def train_running():
with tf.name_scope('input'):
train_batch, train_label_batch, _ = input_data.get_batch(train_txt, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
val_batch, val_label_batch, _ = input_data.get_batch(val_txt, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
x = tf.placeholder(tf.float32, shape=[BATCH_SIZE, IMG_W, IMG_H, 3])
y_ = tf.placeholder(tf.int32, shape=[BATCH_SIZE])
model = models.model(x, N_CLASSES)
model.AlexNet()
logits = model.fc3
loss = tools.loss(logits, y_)
acc = tools.accuracy(logits, y_)
train_op = tools.optimize(loss, LEARNING_RATE)
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(logs_train_dir, sess.graph)
val_writer = tf.summary.FileWriter(logs_val_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 = %.4f, train accuracy = %.2f%%' % (step, tra_loss, tra_acc))
summary_str = sess.run(summary_op, feed_dict={x: tra_images, y_: tra_labels})
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 = %.4f, val accuracy = %.2f%% **' % (step, val_loss, val_acc))
summary_str = sess.run(summary_op, feed_dict={x: val_images, y_: val_labels})
val_writer.add_summary(summary_str, step)
#
if step % 2000 == 0 or (step + 1) == MAX_STEP:
checkpoint_path = os.path.join(model_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()
def train_running():
with tf.variable_scope('input'):
train_batch, train_label_batch, _ = input_data.get_batch(train_txt, model.config.img_w, model.config.img_h, BATCH_SIZE, CAPACITY)
val_batch, val_label_batch, _ = input_data.get_batch(val_txt, model.config.img_w, model.config.img_h, BATCH_SIZE, CAPACITY)
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(logs_train_dir, sess.graph)
val_writer = tf.summary.FileWriter(logs_val_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([model.loss, model.acc, model.optim],
feed_dict={model.input_x: tra_images, model.input_y: tra_labels,
model.keep_prob: 0.5, model.batch_size: BATCH_SIZE})
if step % 50 == 0:
print('Step %d, train loss = %.4f, train accuracy = %.2f%%' % (step, tra_loss, tra_acc))
summary_str = sess.run(summary_op,
feed_dict={model.input_x: tra_images, model.input_y: tra_labels,
model.keep_prob: 0.5, model.batch_size: BATCH_SIZE})
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([model.loss, model.acc],
feed_dict={model.input_x: val_images, model.input_y: val_labels,
model.keep_prob: 1.0, model.batch_size: BATCH_SIZE})
print('** Step %d, val loss = %.4f, val accuracy = %.2f%% **' % (step, val_loss, val_acc))
summary_str = sess.run(summary_op,
feed_dict={model.input_x: val_images, model.input_y: val_labels,
model.keep_prob: 1.0, model.batch_size: BATCH_SIZE})
val_writer.add_summary(summary_str, step)
#
if step % 2000 == 0 or (step + 1) == MAX_STEP:
checkpoint_path = os.path.join(model_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 evaluate_running():
with tf.Graph().as_default():
data_dir = './data/KTH_RGB/'
model_dir = './model/KTH_RGB6000/'
train_image, train_label, val_image, val_label, n_test = input_data.get_files(
data_dir, RATIO, ret_val_num=True)
train_batch, train_label_batch = input_data.get_batch(
train_image, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
val_batch, val_label_batch = input_data.get_batch(
val_image, val_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
#
logits = models.AlexNet(val_batch, N_CLASSES)
top_k_op = tf.nn.in_top_k(logits, val_label_batch, 1)
saver = tf.train.Saver(tf.global_variables())
with tf.Session() as sess:
print("Reading checkpoints...")
