基于tensorflow、CNN网络识别花卉的种类
这是一个图像识别项目，基于 tensorflow，现有的 CNN 网络可以识别四种花的种类。适合新手对使用 tensorflow进行一个完整的图像识别过程有一个大致轮廓。项目包括对数据集的处理，从硬盘读取数据，CNN 网络的定义，训练过程，还实现了一个 GUI界面用于使用训练好的网络。
Notice:本项目完全开源，需要源码关注我，再私信我哦
1、环境工具支持
- 安装 Anaconda
- 导入环境 environment.yaml
conda env update -f=environment.yaml
2、运行方法
- git clone 这个项目;
- 解压 input_data.rar 到你喜欢的目录;
- 修改 train.py 中;(如下修改）
train_dir = 'D:/ML/flower/input_data' # 训练样本的读入路径
logs_train_dir = 'D:/ML/flower/save' # logs存储路径
为你本机的目录。
- 运行 train.py 开始训练。
- 训练完成后，修改 test.py 中的
logs_train_dir = 'D:/ML/flower/save/'为你的目录。 - 运行 test.py 或者 gui.py 查看结果。
3、运行UI界面结果
gui.py运行界面：
4、项目源码模块化介绍（需要源码关注我，并私信我）
主界面文件（gui.py）：
主要包含控件的设计，很简单，没有用到其他库
class HelloFrame(wx.Frame):
def __init__(self,*args,**kw):
super(HelloFrame,self).__init__(*args,**kw)
pnl = wx.Panel(self)
self.pnl = pnl
st = wx.StaticText(pnl, label="花朵识别", pos=(200, 0))
font = st.GetFont()
font.PointSize += 10
font = font.Bold()
st.SetFont(font)
# 选择图像文件按钮
btn = wx.Button(pnl, -1, "select")
btn.Bind(wx.EVT_BUTTON, self.OnSelect)
self.makeMenuBar()
self.CreateStatusBar()
self.SetStatusText("Welcome to flower world")
def makeMenuBar(self):
fileMenu = wx.Menu()
helloItem = fileMenu.Append(-1, "&Hello...\tCtrl-H",
"Help string shown in status bar for this menu item")
fileMenu.AppendSeparator()
exitItem = fileMenu.Append(wx.ID_EXIT)
helpMenu = wx.Menu()
aboutItem = helpMenu.Append(wx.ID_ABOUT)
menuBar = wx.MenuBar()
menuBar.Append(fileMenu, "&File")
menuBar.Append(helpMenu, "Help")
self.SetMenuBar(menuBar)
self.Bind(wx.EVT_MENU, self.OnHello, helloItem)
self.Bind(wx.EVT_MENU, self.OnExit, exitItem)
self.Bind(wx.EVT_MENU, self.OnAbout, aboutItem)
def OnExit(self, event):
self.Close(True)
def OnHello(self, event):
wx.MessageBox("Hello again from wxPython")
def OnAbout(self, event):
"""Display an About Dialog"""
wx.MessageBox("This is a wxPython Hello World sample",
"About Hello World 2",
wx.OK | wx.ICON_INFORMATION)
def OnSelect(self, event):
wildcard = "image source(*.jpg)|*.jpg|" \
"Compile Python(*.pyc)|*.pyc|" \
"All file(*.*)|*.*"
dialog = wx.FileDialog(None, "Choose a file", os.getcwd(),
"", wildcard, wx.ID_OPEN)
if dialog.ShowModal() == wx.ID_OK:
print(dialog.GetPath())
img = Image.open(dialog.GetPath())
imag = img.resize([64, 64])
image = np.array(imag)
result = evaluate_one_image(image)
result_text = wx.StaticText(self.pnl, label=result, pos=(320, 0))
font = result_text.GetFont()
font.PointSize += 8
result_text.SetFont(font)
self.initimage(name= dialog.GetPath())
# 生成图片控件
def initimage(self, name):
imageShow = wx.Image(name, wx.BITMAP_TYPE_ANY)
sb = wx.StaticBitmap(self.pnl, -1, imageShow.ConvertToBitmap(), pos=(0,30), size=(600,400))
return sb
if __name__ == '__main__':
app = wx.App()
frm = HelloFrame(None, title='flower wolrd', size=(1000,600))
frm.Show()
app.MainLoop()
将原始图片转换成需要的大小，并将其保存（creat record.py):
这里就不做详细介绍了，具体解释看源码注释，注释里面写的很详细
# 原始图片的存储位置
orig_picture = 'D:/ML/flower/flower_photos/'
# 生成图片的存储位置
gen_picture = 'D:/ML/flower/input_data/'
# 需要的识别类型
classes = {'dandelion', 'roses', 'sunflowers','tulips'}
# 样本总数
num_samples = 4000
# 制作TFRecords数据
def create_record():
