def train():
"""
Train model
:return:
"""
X = tf.placeholder(tf.float32, [
cfg.CFG['batch_size'], cfg.CFG['image_size'], cfg.CFG['image_size'],
cfg.CFG['image_channel']
],
name='train-input')
Y = tf.placeholder(tf.float32, [None], name='label-input')
train, train_label = generator.get_files('./dataset/')
train_batch, train_label_batch = generator.get_batches(
train, train_label, cfg.CFG["image_size"], cfg.CFG["image_size"],
cfg.CFG["batch_size"], 20)
train_logits = model.model(train_batch, cfg.CFG["batch_size"],
cfg.CFG["classes"])
train_loss = model.losses(train_logits, train_label_batch)
train_op = model.trainning(train_loss, cfg.CFG["learning_rate"])
train_acc = model.evaluation(train_logits, train_label_batch)
sess = tf.Session()
saver = tf.train.Saver(max_to_keep=5)
sess.run(tf.global_variables_initializer())
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
ptar = tqdm(range(50))
for iter in ptar:
if coord.should_stop():
break
image_data, label = sess.run([train_batch, train_label_batch])
# _, tra_loss, tra_acc = sess.run([train_op, train_loss, train_acc])
_, tra_loss, tra_acc = sess.run([train_op, train_loss, train_acc],
feed_dict={
X: image_data,
Y: label
})
ptar.set_description(
"iterative %d times,train loss=%.4f train accuracy = %.4f"
% (iter, tra_loss, tra_acc))
checkpoint_path = cfg.CFG[
'model_path'] + 'flame_dector_%.4f.ckpt' % tra_acc
# print(checkpoint_path)
saver.save(sess, checkpoint_path, global_step=iter)
except tf.errors.OutOfRangeError:
print('Done training')
finally:
coord.request_stop()
coord.join(threads)
def run_training():
# 数据集
train_dir = r'D:\Python\mnist\test_my\big_0_1_4/' # My dir--20170727-csq
# logs_train_dir 存放训练模型的过程的数据，在tensorboard 中查看
logs_train_dir = r'D:\PyCharm_code\Ai\Tensorflow_mooc_note\6\MinstNew\logs\train/'
# 获取图片和标签集
train, train_label = input_data.get_files(train_dir)
# 生成批次
train_batch, train_label_batch = input_data.get_batch(train,
train_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY)
# 进入模型
train_logits = model.inference(train_batch, BATCH_SIZE, N_CLASSES)
# 获取 loss
train_loss = model.losses(train_logits, train_label_batch)
# 训练
train_op = model.trainning(train_loss, learning_rate)
# 获取准确率
train__acc = model.evaluation(train_logits, train_label_batch)
# 合并 summary
summary_op = tf.summary.merge_all()
sess = tf.Session()
# 保存summary
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):
ckpt = tf.train.get_checkpoint_state(logs_train_dir)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
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:
# 每隔2000步保存一下模型，模型保存在 checkpoint_path 中
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()
def train():
with tf.Graph().as_default():
global_step = tf.train.get_or_create_global_step()
images, labels = input.createBatch(tfrecords_name, batch_size)
logits = model.inference(images, batch_size, n_classes)
loss = model.loss(logits, labels)
accuracy = model.evaluation(logits, labels)
train_op = model.trainning(loss, learning_rate, global_step)
class _LoggerHook(tf.train.SessionRunHook):
"""Logs loss and runtime."""
def begin(self):
self._step = -1
self._start_time = time.time()
def before_run(self, run_context):
self._step += 1
#if self._step % log_frequency == 0:
# print(self.run(accuracy))
# print("step %d, accuracy = %.2f"%(self._step ,accuracy))
return tf.train.SessionRunArgs([loss, accuracy
]) # Asks for loss value.
