@
一.猫狗大战
1.1 简介
这是计算机视觉系列的第一篇博文，主要介绍用TensorFlow来实现猫狗分类、识别。该项目主要包括dataset、train、predict三部分。其中dataset.py主要是读取数据并对数据进行预处理；train.py主要是训练一个二分类模型;predict.py是用训练好的模型进行测试。GitHub地址:https://github.com/jx1100370217/dog-cat-master
1.2 数据集
该项目的数据主要包括1000张网上找的猫和狗的图片，其中猫，狗各500张。
二.代码：
dataset.py
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# author: JX
# data: 20181101
import cv2
import os
import glob
from sklearn.utils import shuffle
import numpy as np
def load_train(train_path,image_size,classes):
images = []
labels = []
img_names = []
cls = []
print('Going to read training images')
for fields in classes:
index = classes.index(fields)
print('Now going to read {} file (Index: {})'.format(fields,index))
path = os.path.join(train_path,fields,'*g')
files = glob.glob(path)
for f1 in files:
image = cv2.imread(f1)
image = cv2.resize(image,(image_size,image_size),0,0,cv2.INTER_LINEAR)
image = image.astype(np.float32)
image = np.multiply(image,1.0 / 255.0)
images.append(image)
label = np.zeros(len(classes))
label[index] = 1.0
labels.append(label)
flbase = os.path.basename(f1)
img_names.append(flbase)
cls.append(fields)
images = np.array(images)
labels = np.array(labels)
img_names = np.array(img_names)
cls = np.array(cls)
return images,labels,img_names,cls
class DataSet(object):
def __init__(self,images,labels,img_names,cls):
self._num_examples = images.shape[0]
self._images = images
self._labels = labels
self._img_names = img_names
self._cls = cls
self._epochs_done = 0
self._index_in_epoch = 0
@property
def images(self):
return self._images
@property
def labels(self):
return self._labels
@property
def img_names(self):
return self._img_names
@property
def cls(self):
return self._cls
@property
def num_examples(self):
return self._num_examples
@property
def epochs_done(self):
return self._epochs_done
def next_batch(self,batch_size):
start = self._index_in_epoch
self._index_in_epoch += batch_size
if self._index_in_epoch > self._num_examples:
self._epochs_done += 1
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],self._img_names[start:end],self.cls[start:end]
def read_train_sets(train_path,image_size,classes,validation_size):
class DataSets(object):
pass
data_sets = DataSets()
images, labels, img_names, cls = load_train(train_path, image_size, classes)
images, labels, img_names, cls = shuffle(images, labels, img_names, cls)
if isinstance(validation_size, float):
validation_size = int(validation_size * images.shape[0])
validation_images = images[:validation_size]
validation_labels = labels[:validation_size]
validation_img_names = img_names[:validation_size]
validation_cls = cls[:validation_size]
train_images = images[validation_size:]
train_labels = labels[validation_size:]
train_img_names = img_names[validation_size:]
train_cls = cls[validation_size:]
data_sets.train = DataSet(train_images,train_labels,train_img_names,train_cls)
data_sets.valid = DataSet(validation_images,validation_labels,validation_img_names,validation_cls)
return data_sets
train.py
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# author: JX
# data: 20181101
import dataset
import tensorflow as tf
import time
from datetime import timedelta
import math
import random
import numpy as np
from tensorflow import set_random_seed
from numpy.random import seed
seed(10)
set_random_seed(20)
batch_size = 32
classes = ['dogs','cats']
num_classes = len(classes)
validation_size = 0.2
img_size = 64
num_channels = 3
train_path = 'training_data'
data = dataset.read_train_sets(train_path,img_size,classes,validation_size=validation_size)
print("Complete reading input data.Will Now print a snippet of it")
print("Number of files in Training-set: {}".format(len(data.train.labels)))
print("Number of files in Validation-set: {}".format(len(data.valid.labels)))
session = tf.Session()
x = tf.placeholder(tf.float32,shape=[None,img_size,img_size,num_channels],name='x')
y_true = tf.placeholder(tf.float32,shape=[None,num_classes],name='y_true')
y_true_cls = tf.argmax(y_true,dimension=1)
filter_size_conv1 = 3
num_filters_conv1 = 32
filter_size_conv2 = 3
num_filters_conv2 = 32
filter_size_conv3 = 3
num_filters_conv3 = 64
fc_layer_size = 1024
def create_weights(shape):
return tf.Variable(tf.truncated_normal(shape,stddev=0.05))
def create_biases(size):
return tf.Variable(tf.constant(0.05,shape=[size]))
def create_convolutional_layer(input,
num_input_channels,
conv_filter_size,