writer = tf.python_io.TFRecordWriter("flower_train.tfrecords")
for index, name in enumerate(classes):
class_path = orig_picture + "/" + name + "/"
for img_name in os.listdir(class_path):
img_path = class_path + img_name
img = Image.open(img_path)
img = img.resize((64, 64)) # 设置需要转换的图片大小
img_raw = img.tobytes() # 将图片转化为原生bytes
print(index, img_raw)
example = tf.train.Example(
features=tf.train.Features(feature={
"label": tf.train.Feature(int64_list=tf.train.Int64List(value=[index])),
'img_raw': tf.train.Feature(bytes_list=tf.train.BytesList(value=[img_raw]))
}))
writer.write(example.SerializeToString())
writer.close()
# =======================================================================================
def read_and_decode(filename):
# 创建文件队列,不限读取的数量
filename_queue = tf.train.string_input_producer([filename])
# create a reader from file queue
reader = tf.TFRecordReader()
# reader从文件队列中读入一个序列化的样本
_, serialized_example = reader.read(filename_queue)
# get feature from serialized example
# 解析符号化的样本
features = tf.parse_single_example(
serialized_example,
features={
'label': tf.FixedLenFeature([], tf.int64),
'img_raw': tf.FixedLenFeature([], tf.string)
})
label = features['label']
img = features['img_raw']
img = tf.decode_raw(img, tf.uint8)
img = tf.reshape(img, [64, 64, 3])
# img = tf.cast(img, tf.float32) * (1. / 255) - 0.5
label = tf.cast(label, tf.int32)
return img, label
# =======================================================================================
if __name__ == '__main__':
create_record()
batch = read_and_decode('flower_train.tfrecords')
init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())
with tf.Session() as sess: # 开始一个会话
sess.run(init_op)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
for i in range(num_samples):
example, lab = sess.run(batch) # 在会话中取出image和label
img = Image.fromarray(example, 'RGB') # 这里Image是之前提到的
img.save(gen_picture + '/' + str(i) + 'samples' + str(lab) + '.jpg') # 存下图片;注意cwd后边加上‘/’
print(example, lab)
coord.request_stop()
coord.join(threads)
sess.close()
生成图片路径和标签的List，Batch：
这里用源码结构图来呈现：
- 生成图片路径和标签的List
- 获取所有的图片路径名，存放到对应的列表中，同时贴上标签，存放到label列表中
- 对生成的图片路径和标签List做打乱处理
- 利用shuffle打乱顺序
- 将所有的img和lab转换成list
- 将所得List分为两部分，一部分用来训练tra，一部分用来测试valratio是测试集的比例
- 生成Batch
- 将上面生成的List传入
get_batch()，转换类型，产生一个输入队列queue，因为img和lab是分开的，所以使用tf.train.slice_input_producer()，然后用tf.read_file()从队列中读取图像 image_W, image_H：设置好固定的图像高度和宽度设置batch_size：每个batch要放多少张图片capacity：一个队列最大多少- 将图像解码，不同类型的图像不能混在一起，要么只用jpeg，要么只用png等
- 数据预处理，对图像进行旋转、缩放、裁剪、归一化等操作，让计算出的模型更健壮
- 重新排列label，行数为[batch_size]
- 将上面生成的List传入
# ============================================================================
# -----------------生成图片路径和标签的List------------------------------------
train_dir = 'D:/ML/flower/input_data'
roses = []
label_roses = []
tulips = []
label_tulips = []
dandelion = []
label_dandelion = []
sunflowers = []
label_sunflowers = []
# step1：获取所有的图片路径名，存放到
# 对应的列表中，同时贴上标签，存放到label列表中。
def get_files(file_dir, ratio):
for file in os.listdir(file_dir + '/roses'):
roses.append(file_dir + '/roses' + '/' + file)
label_roses.append(0)
for file in os.listdir(file_dir + '/tulips'):
