(sess, ckpt.model_checkpoint_path)
# print('Loading success, global_step is %s' % global_step)
# else:
# print('No checkpoint file found')
#
# prediction = sess.run(logit, feed_dict={x: image_array})
# max_index = np.argmax(prediction)
# if max_index==0:
# print('This is a cat with possibility %.6f' %prediction[:, 0])
# else:
# print('This is a dog with possibility %.6f' %prediction[:, 1])
#%%
然后建立一个evaluate_one_image.py文件
#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Mon Jul 24 05:33:09 2017
@author: hjxu
"""
#%% Evaluate one image
# when training, comment the following codes.
import model
import numpy as np
from PIL import Image
import tensorflow as tf
import matplotlib.pyplot as plt
import input_data
def get_one_image(train):
'''Randomly pick one image from training data
Return: ndarray
'''
n = len(train)
ind = np.random.randint(0, n)
img_dir = train[ind]
image = Image.open(img_dir)
plt.imshow(image)
image = image.resize([208, 208])
image = np.array(image)
return image
def get_one_img(img_dir):
image = Image.open(img_dir)
plt.imshow(image)
image = image.resize([208, 208])
image = np.array(image)
return image
def evaluate_one_image():
'''Test one image against the saved models and parameters
'''
# you need to change the directories to yours.
# img_dir = '/home/hjxu/PycharmProjects/01_cats_vs_dogs/222.jpg'
# image_array = get_one_img(img_dir)
train_dir = '/home/hjxu/PycharmProjects/01_cats_vs_dogs/data/train/'
train, train_label = input_data.get_files(train_dir)
image_array = get_one_image(train)
with tf.Graph().as_default():
BATCH_SIZE = 1
N_CLASSES = 2
image = tf.cast(image_array, tf.float32)
image = tf.image.per_image_standardization(image)
image = tf.reshape(image, [1, 208, 208, 3])
logit = model.inference(image, BATCH_SIZE, N_CLASSES)
logit = tf.nn.softmax(logit)
x = tf.placeholder(tf.float32, shape=[208, 208, 3])
# you need to change the directories to yours.
logs_train_dir = '/home/hjxu/PycharmProjects/01_cats_vs_dogs/logs/recordstrain/'
saver = tf.train.Saver()
with tf.Session() as sess:
print("Reading checkpoints...")
ckpt = tf.train.get_checkpoint_state(logs_train_dir)
if ckpt and ckpt.model_checkpoint_path:
global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
saver.restore(sess, ckpt.model_checkpoint_path)
print('Loading success, global_step is %s' % global_step)
else:
print('No checkpoint file found')
prediction = sess.run(logit, feed_dict={x: image_array})
max_index = np.argmax(prediction)
if max_index==0:
print('This is a cat with possibility %.6f' %prediction[:, 0])
else:
print('This is a dog with possibility %.6f' %prediction[:, 1])