def after_run(self, run_context, run_values):
if self._step % log_frequency == 0:
current_time = time.time()
duration = current_time - self._start_time
self._start_time = current_time
[loss_value, accuracy_value] = run_values.results
#accuracy_value = run_context.accuracy
examples_per_sec = log_frequency * batch_size / duration
sec_per_batch = float(duration / log_frequency)
format_str = (
'%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
'sec/batch)')
print(format_str % (datetime.now(), self._step, loss_value,
examples_per_sec, sec_per_batch))
print('Accuracy = %.2f' % accuracy_value)
with tf.train.MonitoredTrainingSession(
checkpoint_dir=train_dir,
hooks=[
tf.train.StopAtStepHook(last_step=max_steps),
tf.train.NanTensorHook(loss),
tf.train.SummarySaverHook(
save_steps=5,
output_dir=board_dir,
summary_op=tf.summary.merge_all()),
_LoggerHook()
]) as mon_sess:
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=mon_sess, coord=coord)
while not mon_sess.should_stop():
mon_sess.run(train_op)
#print('dont stop')
coord.request_stop()
coord.join(threads)
def run_training():
# dataset
train_dir = '/Users/xcliang/PycharmProjects/cats_vs_dogs/data/train/' # My dir--20170727-csq
# logs_train_dir store the data of the process of training model, view in tensorbpard
logs_train_dir = '/Users/xcliang/PycharmProjects/cats_vs_dogs/data/saveNet'
# Get images and tag sets
train, train_label = input_data.get_files(train_dir)
# Generate batch
train_batch, train_label_batch = input_data.get_batch(train,
train_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY)
# Entering the model
train_logits = model.inference(train_batch, BATCH_SIZE, N_CLASSES)
# Get loss
train_loss = model.losses(train_logits, train_label_batch)
# train
train_op = model.trainning(train_loss, learning_rate)
# Get accuracy
train__acc = model.evaluation(train_logits, train_label_batch)
# merge summary
summary_op = tf.summary.merge_all()
sess = tf.Session()
# save summary
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:
# Save the model every 2000 steps and save the model in checkpoint_path
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()
def run_training():
'''
'''
'''
tf.train.Coordinator和tf.train.start_queue_runners貌似都要在sess.run之前使用,不然会无法运行
try:这些语法貌似是模板,直接使用就好
'''
# you need to change the directories to yours.
train_dir = '/home/kevin/tensorflow/cats_vs_dogs/data/train/'
logs_train_dir = '/home/kevin/tensorflow/cats_vs_dogs/logs/train/'
train, train_label = input_data.get_files(train_dir)
train_batch, train_label_batch = input_data.get_batch(
train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
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() #和下面的queue_runners配合使用,发生错误可以正确关闭线程
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:
# When done, ask the threads to stop.
coord.request_stop()
# Wait for threads to finish.
coord.join(threads)
sess.close()
def run_training():
# you need to change the directories to yours.
s_train_dir = '/home/hrz/projects/tensorflow/emotion/ck+/CK+YuanTu'
T_train_dir = '/home/hrz/projects/tensorflow/emotion/ck+/CK+X_mid'
logs_train_dir = '/home/hrz/projects/tensorflow/emotion/ck+'
s_train, s_train_label = input_data.get_files(s_train_dir)
s_train_batch, s_train_label_batch = input_data.get_batch(
s_train, s_train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
T_train, T_train_label = input_data.get_files(T_train_dir)
T_train_batch, T_train_label_batch = input_data.get_batch(
T_train, T_train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
train_logits = model.inference(s_train_batch, T_train_batch, BATCH_SIZE,
N_CLASSES)
train_loss = model.losses(train_logits, s_train_label_batch)
train_op = model.trainning(train_loss, learning_rate)
train__acc = model.evaluation(train_logits, s_train_label_batch)
summary_op = tf.summary.merge_all() #汇总操作
sess = tf.Session() #定义sess
train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph) #
saver = tf.train.Saver() #保存操作
sess.run(tf.global_variables_initializer()) #初始化所有变量
coord = tf.train.Coordinator() #设置多线程协调器
threads = tf.train.start_queue_runners(
sess=sess, coord=coord) #开始Queue Runners(队列运行器)
#开始训练过程
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))
#运行汇总操作，写入汇总
summary_str = sess.run(summary_op)
train_writer.add_summary(summary_str, step)
if step % 800 == 0 or (step + 1) == MAX_STEP:
#保存当前模型和权重到 logs_train_dir,global_step为当前迭代次数
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()
def fit():
train_logits1, train_logits2, train_logits3, train_logits4, train_logits5, train_logits6, train_logits7 = model.inference(
image_holder, keep_prob)
train_loss1, train_loss2, train_loss3, train_loss4, train_loss5, train_loss6, train_loss7 = model.losses(
train_logits1, train_logits2, train_logits3, train_logits4,
train_logits5, train_logits6, train_logits7, label_holder)
train_op1, train_op2, train_op3, train_op4, train_op5, train_op6, train_op7 = model.trainning(
train_loss1, train_loss2, train_loss3, train_loss4, train_loss5,
train_loss6, train_loss7, learning_rate)
train_acc = model.evaluation(train_logits1, train_logits2, train_logits3,
train_logits4, train_logits5, train_logits6,
train_logits7, label_holder)
input_image = tf.summary.image('input', image_holder)
summary_op = tf.summary.merge(tf.get_collection(tf.GraphKeys.SUMMARIES))
sess = tf.Session()
train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph)
saver = tf.train.Saver()
sess.run(tf.global_variables_initializer())
start_time1 = time.time()
for step in range(count):
x_batch, y_batch = get_batch()
start_time2 = time.time()
time_str = datetime.datetime.now().isoformat()
feed_dict = {
image_holder: x_batch,
label_holder: y_batch,
keep_prob: 0.5
}
_, _, _, _, _, _, _, tra_loss1, tra_loss2, tra_loss3, tra_loss4, tra_loss5, tra_loss6, tra_loss7, acc, summary_str = sess.run(
[
train_op1, train_op2, train_op3, train_op4, train_op5,
train_op6, train_op7, train_loss1, train_loss2, train_loss3,
train_loss4, train_loss5, train_loss6, train_loss7, train_acc,
summary_op
], feed_dict)
train_writer.add_summary(summary_str, step)
duration = time.time() - start_time2
tra_all_loss = tra_loss1 + tra_loss2 + tra_loss3 + tra_loss4 + tra_loss5 + tra_loss6 + tra_loss7
# print(y_batch) #仅测试代码训练实际样本与标签是否一致
if step % 10 == 0:
sec_per_batch = float(duration)
print('%s : Step %d,train_loss = %.2f,acc= %.2f,sec/batch=%.3f' %
(time_str, step, tra_all_loss, acc, sec_per_batch))
if step % 10000 == 0 or (step + 1) == count:
checkpoint_path = os.path.join(logs_train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
sess.close()
print(time.time() - start_time1)
def run_training():
#train set path
train_dir = '/raidHDD/experimentData/Dev/Knife/hackthon/upup7/'
#output model path
logs_train_dir = '/raidHDD/experimentData/Dev/Knife/hackthon/modelX'
if removeLogFIle:
if os.path.exists(logs_train_dir):
for logFile in os.listdir(logs_train_dir):
os.remove("{0}/{1}".format(logs_train_dir, logFile))
print("Delete Log file success...")
train, train_label = input_data.get_files(train_dir)
train_batch, train_label_batch = input_data.get_batch(
train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
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()
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.8 #0.8 =GPU_memory usage
sess = tf.Session(config=config)
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)
train_writer.flush()
#only save end model
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()
coord.join(threads)
sess.close()
def run_training():
train_dir = "/home/sxy/PycharmProjects/defect2/data/train"
logs_train_dir = "/home/sxy/PycharmProjects/defect2/logs/train-4"
tf.reset_default_graph()
train, train_label = input_data.get_files(train_dir)
train_batch, train_label_batch = input_data.get_batch(
train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
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)
#测试准确率
# test_dir="/home/sxy/PycharmProjects/defect2/data/test"
# test,test_label=input_data.get_files(test_dir)
# test_batch,test_label_batch=input_data.get_batch(test,
# test_label,
# IMG_W,
# IMG_H,
# BATCH_SIZE,
# CAPACITY)
# test_logits = model.inference(test_batch, BATCH_SIZE, N_CLASSES)
# train_loss = model.losses(test_logits, test_label_batch)
# train_op = model.trainning(train_loss, learning_rate)
# train_acc = model.evaluation(test_logits, test_label_batch)
summary_op = tf.merge_all_summaries()
sess = tf.Session()
train_writer = tf.train.SummaryWriter(logs_train_dir, sess.graph)
saver = tf.train.Saver()
sess.run(tf.initialize_all_variables())
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))
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()
def run_training():
starttime = datetime.datetime.now()