ckpt = tf.train.get_checkpoint_state(model_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')
return
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
num_iter = int(math.ceil(n_test / BATCH_SIZE))
true_count = 0
total_sample_count = num_iter * BATCH_SIZE
step = 0
while step < num_iter and not coord.should_stop():
val_images_, val_labels_ = sess.run(
[val_batch, val_label_batch])
predictions = sess.run([top_k_op])
true_count += np.sum(predictions)
step += 1
precision = true_count / total_sample_count
print('precision = %.3f' % precision)
except Exception as e:
coord.request_stop(e)
finally:
coord.request_stop()
coord.join(threads)
def run_training():
traindir = 'data/train/'
logs_train_dir = 'logs/train/'
train_image, train_label = input_data.get_files(traindir)
train_batch, train_label_batch = input_data.get_batch(
train_image, 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.training(train_loss, learning_rate)
train_acc = model.evaluation(train_logits, train_label_batch)
sess = tf.Session()
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 range(MAX_STEP):
if coord.should_stop():
break
_, tra_loss, tra_acc = sess.run([train_op, train_loss, train_acc])
if step % 20 == 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(N_CLASSES, IMG_W, IMG_H, BATCH_SIZE, MAX_STEP, CAPACITY,
model1_data, learning_rate, total):
train, train_label, randomList = input_data.get_files(model1_data, total)
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)
return train_logits, train_batch, train_label_batch, randomList
def conv_feature_extract(txtfile):
with tf.Graph().as_default():
batch, label_batch, n = input_data.get_batch(txtfile, IMG_W, IMG_H,
BATCH_SIZE, CAPACITY)
x = tf.placeholder(tf.float32, shape=[BATCH_SIZE, IMG_W, IMG_H, 3])
model = models.model(x, N_CLASSES)
model.AlexNet() #### notice
feature = model.conv1
saver = tf.train.Saver(tf.global_variables())
with tf.Session() as sess:
print("Reading checkpoints...")
ckpt = tf.train.get_checkpoint_state(model_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')
return
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
num_iter = int(math.ceil(n / BATCH_SIZE))
step = 0
while step < num_iter and not coord.should_stop():
images, labels = sess.run([batch, label_batch])
feature_map = sess.run([feature], feed_dict={x: images})
feature_map = np.array(feature_map)
feature_map = np.squeeze(feature_map)
if step == 0:
tools.print_all_variables()
print("batch %d-0: feature map------------------------" %
step)
tools.plot_feature_map(feature_map)
step = step + 1
except Exception as e:
coord.request_stop(e)
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 evaluate_running():
with tf.Graph().as_default():
val_batch, val_label_batch, n_test = input_data.get_batch(
val_txt, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
x = tf.placeholder(tf.float32, shape=[BATCH_SIZE, IMG_W, IMG_H, 3])
y_ = tf.placeholder(tf.int32, shape=[BATCH_SIZE])
model = models.model(x, N_CLASSES)
model.AlexNet() #### notice
logits = model.fc3
top_k_op = tf.nn.in_top_k(logits, y_, 1)
saver = tf.train.Saver(tf.global_variables())
with tf.Session() as sess:
print("Reading checkpoints...")
ckpt = tf.train.get_checkpoint_state(model_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')
return
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
num_iter = int(math.ceil(n_test / BATCH_SIZE))
true_count = 0
total_sample_count = num_iter * BATCH_SIZE
step = 0
while step < num_iter and not coord.should_stop():
val_images, val_labels = sess.run(
[val_batch, val_label_batch])
predictions = sess.run([top_k_op],
feed_dict={
x: val_images,
y_: val_labels
})
true_count += np.sum(predictions)
step += 1
precision = true_count / total_sample_count * 100.0
print('precision = %.2f%%' % precision)
except Exception as e:
coord.request_stop(e)
finally:
coord.request_stop()
coord.join(threads)
def run_evaluating():
eval_data, eval_label = input_data.get_files(FLAGS.eval_dir)
eval_batch, eval_label_batch = input_data.get_batch(
eval_data, eval_label, FLAGS.height, FLAGS.width, FLAGS.batch_size,
FLAGS.capacity)
keep_prob = tf.placeholder(tf.float32)
hypothesis, cross_entropy, eval_step = model.make_network(
eval_batch, eval_label_batch, keep_prob)
cost_sum = tf.summary.scalar("cost_eval", cross_entropy)
eval_accuracy = tf.nn.in_top_k(hypothesis, eval_label_batch, 1)
eval_acc = model.evaluation(hypothesis, eval_label_batch)
saver = tf.train.Saver()
print('Start Evaluation......')
