import tensorflow as tf
import cv2
import numpy as np
import os
import random
import sys
from sklearn.model_selection import train_test_split
#定义预处理后的图片（我的和别人的）所在目录如下。
my_face_path = r'D:\data\my_faces'
other_faces_path = r'D:\data\other_faces'
size = 64
#调整或规范图片大小。
imgs = []
labs = []
#重新创建图形变量
tf.compat.v1.reset_default_graph()
#获取需要填充的图片大小
def getPaddingSize(img1):
h, w, _ = img1.shape
top, bottom, left, right = (0, 0, 0, 0)
longest = max(h, w)
if w < longest:
tmp = longest - w
#//表示整除符号
left = tmp // 2
right = tmp - left
elif h < longest:
tmp = longest - h
top = tmp // 2
bottom = tmp - top
else:
pass
return top, bottom, left, right
tf.compat.v1.disable_eager_execution()
#读取测试图片
def readData(path, h=size, w=size):
for filename in os.listdir(path):
if filename.endswith('.jpg'):
filename = path + '/' + filename
img = cv2.imread(filename)
top, bottom, left, right = getPaddingSize(img)
#将图片放大，扩充边缘部分
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=[0, 0, 0])
img = cv2.resize(img, (h, w))
imgs.append(img)
labs.append(path)
readData(my_face_path)
readData(other_faces_path)
#将图片数据与标签转换成数组
imgs = np.array(imgs)
labs = np.array([[0, 1] if lab == my_face_path else [1, 0] for lab in labs])
#随即划分测试集与训练集
train_x, test_x, train_y, test_y = train_test_split(imgs, labs, test_size=0.05, random_state=random.randint(0, 100))
#参数：图片数据的总数，图片的高，宽，通道
train_x = train_x.reshape(train_x.shape[0], size, size, 3)
test_x = test_x.reshape(test_x.shape[0], size, size, 3)
#将数据转换成小于1的数
train_x = train_x.astype('float32')/255.0
test_x = test_x.astype('float32')/255.0
print('train size:%s, test size:%s' % (len(train_x), len(test_x)))
#图片块，每次取100张图片
batch_size = 20
num_batch = len(train_x) // batch_size
#定义变量及神经网络层
x = tf.compat.v1.placeholder(tf.float32, [None, size, size, 3])
y_ = tf.compat.v1.placeholder(tf.float32, [None, 2])
keep_prob_5 = tf.compat.v1.placeholder(tf.float32)
keep_prob_75 = tf.compat.v1.placeholder(tf.float32)
def weightVariable(shape):
init = tf.compat.v1.random_normal(shape, stddev=0.01)
return tf.Variable(init)
def biasVariable(shape):
init = tf.compat.v1.random_normal(shape)
return tf.Variable(init)
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 2, 2, 1], padding='SAME')
def maxPool(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 1, 1, 1], padding='SAME')
def dropout(x, keep):
return tf.nn.dropout(x, keep)
#定义卷积神经网络框架
def cnnLayer():
#第一层
W1 = weightVariable([3, 3, 3, 32]) #卷积核大小（3，3）， 输入通道（3）， 输出通道（32）
b1 = biasVariable([32])
#卷积
conv1 = tf.nn.relu(conv2d(x, W1)+b1)
#池化
pool1 = maxPool(conv1)
#减少过拟合，随即让某些权重不更新
drop1 = dropout(pool1, keep_prob_5)
#第二层
W2 = weightVariable([3, 3, 32, 64])
b2 = biasVariable([64])
conv2 = tf.nn.relu(conv2d(drop1, W2) + b2)
pool2 = maxPool(conv2)
drop2 = dropout(pool2, keep_prob_5)
#第三层
W3 = weightVariable([3, 3, 64, 64])
b3 = biasVariable([64])
conv3 = tf.nn.relu(conv2d(drop2, W3) + b3)
pool3 = maxPool(conv3)
drop3 = dropout(pool3, keep_prob_5)
#全连接层
Wf = weightVariable([8*16*32, 512])
bf = biasVariable([512])
drop3_flat = tf.reshape(drop3, [-1, 8*16*32])
dense = tf.nn.relu(tf.matmul(drop3_flat, Wf) + bf)
dropf = dropout(dense, keep_prob_75)
#输出层
Wout = weightVariable([512, 2])
bout = weightVariable([2])
#out = tf.matmul(dropf.Wout) + bout
out = tf.add(tf.matmul(dropf, Wout), bout)