# you need to change the directories to yours.
train_dir = 'D:\\Thesis\\sample_patch\\6110_4_0\\*\\*.tif'
logs_train_dir = 'D:\\Thesis\\classify\\6110_4_0\\logs\\train'
train_image, train_label= input_data.new_getfiles(train_dir)
train_image = input_data.read_images(train_image,R_Size)
train_batch, train_label_batch = input_data.get_batch(train_image,
train_label,
BATCH_SIZE,
CAPACITY)
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()
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
sess = tf.Session(config=config) # allowing dynamic memory growth as follows
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)
test = coord.should_stop()
try:
for step in np.arange(MAX_STEP):
if test:
break
_, tra_loss, tra_acc = sess.run([train_op, train_loss, train__acc])
if step % 1 == 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 % 100 == 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()
endtime=datetime.datetime.now()
print(endtime-starttime).seconds
def run_training():
# 调用input_data文件的get_files()函数获得image_list, label_list
train, train_label = input_data.get_files(train_dir)
# 获得image_batch, label_batch
train_batch, train_label_batch = input_data.get_batch(
train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
# 进行前向训练，获得回归值
train_logits = model.inference(train_batch, BATCH_SIZE, N_CLASSES)
# 计算获得损失值loss
train_loss = model.losses(train_logits, train_label_batch)
# 对损失值进行优化
train_op = model.trainning(train_loss, learning_rate)
# 根据计算得到的损失值，计算出分类准确率
train__acc = model.evaluation(train_logits, train_label_batch)
# 将图形、训练过程合并在一起
summary_op = tf.summary.merge_all()
# 新建会话
sess = tf.Session()
# 将训练日志写入到logs_train_dir的文件夹内
train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph)
# 保存变量
saver = tf.train.Saver()
# 执行训练过程，初始化变量
sess.run(tf.global_variables_initializer())
# 创建一个线程协调器，用来管理之后在Session中启动的所有线程
coord = tf.train.Coordinator()
# 启动入队的线程，一般情况下，系统有多少个核，就会启动多少个入队线程（入队具体使用多少个线程在tf.train.batch中定义）;
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
for step in np.arange(MAX_STEP):
# 使用 coord.should_stop()来查询是否应该终止所有线程，当文件队列（queue）中的所有文件都已经读取出列的时候，
# 会抛出一个 OutofRangeError 的异常，这时候就应该停止Sesson中的所有线程了;
if coord.should_stop():
break
_, tra_loss, tra_acc = sess.run([train_op, train_loss, train__acc])
# 每50步打印一次损失值和准确率
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)
# 每2000步保存一次训练得到的模型
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)
# 如果读取到文件队列末尾会抛出此异常
except tf.errors.OutOfRangeError:
print('Done training -- epoch limit reached')
finally:
coord.request_stop() # 使用coord.request_stop()来发出终止所有线程的命令
coord.join(threads) # coord.join(threads)把线程加入主线程，等待threads结束
def run_training():
# you need to change the directories to yours.
train_dir = './data/train/train/'
logs_train_dir = './logs/'
train, train_label = input_data.get_files(train_dir)
train_batch, train_label_batch = input_data.get_batch(
train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
with tf.name_scope("training"):
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 % 20 == 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) #保存模型和模型参数到logs_train_dir文件夹
except tf.errors.OutOfRangeError:
print('Done training -- epoch limit reached')
finally:
coord.request_stop()
coord.join(threads)
sess.close()
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/scy/eclipse-workspace/PythonProject/src/12yue3ri/logs/'
#
# train, train_label = input_data.get_files(train_dir)
tfrecords_file = '/home/scy/eclipse-workspace/PythonProject/src/12yue3ri/my_train2.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 % 5 == 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)
saver.save(sess, 'net/mydataset_net.ckpt')
# if step % 4 == 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()
def run_training():
train_dir = './train/' # 加载数据训练
logs_train_dir = './save_model/' # 储存训练好的位置
train, train_label = input_data.get_files(train_dir)
train_batch, train_label_batch = input_data.get_batch(train,
train_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY)
train_logits = model.inference(train_batch, BATCH_SIZE, N_CLASSES,True) # forward pass
train_loss = model.losses(train_logits, train_label_batch) # 设置损失函数
train_op = model.trainning(train_loss,learning_rate=) # training
train__acc = model.evaluation(train_logits, train_label_batch) # 验证正确率
summary_op = tf.summary.merge_all() # 定义合并变量操作，一次性生成所有摘要数据
sess = tf.Session() # 初始化会话
train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph) # TensorBoard的记录
saver = tf.train.Saver() # 储存模型
sess.run(tf.global_variables_initializer()) # 所有变量初始化
coord = tf.train.Coordinator() # 多线程
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
csvfile = open('csv.csv', 'w', newline='')
writer = csv.writer(csvfile)
writer.writerow(['name','label'])
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()
def train():
img, label = data.read_and_decode("train.tfrecords")
img_batch, label_batch = data.get_batch(img, label, BATCH_SIZE, CAPACITY)
train_logits = model.inference(img_batch)