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
total_sample_count = FLAGS.eval_steps * FLAGS.batch_size
true_count = 0
writer = tf.summary.FileWriter(FLAGS.log_dir)
writer.add_graph(sess.graph) # Show the graph
merge_sum = tf.summary.merge_all()
saver.restore(sess, './CNN_Homework/logs/model.ckpt-36000')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
for step in np.arange(FLAGS.eval_steps + 1):
_, summary, eval_loss = sess.run(
[eval_step, merge_sum, cross_entropy],
feed_dict={keep_prob: 1.0})
predictions, accuracy = sess.run([eval_accuracy, eval_acc],
feed_dict={keep_prob: 1.0})
writer.add_summary(summary, global_step=step)
true_count = true_count + np.sum(predictions)
if step % 10 == 0:
print('step : %d, loss : %f, eval_accuracy : %f' %
(step, eval_loss, accuracy * 100))
coord.request_stop()
coord.join(threads)
print('precision : %f' % (true_count / total_sample_count))
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.
train_dir = 'D:/tensorflow/practicePlus/ResNet/train/'
# val_dir = 'D:/tensorflow/practicePlus/cats_vs_dogs/test'
logs_train_dir = 'D:/tensorflow/practicePlus/ResNet/save/'
train, train_label = input_data.get_files(train_dir)
# val, val_label = input_data.get_files(val_dir)
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)
# train
train_logits = model_resnet50.inference(train_batch, BATCH_SIZE, N_CLASSES)
train_loss = model_resnet50.losses(train_logits, train_label_batch)
train_op = model_resnet50.trainning(train_loss, learning_rate)
train_acc = model_resnet50.evaluation(train_logits, train_label_batch)
# validation
# 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)
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)
# batch trainning
try:
# one step one 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])
# print loss and acc each 10 step, record log and write at same time
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)
# save modle each 500 steps
if ((step == 500) 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()
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():
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 evaluate():
with tf.Graph().as_default():
# log_dir = 'C://Users//kevin//Documents//tensorflow//VGG//logsvgg//train//'
data_dir = '/home/viplab/Desktop/Syneh/HW01/data/'
train_log_dir = '/home/viplab/Desktop/Syneh/HW01/code/train_log'
val_log_dir = '/home/viplab/Desktop/Syneh/HW01/code/train_log/val'
n_test = 12776
val_image_list, val_label_list = input_data.read_files(data_dir=data_dir,
is_train=False)
val_image_batch, val_label_batch = input_data.get_batch( val_image_list,
val_label_list,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY)
logits = VGG.VGG16N(val_image_batch, N_CLASSES, IS_PRETRAIN)
correct = tools.num_correct_prediction(logits, val_label_batch)
saver = tf.train.Saver(tf.global_variables())
with tf.Session() as sess:
print("Reading checkpoints...")
ckpt = tf.train.get_checkpoint_state(train_log_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')
return
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess = sess, coord = coord)
try:
print('\nEvaluating......')
num_step = int(math.floor(n_test / BATCH_SIZE))
num_sample = num_step*BATCH_SIZE
step = 0
total_correct = 0
while step < num_step and not coord.should_stop():
batch_correct = sess.run(correct)
total_correct += np.sum(batch_correct)
step += 1
print('Total testing samples: %d' %num_sample)
print('Total correct predictions: %d' %total_correct)
print('Average accuracy: %.2f%%' %(100*total_correct/num_sample))
except Exception as e:
coord.request_stop(e)
finally:
coord.request_stop()
coord.join(threads)
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():
# 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_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 evaluate_all_image():
start_time = time.time()
'''
Test all image against the saved models and parameters.
Return global accuracy of test_image_set
##############################################
##Notice that test image must has label to compare the prediction and real
##############################################
'''