tulips.append(file_dir + '/tulips' + '/' + file)
label_tulips.append(1)
for file in os.listdir(file_dir + '/dandelion'):
dandelion.append(file_dir + '/dandelion' + '/' + file)
label_dandelion.append(2)
for file in os.listdir(file_dir + '/sunflowers'):
sunflowers.append(file_dir + '/sunflowers' + '/' + file)
label_sunflowers.append(3)
# step2：对生成的图片路径和标签List做打乱处理
image_list = np.hstack((roses, tulips, dandelion, sunflowers))
label_list = np.hstack((label_roses, label_tulips, label_dandelion, label_sunflowers))
# 利用shuffle打乱顺序
temp = np.array([image_list, label_list])
temp = temp.transpose()
np.random.shuffle(temp)
# 从打乱的temp中再取出list（img和lab）
# image_list = list(temp[:, 0])
# label_list = list(temp[:, 1])
# label_list = [int(i) for i in label_list]
# return image_list, label_list
# 将所有的img和lab转换成list
all_image_list = list(temp[:, 0])
all_label_list = list(temp[:, 1])
# 将所得List分为两部分，一部分用来训练tra，一部分用来测试val
# ratio是测试集的比例
n_sample = len(all_label_list)
n_val = int(math.ceil(n_sample * ratio)) # 测试样本数
n_train = n_sample - n_val # 训练样本数
tra_images = all_image_list[0:n_train]
tra_labels = all_label_list[0:n_train]
tra_labels = [int(float(i)) for i in tra_labels]
val_images = all_image_list[n_train:-1]
val_labels = all_label_list[n_train:-1]
val_labels = [int(float(i)) for i in val_labels]
return tra_images, tra_labels, val_images, val_labels
# ---------------------------------------------------------------------------
# --------------------生成Batch----------------------------------------------
# step1：将上面生成的List传入get_batch() ，转换类型，产生一个输入队列queue，因为img和lab
# 是分开的，所以使用tf.train.slice_input_producer()，然后用tf.read_file()从队列中读取图像
# image_W, image_H, ：设置好固定的图像高度和宽度
# 设置batch_size：每个batch要放多少张图片
# capacity：一个队列最大多少
def get_batch(image, label, image_W, image_H, batch_size, capacity):
# 转换类型
image = tf.cast(image, tf.string)
label = tf.cast(label, tf.int32)
# make an input queue
input_queue = tf.train.slice_input_producer([image, label])
label = input_queue[1]
image_contents = tf.read_file(input_queue[0]) # read img from a queue
# step2：将图像解码，不同类型的图像不能混在一起，要么只用jpeg，要么只用png等。
image = tf.image.decode_jpeg(image_contents, channels=3)
# step3：数据预处理，对图像进行旋转、缩放、裁剪、归一化等操作，让计算出的模型更健壮。
image = tf.image.resize_image_with_crop_or_pad(image, image_W, image_H)
image = tf.image.per_image_standardization(image)
# step4：生成batch
# image_batch: 4D tensor [batch_size, width, height, 3],dtype=tf.float32
# label_batch: 1D tensor [batch_size], dtype=tf.int32
image_batch, label_batch = tf.train.batch([image, label],
batch_size=batch_size,
num_threads=32,
capacity=capacity)
# 重新排列label，行数为[batch_size]
label_batch = tf.reshape(label_batch, [batch_size])
image_batch = tf.cast(image_batch, tf.float32)
return image_batch, label_batch
CNN网络结构的定义（model.py):
这里主要运用tensorflow库进行定义，不懂源码的可以看一下我的注释
# 网络结构定义
# 输入参数：images，image batch、4D tensor、tf.float32、[batch_size, width, height, channels]
# 返回参数：logits, float、 [batch_size, n_classes]
def inference(images, batch_size, n_classes):
# 一个简单的卷积神经网络，卷积+池化层x2，全连接层x2，最后一个softmax层做分类。
# 卷积层1
# 64个3x3的卷积核（3通道），padding=’SAME’，表示padding后卷积的图与原图尺寸一致，激活函数relu()
with tf.variable_scope('conv1') as scope:
weights = tf.Variable(tf.truncated_normal(shape=[3, 3, 3, 64], stddev=1.0, dtype=tf.float32),
name='weights', dtype=tf.float32)
biases = tf.Variable(tf.constant(value=0.1, dtype=tf.float32, shape=[64]),
name='biases', dtype=tf.float32)
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)
# 池化层1
# 3x3最大池化，步长strides为2，池化后执行lrn()操作，局部响应归一化，对训练有利。
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')
# 卷积层2
# 16个3x3的卷积核（16通道），padding=’SAME’，表示padding后卷积的图与原图尺寸一致，激活函数relu()
with tf.variable_scope('conv2') as scope:
weights = tf.Variable(tf.truncated_normal(shape=[3, 3, 64, 16], stddev=0.1, dtype=tf.float32),
name='weights', dtype=tf.float32)
biases = tf.Variable(tf.constant(value=0.1, dtype=tf.float32, shape=[16]),
name='biases', dtype=tf.float32)
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')
# 池化层2
# 3x3最大池化，步长strides为2，池化后执行lrn()操作，
# 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')
# 全连接层3
# 128个神经元，将之前pool层的输出reshape成一行，激活函数relu()
with tf.variable_scope('local3') as scope:
reshape = tf.reshape(pool2, shape=[batch_size, -1])
dim = reshape.get_shape()[1].value
weights = tf.Variable(tf.truncated_normal(shape=[dim, 128], stddev=0.005, dtype=tf.float32),
name='weights', dtype=tf.float32)
biases = tf.Variable(tf.constant(value=0.1, dtype=tf.float32, shape=[128]),
name='biases', dtype=tf.float32)
local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name)
# 全连接层4
# 128个神经元，激活函数relu()
with tf.variable_scope('local4') as scope:
weights = tf.Variable(tf.truncated_normal(shape=[128, 128], stddev=0.005, dtype=tf.float32),
name='weights', dtype=tf.float32)
biases = tf.Variable(tf.constant(value=0.1, dtype=tf.float32, shape=[128]),
name='biases', dtype=tf.float32)
local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name='local4')
# dropout层
# with tf.variable_scope('dropout') as scope:
# drop_out = tf.nn.dropout(local4, 0.8)
# Softmax回归层
# 将前面的FC层输出，做一个线性回归，计算出每一类的得分
with tf.variable_scope('softmax_linear') as scope:
weights = tf.Variable(tf.truncated_normal(shape=[128, n_classes], stddev=0.005, dtype=tf.float32),
name='softmax_linear', dtype=tf.float32)
biases = tf.Variable(tf.constant(value=0.1, dtype=tf.float32, shape=[n_classes]),
name='biases', dtype=tf.float32)
softmax_linear = tf.add(tf.matmul(local4, weights), biases, name='softmax_linear')
return softmax_linear
# -----------------------------------------------------------------------------
# loss计算
# 传入参数：logits，网络计算输出值。labels，真实值，在这里是0或者1
# 返回参数：loss，损失值
def losses(logits, labels):
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
# --------------------------------------------------------------------------
# loss损失值优化
# 输入参数：loss。learning_rate，学习速率。
# 返回参数：train_op，训练op，这个参数要输入sess.run中让模型去训练。
def trainning(loss, learning_rate):
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
# -----------------------------------------------------------------------
# 评价/准确率计算
# 输入参数：logits，网络计算值。labels，标签，也就是真实值，在这里是0或者1。
# 返回参数：accuracy，当前step的平均准确率，也就是在这些batch中多少张图片被正确分类了。
def evaluation(logits, labels):
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
训练模块（train.py):
这里只针对四种花进行分类（时间有限，只准备了四种花的数据）