# s = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, 'ALexNet')
# print(s)
# for v in s:
# print(v.name)
# exit(0)
train_loss = model.losses(train_logits, label_batch)
train_op = model.trainning(train_loss, learning_rate)
summary_op = tf.summary.merge_all()
sess = tf.Session()
train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph)
saver = tf.train.Saver()
with tf.Session() as sess:
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
im, la = sess.run([img_batch, label_batch])
print(im.shape, la.shape)
cv2.imshow("asdas", im[0, :, :, :])
cv2.waitKey(0)
exit(0)
try:
img, label = sess.run([img_batch, label_batch])
for step in range(MAX_STEP):
if coord.should_stop():
break
_, tra_loss = sess.run([train_op, train_loss])
if step % 50 == 0:
print('Step %d, train loss = %.2f' % (step, tra_loss))
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()
def train():
with tf.device('/cpu:0'):
img, label = data.read_and_decode([tf_file1, tf_file2])
img_batch, label_batch = data.get_batch(img, label, BATCH_SIZE,
CAPACITY)
train_logits, train_weight = model.inference(img_batch)
# s = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, 'ALexNet')
# print(s)
# for v in s:
# print(v.name)
# exit(0)
train_loss = model.losses(train_logits, label_batch)
train_op = model.trainning(train_loss, learning_rate)
summary_op = tf.summary.merge_all()
sess = tf.Session()
train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph)
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
load_parameters("Alexnet.npy", sess, 'Alexnet')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
for step in range(MAX_STEP):
if coord.should_stop():
break
_, tra_loss = sess.run([train_op, train_loss])
if step % 50 == 0:
# tra_weight.imshow()
print('Step %d, train loss = %.2f, l2 loss = %.2f' %
(step, tra_loss, tra_loss))
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()
def run_train(image_batch, label_batch, n_class, batch_size, checkpoint_dir,
lr, MAX_STEP):
print('{:*^70}'.format('【train starting!】'))
global result
if args.inference == '2D':
result = inference(image_batch, batch_size, n_class)
elif args.inference == '1D':
result = inference1D(image_batch, batch_size, n_class)
else:
print('【Unknown error】')
print('{:*^70}'.format('DEBUG'))
train_loss = losses(result[-1], label_batch)
train_op = trainning(train_loss, lr)
train__acc = evaluation(result[-1], label_batch)
summary_op = tf.summary.merge_all()
sess = tf.Session()
train_writer = tf.summary.FileWriter(checkpoint_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(checkpoint_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()
print('{:*^70}'.format(' train ending! '))
def run_training():
DIR_PRE = os.getcwd() + '/'
train_dir = DIR_PRE + 'data/train/'
logs_train_dir = DIR_PRE + 'logs/train/'
os.makedirs(train_dir, exist_ok=True)
os.makedirs(logs_train_dir, exist_ok=True)
# 获取所有图片文件列表和对应的标签列表
train, train_label = input_data.get_files(train_dir)
#
train_batch, train_label_batch = input_data.get_batch(
train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
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()
def run_training():
# you need to change the directories to yours.
train_dir = '/home/kevin/tensorflow/cats_vs_dogs/data/train/'
logs_train_dir = '/home/kevin/tensorflow/cats_vs_dogs/logs/train/'
train, train_label = input_data.get_files(train_dir)
train_batch, train_label_batch = input_data.get_batch(train,
train_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY)
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()
def run_training():
# you need to change the directories to yours.
# train_dir = '/home/kevin/tensorflow/hams_vs_hots/data/train/'
train_dir = 'D:/workspace/uploadPicJudge3Class/train/'
# logs_train_dir = '/home/kevin/tensorflow/hams_vs_hots/logs/train/'
logs_train_dir = 'D:/workspace/uploadPicJudge3Class/logs/'
train, train_label = input_data.get_files(train_dir)
train_batch, train_label_batch = input_data.get_batch(
train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
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 % 10 == 0:
print('Step %d, train loss = %.2f, train accuracy = %.2f%%' %
(step, tra_loss, tra_acc * 100.0) + ' ' +
datetime.datetime.now().strftime('%Y-%m-%d %H_%M_%S'))
summary_str = sess.run(summary_op)
train_writer.add_summary(summary_str, step)
if step % 100 == 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()
def run_training():
train_dir = "./data/TRAIN/"
logs_train_dir = "./logs/"
train, train_label = input_data.get_files(train_dir)
train_batch, train_label_batch = input_data.get_batch(train,train_label,IMG_W,IMG_H,BATCH_SIZE,CAPACITY)
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 % 100 == 0:
print('Step:', step, 'train loss:', tra_loss, 'train accuracy:', tra_acc)
summary_str = sess.run(summary_op)
train_writer.add_summary(summary_str, step)
if tra_acc > 0.95 and step>6000:
checkpoint_path = os.path.join(logs_train_dir, "model")
saver.save(sess, checkpoint_path, global_step=step)
print("train success!")