return out
#训练模型
def cnnTrain():
out = cnnLayer()
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=out, labels=y_))
train_step = tf.compat.v1.train.AdamOptimizer(0.01).minimize(cross_entropy)
# 比较标签是否相等，再求所有数的平均值，tf。cast(强制转换类型）
accuracy = tf.reduce_mean(tf.cast(tf.equal(tf.argmax(out, 1), tf.argmax(y_, 1)), tf.float32))
# 将loss与accuracy保存以供tensorboard使用
tf.summary.scalar('loss', cross_entropy)
tf.summary.scalar('accuracy', accuracy)
merged_summary_op = tf.compat.v1.summary.merge_all()
# 数据保存期的初始化
saver = tf.compat.v1.train.Saver()
with tf.compat.v1.Session() as sess:
sess.run(tf.compat.v1.global_variables_initializer())
summary_writer = tf.compat.v1.summary.FileWriter('.tmp', graph=tf.compat.v1.get_default_graph())
for n in range(10):
#每次取128（batch_size）张图片
for i in range(num_batch):
batch_x = train_x[i*batch_size: (i+1)*batch_size]
batch_y = train_y[i*batch_size: (i+1)*batch_size]
# 开始训练数据，同时训练3个变量，返回3个数据
_, loss, summary = sess.run([train_step, cross_entropy, merged_summary_op],
feed_dict={x: batch_x, y_: batch_y, keep_prob_5: 0.5, keep_prob_75: 0.75})
summary_writer.add_summary(summary, n*num_batch+i)
#打印损失
print(n*num_batch+i, loss)
if(n*num_batch+i) % 40 == 0:
#获取测试数据的准确率
acc = accuracy.eval({x: test_x, y_: test_y, keep_prob_5: 1.0, keep_prob_75: 1.0})
print(n*num_batch+i, acc)
#由于数据不多，这里设为准确率大于0.80时保存并输出
if acc > 0.8 and n > 2:
saver.save(sess, r'F:\data')
#sys.exit(0)
#print('accuracy less 0.80, exited')
cnnTrain()求问 所有的值之间的逻辑都没有问题 为什么fetch不到有效的r% 求问
以下是报错内容
2021-04-04 19:40:44.269590: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)to use the following CPU instructions in performance-critical operations: AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
Traceback (most recent call last):
File "D:/python PROJRCT/cut test face2.py", line 195, in <module>
cnnTrain()
File "D:/python PROJRCT/cut test face2.py", line 180, in cnnTrain
_, loss, summary = sess.run([train_step, cross_entropy, merged_summary_op],
File "D:\ANACONDA\lib\site-packages\tensorflow\python\client\session.py", line 957, in run
result = self._run(None, fetches, feed_dict, options_ptr,
File "D:\ANACONDA\lib\site-packages\tensorflow\python\client\session.py", line 1165, in _run
fetch_handler = _FetchHandler(
File "D:\ANACONDA\lib\site-packages\tensorflow\python\client\session.py", line 477, in __init__
self._fetch_mapper = _FetchMapper.for_fetch(fetches)
File "D:\ANACONDA\lib\site-packages\tensorflow\python\client\session.py", line 266, in for_fetch
return _ListFetchMapper(fetch)
File "D:\ANACONDA\lib\site-packages\tensorflow\python\client\session.py", line 378, in __init__
self._mappers = [_FetchMapper.for_fetch(fetch) for fetch in fetches]
File "D:\ANACONDA\lib\site-packages\tensorflow\python\client\session.py", line 378, in <listcomp>
self._mappers = [_FetchMapper.for_fetch(fetch) for fetch in fetches]
File "D:\ANACONDA\lib\site-packages\tensorflow\python\client\session.py", line 262, in for_fetch
raise TypeError('Fetch argument %r has invalid type %r' %
TypeError: Fetch argument None has invalid type <class 'NoneType'>
检查一下Fetch argument类型是不是有问题
您好，我是有问必答小助手，你的问题已经有小伙伴为您解答了问题，您看下是否解决了您的问题，可以追评进行沟通哦~
如果有您比较满意的答案 / 帮您提供解决思路的答案，可以点击【采纳】按钮，给回答的小伙伴一些鼓励哦～～
ps:问答VIP仅需29元，即可享受5次/月 有问必答服务，了解详情>>> https://vip.csdn.net/askvip?utm_source=1146287632