def train(lr, batch_size, epoches, keep_prob_value):
# 下载图片
path = './data/'
x_train, y_train, x_val, y_val = read_image.read_img(path)
x = tf.placeholder(tf.float32, [None, w * h * c], name="images")
y_ = tf.placeholder(tf.float32, [None, n_class], name="labels")
keep_prob = tf.placeholder(tf.float32, name="keep_prob")
y = model.model(x, keep_prob)
# Cost function
cross_entropy = tf.reduce_mean(
-tf.reduce_sum(y_ * tf.log(y + 1e-10), reduction_indices=[1]),
name="corss_entropy")
train_step = tf.train.AdamOptimizer(lr).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32),
name="accuracy")
saver = tf.train.Saver()
# Start training
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(epoches):
iters = np.int32(len(x_train) / batch_size) + 1
for j in range(iters):
if j == iters - 1:
batch0 = x_train[j * batch_size:]
batch1 = y_train[j * batch_size:]
else:
batch0 = x_train[j * batch_size:(j + 1) * batch_size]
batch1 = y_train[j * batch_size:(j + 1) * batch_size]
sess.run(train_step,
feed_dict={
x: batch0,
y_: batch1,
keep_prob: keep_prob_value
})
if i % 5 == 0:
train_accuracy = sess.run(accuracy,
feed_dict={
x: batch0,
y_: batch1,
keep_prob: keep_prob_value
})
print("step %d, training accuracy %.6f" % (i, train_accuracy))
# Save model
saver_path = saver.save(sess, "./model/model.ckpt")
print("Model saved in file:", saver_path)
test_accuracy = sess.run(accuracy,
feed_dict={
x: x_val,
y_: y_val,
keep_prob: 1.0
})
print("test accuracy %g" % test_accuracy)
def train(lr, batch_size, epoches, keep_prob_value):
# 读入图片，并进行预处理
path = 'D:\\picbase\\test\\capture_police\\'
x_train, y_train, x_val, y_val = read_image.read_img(path)
#x_train = x_train/255.0
#x_val = x_val/255.0
x = tf.placeholder(tf.float32, [None, w * h], name="images")
y_ = tf.placeholder(tf.float32, [None, 5], name="labels")
keep_prob = tf.placeholder(tf.float32, name="keep_prob")
y = model.model(x, keep_prob)
# Cost function
#cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y), reduction_indices=[1]),name="corss_entropy")
cross_entropy = tf.reduce_mean(-tf.reduce_sum(
y_ * tf.log(tf.clip_by_value(y, 1e-25, 1.0)), reduction_indices=[1]),
name="corss_entropy")
train_step = tf.train.AdamOptimizer(lr).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32),
name="accuracy")
saver = tf.train.Saver()
# Start training
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
while True:
for i in range(epoches + 1):
#每一轮迭代
iters = np.int32(len(x_train) / batch_size) + 1
for j in range(iters):
if j == iters - 1:
batch0 = x_train[j * batch_size:]
batch1 = y_train[j * batch_size:]
else:
batch0 = x_train[j * batch_size:(j + 1) * batch_size]
batch1 = y_train[j * batch_size:(j + 1) * batch_size]
if j == 1:
train_accuracy, cross_ent = sess.run(
[accuracy, cross_entropy],
feed_dict={
x: batch0,
y_: batch1,
keep_prob: keep_prob_value
})
print(
"step %d, training accuracy %g, corss_entropy %g" %
(i, train_accuracy, cross_ent))
# Save model
saver_path = saver.save(
sess,
'D:\\picbase\\test\\model_police\\model.ckpt')
print("Model saved in file:", saver_path)
test_accuracy = sess.run(accuracy,
feed_dict={
x: x_val,
y_: y_val,
keep_prob: 1.0
})
print("test accuracy %g" % test_accuracy)
sess.run(train_step,
feed_dict={
x: batch0,
y_: batch1,
keep_prob: keep_prob_value
})
test_accuracy = sess.run(accuracy,
feed_dict={
x: x_val,
y_: y_val,
keep_prob: 1.0
})
print("test accuracy %g" % test_accuracy)
ask_for_continue = input("Would like to continue training?y/n\n")
if ask_for_continue == 'n':
break
def train(lr, batch_size, epoches, keep_prob_value):
# 读入图片
path = 'images/'
x_train, y_train, x_val, y_val = read_image.read_img(path)
x_train = x_train/255.0 # 图片预处理
x_val = x_val/255.0
x = tf.placeholder(tf.float32, [None, w*h], name="images")
y_ = tf.placeholder(tf.float32, [None, 4], name="labels")
keep_prob = tf.placeholder(tf.float32,name="keep_prob")
y = model.model(x, keep_prob)
# Cost function
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_*tf.log(y),
reduction_indices=[1]),name="corss_entropy")
train_step = tf.train.AdamOptimizer(lr).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name="accuracy")
saver = tf.train.Saver()
#draw data
x_lable=[]
y1_lable=[]
y2_lable=[]
# Start training
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(epoches+1):
iters = np.int32(len(x_train)/batch_size)+1
for j in range(iters):
if j==iters-1:
batch0 = x_train[j*batch_size:]
batch1 = y_train[j*batch_size:]
#print(x_train,y_train)
else:
batch0 = x_train[j*batch_size:(j+1)*batch_size]
batch1 = y_train[j*batch_size:(j+1)*batch_size]
if i%25==0 and j==1:
train_accuracy, cross_ent = sess.run([accuracy, cross_entropy],
feed_dict={x:batch0, y_:batch1,
keep_prob: keep_prob_value})
print("step %d, training accuracy %g, cross_entropy %g" % (i, train_accuracy, cross_ent))
x_lable.append(i)
y1_lable.append(train_accuracy)
y2_lable.append(cross_ent)
# Save model
saver_path = saver.save(sess,"model/model.ckpt")
print("Model saved in file:", saver_path)
test_accuracy = sess.run(accuracy, feed_dict={x:x_val,
y_:y_val,
keep_prob: 1.0})
print("test accuracy %g" % test_accuracy)
sess.run(train_step, feed_dict={x:batch0, y_:batch1,
keep_prob:keep_prob_value})
test_accuracy = sess.run(accuracy, feed_dict={x:x_val,
y_:y_val,
keep_prob: 1.0})
#print("test accuracy %g" % test_accuracy)
fig = plt.figure(figsize=(20,8),dpi=100)
plt.plot(x_lable,y1_lable,'s-',markersize=4,color = 'r',label="train_accuracy",linewidth=2)#s-:方形
plt.plot(x_lable,y2_lable,'o-',markersize=4,color = 'g',label="cross_ent",linewidth=2)#o-:圆形
plt.xlabel("thr number of training")#横坐标名字
plt.ylabel("percentage")#纵坐标名字
plt.legend(loc = "percentage test")#图例
plt.grid(color='b', ls = '-.', lw = 0.25)
plt.show()
plt.savefig('./percentage.jpg')