print('Step:', step, 'train loss:', tra_loss, 'train accuracy:', tra_acc)
coord.request_stop()
except tf.errors.OutOfRangeError:
print("Done training -- epoch limit reached.")
finally:
coord.request_stop()
coord.join(threads)
sess.close()
def run_training(w1, b1, w2, b2, w3, b3, w4, b4, w5, b5):
train, train_label = get_data.get_zacao_input(train_dir, label_dir)
train_batch, train_label_batch = get_data.get_batch_jpg(
train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
train_logits = model.inference(train_batch, BATCH_SIZE, N_CLASSES, w1, b1,
w2, b2, w3, b3, w4, b4, w5, b5)
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)
step = 0
ckpt = tf.train.get_checkpoint_state(logs_train_dir)
if ckpt and ckpt.model_checkpoint_path:
step = int(ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1])
saver.restore(sess, ckpt.model_checkpoint_path)
print('Loading success, global_step is %d' % step)
step += 1
try:
while step < MAX_STEP:
if coord.should_stop():
break
_, tra_loss, tra_acc, summary_str = sess.run(
[train_op, train_loss, train__acc, summary_op])
train_writer.add_summary(summary_str, step)
if step % 50 == 0 or step + 1 == MAX_STEP:
print('Step %d, train loss = %.2f, train accuracy = %.2f%%' %
(step, tra_loss, tra_acc * 100.0))
if step % 1000 == 0 or step + 1 == MAX_STEP:
checkpoint_path = os.path.join(logs_train_dir, 'model')
saver.save(sess, checkpoint_path, global_step=step)
step += 1
except tf.errors.OutOfRangeError:
print('Done training -- epoch limit reached')
finally:
coord.request_stop()
coord.join(threads)
sess.close()
def run_training1():
logs_train_dir = dataDir + '/logs/recordstrain/'
#
# train, train_label = input_data.get_files(train_dir)
tfrecords_file = 'Idcard_train.tfrecords'
train_batch, train_label_batch = 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()
def run_training():
print 'let us begin....'
train_dir = '../data/train/'
logs_train_dir = './train/'
train, train_label = input_data.get_files(train_dir)
train_batch, train_label_batch = input_data.get_batch(
train, train_label, IMG_H, IMG_W, BATCH_SIZE, CAPACITY)
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, lr)
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():
print 'coord 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\n' % (
step, tra_loss, tra_acc * 100.0)
summary_str = sess.run(summary_op)
train_writer.add_summary(summary_str, step)
if step % 2500 == 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()
def run_training():
train_dir = '/home/fengyu/python_workspace/cats_vs_dogs/picData/train/train/'
logs_traing_dir = '/home/fengyu/python_workspace/cats_vs_dogs/logs/'
train, train_label = input_data.get_files(train_dir)
train_batch, train_label_batch = input_data.get_batch(
train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
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_accuracy = model.evaluation(train_logits, train_label_batch)
summary_op = tf.summary.merge_all()
sess = tf.Session()
train_writer = tf.summary.FileWriter(logs_traing_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_accuracy = sess.run(
[train_op, train_loss, train_accuracy])
if step % 50 == 0:
print 'Step %d, train loss = %.2f, accuracy = %.2f' % (
step, tra_loss, tra_accuracy)
summary_str = sess.run(summary_op)
train_writer.add_summary(summary_str, step)
if step % 2000 == 0 or (step + 1) == MAX_STEP:
check_point_path = os.path.join(logs_traing_dir, 'model.ckpt')
saver.save(sess, check_point_path, global_step=step)
except tf.errors.OutOfRangeError:
print 'Done training -- epoch limit reached'
finally:
coord.request_stop()
coord.join(threads)
sess.close()
def run_training():
train_dir = 'F://CAE_CNN//data//train_imgs//'
#产生一些文件，可以用tensorboard查看
logs_train_dir = 'F://CAE_CNN//log//train//'
#读取数据
train, train_label = input_data.get_files(train_dir)
#获得batch
train_batch, train_label_batch = input_data.get_batch(
train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
#参数传景区
train_logits = model.inference(train_batch, BATCH_SIZE, N_CLASSES)
train_loss = model.losses(train_logits, train_label_batch)
#训练
train_op = model.trainning(train_loss, learning_rate)
train__acc = model.evaluation(train_logits, train_label_batch)
#merge到一块？
summary_op = tf.summary.merge_all() # 这个是log汇总记录
# 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)
# 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)
for step in np.arange(MAX_STEP):
_, 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 % 2 == 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2000步，保存一次训练好的模型
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)
def run_training():