num_filters):
weights = create_weights(shape=[conv_filter_size,conv_filter_size,num_input_channels,num_filters])
biases = create_biases(num_filters)
layer = tf.nn.conv2d(input=input,
filter=weights,strides=[1,1,1,1],
padding='SAME')
layer += biases
layer = tf.nn.relu(layer)
layer = tf.nn.max_pool(value=layer,
ksize=[1,2,2,1],
strides=[1,2,2,1],
padding='SAME')
return layer
def create_flatten_layer(layer):
layer_shape = layer.get_shape()
num_features = layer_shape[1:4].num_elements()
layer = tf.reshape(layer,[-1,num_features])
return layer
def create_fc_layer(input,
num_inputs,
num_outputs,
use_relu=True):
weights = create_weights(shape=[num_inputs,num_outputs])
biases = create_biases(num_outputs)
layer = tf.matmul(input,weights) + biases
layer = tf.nn.dropout(layer,keep_prob=0.7)
if use_relu:
layer = tf.nn.relu(layer)
return layer
layer_conv1 = create_convolutional_layer(input=x,
num_input_channels=num_channels,
conv_filter_size=filter_size_conv1,
num_filters=num_filters_conv1)
layer_conv2 = create_convolutional_layer(input=layer_conv1,
num_input_channels=num_filters_conv1,
conv_filter_size=filter_size_conv2,
num_filters=num_filters_conv2)
layer_conv3 = create_convolutional_layer(input=layer_conv2,
num_input_channels=num_filters_conv2,
conv_filter_size=filter_size_conv3,
num_filters=num_filters_conv3)
layer_flat = create_flatten_layer(layer_conv3)
layer_fc1 = create_fc_layer(input=layer_flat,
num_inputs=layer_flat.get_shape()[1:4].num_elements(),
num_outputs=fc_layer_size,
use_relu=True)
layer_fc2 = create_fc_layer(input=layer_fc1,
num_inputs=fc_layer_size,
num_outputs=num_classes,
use_relu=False)
y_pred = tf.nn.softmax(layer_fc2,name='y_pred')
y_pred_cls = tf.argmax(y_pred,dimension=1)
session.run(tf.global_variables_initializer())
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=layer_fc2,labels=y_true)
cost = tf.reduce_mean(cross_entropy)
optimizer = tf.train.AdamOptimizer(learning_rate=1e-4).minimize(cost)
correct_prediction = tf.equal(y_pred_cls,y_true_cls)
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
session.run(tf.global_variables_initializer())
def show_pregress(epoch,feed_dict_train,feed_dict_validata,val_loss,i):
acc = session.run(accuracy,feed_dict=feed_dict_train)
val_acc = session.run(accuracy,feed_dict=feed_dict_validata)
msg = "Training Epoch {0}---iterations: {1}---Training Accuracy:{2:>6.1%},"
"Validation Accuracy:{3:>6.1%},Validation Loss:{4:.3f}"
print(msg.format(epoch+1,i,acc,val_acc,val_loss))
total_iterations = 0
saver = tf.train.Saver()
def train(num_iteration):
global total_iterations
for i in range(total_iterations,total_iterations + num_iteration):
x_batch,y_true_batch,_,cls_batch = data.train.next_batch(batch_size)
x_valid_batch,y_valid_batch,_,valid_cls_batch = data.valid.next_batch(batch_size)
feed_dict_tr = {x: x_batch,y_true:y_true_batch}
feed_dict_val = {x: x_valid_batch, y_true: y_valid_batch}
session.run(optimizer,feed_dict=feed_dict_tr)
if i % int(data.train.num_examples/batch_size) == 0:
val_loss = session.run(cost,feed_dict=feed_dict_val)
epoch = int(i / int(data.train.num_examples/batch_size))
show_pregress(epoch,feed_dict_tr,feed_dict_val,val_loss,i)
saver.save(session,'./dogs-cats-model/dog-cat.ckpt',global_step=i)
total_iterations += num_iteration
train(num_iteration=10000)
predict.py
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# author: JX
# data: 20181101
import tensorflow as tf
import numpy as np
import os
import glob
import cv2
import sys
image_size = 64
num_channels = 3
images = []
path = 'cat.1.jpg'
image = cv2.imread(path)
image = cv2.resize(image,(image_size,image_size),0,0,cv2.INTER_LINEAR)
images.append(image)
images = np.array(images,dtype=np.uint8)
images = images.astype('float32')
images = np.multiply(images,1.0/255.0)
x_batch = images.reshape(1,image_size,image_size,num_channels)
sess = tf.Session()
saver = tf.train.import_meta_graph('./dogs-cats-model/dog-cat.ckpt-9975.meta')
saver.restore(sess,'./dogs-cats-model/dog-cat.ckpt-9975')
graph = tf.get_default_graph()
y_pred = graph.get_tensor_by_name("y_pred:0")
x = graph.get_tensor_by_name("x:0")
y_true = graph.get_tensor_by_name("y_true:0")
y_test_images = np.zeros((1,2))
feed_dict_testing = {x:x_batch,y_true:y_test_images}
result = sess.run(y_pred,feed_dict=feed_dict_testing)
res_label = ['dog','cat']
print(res_label[result.argmax()])
三.程序输出：
train.py
predict.py