# 变量声明
N_CLASSES = 4 # 四种花类型
IMG_W = 64 # resize图像，太大的话训练时间久
IMG_H = 64
BATCH_SIZE = 20
CAPACITY = 200
MAX_STEP = 10000 # 一般大于10K
learning_rate = 0.0001 # 一般小于0.0001
# 获取批次batch
train_dir = 'D:/ML/flower/input_data' # 训练样本的读入路径
logs_train_dir = 'D:/ML/flower/save' # logs存储路径
# train, train_label = input_data.get_files(train_dir)
train, train_label, val, val_label = input_data.get_files(train_dir, 0.3)
# 训练数据及标签
train_batch, train_label_batch = input_data.get_batch(train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
# 测试数据及标签
val_batch, val_label_batch = input_data.get_batch(val, val_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
# 训练操作定义
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)
# 测试操作定义
test_logits = model.inference(val_batch, BATCH_SIZE, N_CLASSES)
test_loss = model.losses(test_logits, val_label_batch)
test_acc = model.evaluation(test_logits, val_label_batch)
# 这个是log汇总记录
summary_op = tf.summary.merge_all()
# 产生一个会话
sess = tf.Session()
# 产生一个writer来写log文件
train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph)
# val_writer = tf.summary.FileWriter(logs_test_dir, sess.graph)
# 产生一个saver来存储训练好的模型
saver = tf.train.Saver()
# 所有节点初始化
sess.run(tf.global_variables_initializer())
# 队列监控
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
# 进行batch的训练
try:
# 执行MAX_STEP步的训练，一步一个batch
for step in np.arange(MAX_STEP):
if coord.should_stop():
break
_, tra_loss, tra_acc = sess.run([train_op, train_loss, train_acc])
# 每隔50步打印一次当前的loss以及acc，同时记录log，写入writer
if step % 10 == 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)
# 每隔100步，保存一次训练好的模型
if (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()
测试模块（test.py):
通过输入指定的图像数据到模型中，进行简单测试（源码中含有注释）
# 获取一张图片
def get_one_image(train):
# 输入参数：train,训练图片的路径
# 返回参数：image，从训练图片中随机抽取一张图片
n = len(train)
ind = np.random.randint(0, n)
img_dir = train[ind] # 随机选择测试的图片
img = Image.open(img_dir)
plt.imshow(img)
plt.show()
image = np.array(img)
return image
# 测试图片
def evaluate_one_image(image_array):
with tf.Graph().as_default():
BATCH_SIZE = 1
N_CLASSES = 4
image = tf.cast(image_array, tf.float32)
image = tf.image.per_image_standardization(image)
image = tf.reshape(image, [1, 64, 64, 3])
logit = model.inference(image, BATCH_SIZE, N_CLASSES)
logit = tf.nn.softmax(logit)
x = tf.placeholder(tf.float32, shape=[64, 64, 3])
# you need to change the directories to yours.
logs_train_dir = 'D:/ML/flower/save/'
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:
result = ('这是玫瑰花的可能性为： %.6f' % prediction[:, 0])
elif max_index == 1:
result = ('这是郁金香的可能性为： %.6f' % prediction[:, 1])
elif max_index == 2:
result = ('这是蒲公英的可能性为： %.6f' % prediction[:, 2])
else:
result = ('这是这是向日葵的可能性为： %.6f' % prediction[:, 3])
return result
# ------------------------------------------------------------------------
if __name__ == '__main__':
img = Image.open('D:/ML/flower/flower_photos/roses/12240303_80d87f77a3_n.jpg')
plt.imshow(img)
plt.show()
imag = img.resize([64, 64])
image = np.array(imag)
evaluate_one_image(image)
至此主要源码部分就讲解完毕了，还包括其他的训练数据集，就不讲解了。
需要源码的同志们请关注，再私信我（本人看到私信一定及时回复）
创作不易，大家且行且珍惜！！！！！！
4062
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