# you need to change the directories to yours.
logs_train_dir = './logs/train/'
train_batch, train_label_batch = read_and_decode('./data/train.tfrecords',
batch_size=BATCH_SIZE)
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())
tf.reset_default_graph()
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('./model/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()
print("training is done")
def run_training():
train_dir = '/home/zhangch/RSS/train_set/'
logs_train_dir = '/home/zhangch/RSS/log/'
train, train_label = input_data.get_files(train_dir)
train_batch, train_label_batch = input_data.get_batch(
train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
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.evalution(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(max_to_keep=2100)
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 % 100 == 0:
print("Step %d,train loss = %.2f,train accuracy = %.2f" %
(step, tra_loss, tra_acc))
summary_str = sess.run(summary_op)
train_writer.add_summary(summary_str, step)
if step % 200 == 0 or (step + 1) == MAX_STEP:
checkpoin_path = os.path.join(logs_train_dir, 'model.ckpt')
saver.save(sess, checkpoin_path, global_step=step)
except tf.errors.OutOfRangeError:
print('Done train')
finally:
coord.request_stop()
coord.join(threads)
sess.close()
def run_training():
train_dir = "E:/tensorflow_model/cats_vs_dogs/data/train/"
logs_train_dir = "E:/tensorflow_model/cats_vs_dogs/logs/"
#train,train_label接收每张图片的路径列表和标签列表
train, train_label = input_data.get_files(train_dir)
train_batch, train_label_batch = input_data.get_batch(
train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
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 % 100 == 0:
print("Step %d, train loss = %.2f, train accuracy = %.2f" %
(step, tra_loss, tra_acc))
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()
def train(tf_file, logs_train_dir):
filenames = tf.placeholder(tf.string, shape=[None])
training_filenames = tf_file
with tf.device('/cpu:0'):
iterator = data.read_and_decode(filenames, BATCH_SIZE, True)
sess = tf.Session()
sess.run(iterator.initializer, feed_dict={filenames: training_filenames})
tra_img, tra_label = iterator.get_next()
train_logits, train_weight = model.inference(tra_img)
train_loss = model.losses(train_logits, tra_label)
train_op = model.trainning(train_loss, learning_rate)
load_parameters("Alexnet.npy", sess, 'Alexnet')
summary_op = tf.summary.merge_all()
sess.run(tf.global_variables_initializer())
train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph)
saver = tf.train.Saver()
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
for step in range(MAX_STEP):
if coord.should_stop():
break
_, tra_loss = sess.run([train_op, train_loss])
if step % 50 == 0:
# tra_weight.imshow()
print('Step %d, train loss = %.2f, l2 loss = %.2f' %
(step, tra_loss, tra_loss))
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()
def running_train(data_dir, log_dir, max_step=10000, batch_size=16, lr=0.05):
'''
'''
image_batch, label_batch = input_data.read_files(data_dir,
batchsize=batch_size)
print label_batch
logits = model.inference(image_batch, batch_size=batch_size)
loss = model.losses(logits, label_batch)
train_op = model.trainning(loss, lr=lr)
summary_op = tf.summary.merge_all()
sess = tf.Session()
train_writer = tf.summary.FileWriter(log_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 = sess.run([train_op, loss])
if step % 50 == 0:
print('Step %d, train loss = %.2f' % (step, tra_loss))
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(log_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()
def training():
train, train_label, val, val_label = input_data.get_files(train_dir, RATIO)
train_batch, train_label_batch = input_data.get_batch(train,
train_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY)
val_batch, val_label_batch = input_data.get_batch(val,
val_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY)
logits = model.inference(train_batch, BATCH_SIZE, N_CLASSES)
loss = model.losses(logits, train_label_batch)