# you need to change the directories to yours.
test_dir = '/Users/sherry/Documents/Study/CS 6220/HW01/HW01_20190901/01_cats_vs_dogs/data/outlier_test/'
N_CLASSES = 2
print('-------------------------')
test, test_label = input_data.get_files(test_dir)
BATCH_SIZE = len(test)
print('There are %d test images totally..' % BATCH_SIZE)
print('-------------------------')
test_batch, test_label_batch = input_data.get_batch(
test, test_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
logits = model.inference(test_batch, BATCH_SIZE, N_CLASSES)
testloss = model.losses(logits, test_label_batch)
testacc = model.evaluation(logits, test_label_batch)
logs_train_dir = '/Users/sherry/Documents/Study/CS 6220/HW01/HW01_20190901/01_cats_vs_dogs/data/logs_dataset1/train/'
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')
print('-------------------------')
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
test_loss, test_acc = sess.run([testloss, testacc])
print('The model\'s loss is %.2f' % test_loss)
correct = int(BATCH_SIZE * test_acc)
print('Correct : %d' % correct)
print('Wrong : %d' % (BATCH_SIZE - correct))
print('The accuracy in test images are %.2f%%' % (test_acc * 100.0))
print(
"------------------------ Testing time is: %s seconds -----------------------"
% (time.time() - start_time))
coord.request_stop()
coord.join(threads)
sess.close()
print("--- Testing time is: %s seconds ---" % (time.time() - start_time))
def test():
test_dir = '/home/saverio_sun/project/chinese_rec_data/test'
keep_prob = 1.0
images, labels = input_data.read_files(test_dir)
num_test = len(labels)
max_step = int(num_test / BATCH_SIZE)
with tf.Graph().as_default():
test_batch, test_label = input_data.get_batch(images, labels, IMG_W,
IMG_H, BATCH_SIZE,
CAPACTIY)
test_logits = network_model.inference(test_batch, BATCH_SIZE, N_CLASS,
keep_prob)
test_acc = network_model.evaluation(logits=test_logits,
labels=test_label)
init = tf.global_variables_initializer()
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(init)
print 'reading checkpoint...'
ckpt = tf.train.get_checkpoint_state(log_dir)
if ckpt and ckpt.model_checkpoint_path:
global_stop = ckpt.model_checkpoint_path.split('/')[-1].split(
'-')[-1]
saver.restore(sess, ckpt.model_checkpoint_path)
print 'load success'
else:
print 'No checkpoint'
print ':::the total number image is {0},step {1}:::'.format(
num_test, max_step)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
acc = 0.0
try:
for step in range(max_step):
if coord.should_stop():
break
tra_acc = sess.run(test_acc)
print 'the step {0} accuracy is {1}'.format(step, tra_acc)
acc += tra_acc
except tf.errors.OutOfRangeError:
print 'done'
finally:
coord.request_stop()
result_accuracy = acc / max_step
print '{0} images , accuracy is {1}'.format(
num_test, result_accuracy)
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():
image, label = decode_from_tfrecords('data/train.tfrecords')
batch_image, batch_label = get_batch(image, label, 96, 227) #生成测试的样例batch
#网络连接，训练所有
net = network()
inf = net.inference(batch_image)
loss = net.softmax_entropy_loss(inf, batch_label)
opti = net.optimize(loss)
#验证集所用
test_image, test_label = decode_from_tfrecords('data/val.tfrecords',
num_epoch=None)
test_images, test_labels = get_test_batch(test_image,
test_label,
batch_size=96,
crop_size=227)
test_inf = net.inference(test_images)
correct_prediction = tf.equal(tf.cast(tf.argmax(test_inf, 1), tf.int32),
test_labels)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
init = tf.global_variables_initializer()
with tf.Session() as session:
session.run(init)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
max_iter = 150
if os.path.exists(os.path.join("model", 'model.ckpt')) is True:
tf.train.Saver(max_to_keep=None).restore(
session, os.path.join("model", 'model.ckpt'))
for l in range(max_iter):
loss_np, _, label_np, image_np = session.run(
[loss, opti, batch_label, batch_image])
# image_np = session.run([batch_image])
print image_np.shape
if l % 5 == 0:
print "Iteration: " + str(iter) + "; Train loss: ", loss_np
if l % 20 == 0:
accuracy_np = session.run([accuracy])
print '***************test accruacy:', accuracy_np, '*******************'
tf.train.Saver(max_to_keep=None).save(
session, os.path.join('model', 'model.ckpt'))
coord.request_stop() #queue需要关闭，否则报错
coord.join(threads)
def test():
global_step=tf.Variable(0,trainable=False)
image, label=decode_from_tfrecords('data/train.tfrecords')
batch_image, batch_label=get_batch(image,label,96,227)
net=network()
inf=net.inference(batch_image)
loss=net.softmax_entropy_loss(inf,batch_label)
learning_rate=tf.train.exponential_decay(
0.001, #初始学习率
global_step,#用于衰减计算
10, #decay_step，每10次，lr衰减一次
0.95, #decay_rate
staircase=True
)
# opti=net.optimize(loss,lr=0.00001)
opti=tf.train.MomentumOptimizer(learning_rate,0.9).minimize(loss,global_step=global_step)
#验证
test_image,test_label=decode_from_tfrecords('data/val.tfrecords')
test_images,test_labels=get_test_batch(test_image,test_label,batch_size=500,crop_size=227)
test_inf=net.inference(test_images)
correct_prediction=tf.equal(tf.cast(tf.argmax(test_inf,1),tf.int32),test_labels)
accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
init=tf.global_variables_initializer()
with tf.Session() as session:
session.run(init)
coord=tf.train.Coordinator()
threads=tf.train.start_queue_runners(coord=coord)
if os.path.exists(os.path.join("model",'model.ckpt')) is True:
tf.train.Saver(max_to_keep=None).restore(session,os.path.join("model",'model.ckpt'))
for l in range(200):
_,loss_np = session.run([opti,loss])
print "Iteration:"+str(l)+";Train loss: ",loss_np
if l%5 == 0:
accuracy_np=session.run(accuracy)
print "Accuracy: ", accuracy_np
tf.train.Saver(max_to_keep=None).save(session,os.path.join('model','model.ckpt'))
coord.request_stop()
coord.join(threads)
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():
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 = '/home/saverio_sun/project/chinese_rec_data/train'
keep_prob = 0.6
images, labels = input_data.read_files(train_dir)
train_batch, train_label = input_data.get_batch(images, labels, IMG_W,
IMG_H, BATCH_SIZE,
CAPACTIY)
train_logits = network_model.inference(train_batch, BATCH_SIZE, N_CLASS,
keep_prob)
train_loss = network_model.losses(train_logits, train_label)
train_op = network_model.training(train_loss, learning_rate)
train_acc = network_model.evaluation(logits=train_logits,
labels=train_label)
summary_op = tf.summary.merge_all()
init = tf.global_variables_initializer()
sess = tf.InteractiveSession()
train_writer = tf.summary.FileWriter('./log/', sess.graph)
saver = tf.train.Saver()
sess.run(init)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
start_step = 0
if isrestore:
ckpt = tf.train.latest_checkpoint(log_dir)
if ckpt:
saver.restore(sess, ckpt)
print 'restore from the checkpoint {0}'.format(ckpt)
start_step += int(ckpt.split('-')[-1])
print '::: Training Start:::'
try:
for step in range(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, global_step=step)
if step % 10000 == 0 or (step + 1) == MAX_STEP:
checkpoint_path = os.path.join(log_dir, 'model.ckpt')
saver.save(sess, save_path=checkpoint_path, global_step=step)
except tf.errors.OutOfRangeError:
print 'done'
finally:
coord.request_stop()
coord.join(threads)
sess.close()
def run_training():
train_dir = 'C://Users/Sizhe/Desktop/CatsvsDogs/data/train/'
logs_train_dir = 'C://Users/Sizhe/Desktop/CatsvsDogs/data/logs/train/'
train, train_label = input_data.get_files(train_dir)
train_batch, train_label_batch = input_data.get_batch(train,
train_label,
image_width,
image_height,
batch_size,
capacity)
train_logits = model.inference(train_batch, batch_size, n_class)
train_loss = model.losses(train_logits, train_label_batch)
train_op = model.training(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])
### step%50 when training
if step%50 == 0:
print ('Step %d, train loss = %.2f, train accuracy = %.2f%%' %(step, tra_loss, tra_acc*100.00))
summary_str = sess.run(summary_op)
train_writer.add_summary(summary_str, step)
if step%2000 == 0 or step == max_step-1:
checkpoint_path = os.path.join(logs_train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step= step)
except tf.errors.OutOfRangeError:
print ('Training finished -- 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 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()
N_CLASSES = 6
IMG_W = 256 # resize the image, if the input image is too large, training will be very slow.
IMG_H = 256
BATCH_SIZE = 16
CAPACITY = 100000
MAX_STEP = 10000 # with current parameters, it is suggested to use MAX_STEP>10k
learning_rate = 0.0001 # with current parameters, it is suggested to use learning rate<0.0001
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)