train_op = model.trainning(loss, learning_rate)
acc = model.evaluation(logits, train_label_batch)
x = tf.placeholder(tf.float32, shape=[BATCH_SIZE, IMG_W, IMG_H, 3])
y_ = tf.placeholder(tf.int16, shape=[BATCH_SIZE])
with tf.Session() as sess:
saver = tf.train.Saver()
sess.run(tf.global_variables_initializer())
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess= sess, coord=coord)
summary_op = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(train_logs_dir, sess.graph)
val_writer = tf.summary.FileWriter(val_logs_dir, sess.graph)
try:
for step in np.arange(MAX_STEP):
if coord.should_stop():
break
tra_images,tra_labels = sess.run([train_batch, train_label_batch])
_, tra_loss, tra_acc = sess.run([train_op, loss, acc],
feed_dict={x:tra_images, y_:tra_labels})
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 % 200 == 0 or (step + 1) == MAX_STEP:
val_images, val_labels = sess.run([val_batch, val_label_batch])
val_loss, val_acc = sess.run([loss, acc],
feed_dict={x:val_images, y_:val_labels})
print('** Step %d, val loss = %.2f, val accuracy = %.2f%% **' %(step, val_loss, val_acc*100.0))
summary_str = sess.run(summary_op)
val_writer.add_summary(summary_str, step)
if step % 2000 == 0 or (step + 1) == MAX_STEP:
checkpoint_path = os.path.join(train_logs_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)
def run_training():
# you need to change the directories to yours.
s_train_dir = '/home/hrz/projects/tensorflow/emotion/ck+/CK+YuanTu'
T_train_dir = '/home/hrz/projects/tensorflow/emotion/ck+/CK+X_mid'
logs_train_dir = '/home/hrz/projects/tensorflow/emotion/ck+'
s_train, s_train_label = input_data.get_files(s_train_dir)
s_train_batch, s_train_label_batch = input_data.get_batch(s_train,
s_train_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY)
T_train, T_train_label = input_data.get_files(T_train_dir)
T_train_batch, T_train_label_batch = input_data.get_batch(T_train,
T_train_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY)
train_logits = model.inference(s_train_batch,T_train_batch, BATCH_SIZE, N_CLASSES)
train_loss = model.losses(train_logits, s_train_label_batch)
train_op = model.trainning(train_loss, learning_rate)
train__acc = model.evaluation(train_logits, s_train_label_batch)
summary_op = tf.summary.merge_all() #汇总操作
sess = tf.Session() #定义sess
train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph) #
saver = tf.train.Saver() #保存操作
sess.run(tf.global_variables_initializer())#初始化所有变量
coord = tf.train.Coordinator() #设置多线程协调器
threads = tf.train.start_queue_runners(sess=sess, coord=coord) #开始Queue Runners(队列运行器)
#开始训练过程
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))
#运行汇总操作，写入汇总
summary_str = sess.run(summary_op)
train_writer.add_summary(summary_str, step)
if step % 800 == 0 or (step + 1) == MAX_STEP:
#保存当前模型和权重到 logs_train_dir,global_step为当前迭代次数
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()
s_train_dir = '/home/hrz/projects/tensorflow/emotion/ck+/CK+YuanTu'
T_train_dir = '/home/hrz/projects/tensorflow/emotion/ck+/CK+X_mid'
logs_train_dir = '/home/hrz/projects/tensorflow/emotion/ck+'
s_train, s_train_label = input_data.get_files(s_train_dir)
#print(s_train)
s_train_batch, s_train_label_batch = input_data.get_batch(s_train,
s_train_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY)
#print(s_train_label_batch)
T_train, T_train_label = input_data.get_files(T_train_dir)
T_train_batch, T_train_label_batch = input_data.get_batch(T_train,
T_train_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY)
#print(len(s_train),len(s_train_label),len(T_train),len(T_train_label))
#print(s_train_batch,s_train_label_batch,T_train_batch,s_train_label_batch)
train_logits = model.inference(s_train_batch,T_train_batch, BATCH_SIZE, N_CLASSES)
train_loss = model.losses(train_logits, s_train_label_batch)
train_op = model.trainning(train_loss, learning_rate)
#correct_prediction = tf.equal(tf.argmax(train_logits,1),tf.argmax(y_,1))
labels_max = tf.reduce_max(s_train_label_batch)
sess = tf.Session()
print(sess.run(labels_max))