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/'
logs_val_dir = '/home/kevin/tensorflow/cats_vs_dogs/logs/val/'
train, train_label, val, val_label = input_train_val_split.get_files(train_dir, RATIO)
train_batch, train_label_batch = input_train_val_split.get_batch(train,
train_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY)
val_batch, val_label_batch = input_train_val_split.get_batch(val,
val_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY)
x = tf.placeholder(tf.float32, shape=[BATCH_SIZE, IMG_W, IMG_H, 3])
y_ = tf.placeholder(tf.int16, shape=[BATCH_SIZE])
logits = model.inference(x, BATCH_SIZE, N_CLASSES)
loss = model.losses(logits, y_)
acc = model.evaluation(logits, y_)
train_op = model.trainning(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 = %.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(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)
def run_training():
# you need to change the directories to yours.
train_dir = 'C:/MIGUEL/ML/dogs and cats/train/'
logs_train_dir = 'C:/MIGUEL/ML/dogs and cats/logs/train/'
logs_val_dir = 'C:/MIGUEL/ML/dogs and cats/logs/val/'
train, train_label, val, val_label = input_train_val_split.get_files(train_dir, RATIO)
train_batch, train_label_batch = input_train_val_split.get_batch(train,
train_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY)
val_batch, val_label_batch = input_train_val_split.get_batch(val,
val_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY)
x = tf.placeholder(tf.float32, shape=[BATCH_SIZE, IMG_W, IMG_H, 3],name='x')
y_ = tf.placeholder(tf.int32, shape=[BATCH_SIZE],name='y')
training = tf.placeholder_with_default(False, shape=(), name='training')
logits = model.inference(x, BATCH_SIZE, N_CLASSES,training)
loss = model.losses(logits, y_)
acc = model.evaluation(logits, y_)
train_op = model.trainning(loss, learning_rate)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess= sess, coord=coord)
saver = tf.train.Saver()
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)
bn_update_ops=tf.get_collection(tf.GraphKeys.UPDATE_OPS)
for op in (x,y_,training,train_op, loss, acc,summary_op,logits):#,bn_update_ops
tf.add_to_collection("retrain_ops",op)
try:
for step in np.arange(MAX_STEP):
if coord.should_stop():
break
tra_images,tra_labels = sess.run([train_batch, train_label_batch])
if step % 50 != 0:
_, lossValue, accValue,bnUpdateOps = sess.run([train_op, loss, acc,bn_update_ops]
,feed_dict={x:tra_images, y_:tra_labels,training:True})
else : # means step % 50 == 0
_, lossValue, accValue,bnUpdateOps,summary_str = sess.run([train_op, loss, acc,bn_update_ops,summary_op]
,feed_dict={x:tra_images, y_:tra_labels,training:True})
train_writer.add_summary(summary_str, step)
print('Step %d, train loss = %.2f, train accuracy = %.2f%%' %(step, lossValue, accValue*100.0))
if step % 200 == 0 or (step) == MAX_STEP:
val_images, val_labels = sess.run([val_batch, val_label_batch])
val_loss, val_acc ,summary_str= sess.run([loss, acc,summary_op],
feed_dict={x:val_images, y_:val_labels})
val_writer.add_summary(summary_str, step)
print('** Step %d, val loss = %.2f, val accuracy = %.2f%% **' %(step, val_loss, val_acc*100.0))
if step % 20 == 0 or (step ) == 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)
def train():
with tf.name_scope('input'):
train, train_label, val, val_label = input_train_val_split.get_files(
train_dir, RATIO)
tra_image_batch, tra_label_batch = input_train_val_split.get_batch(
train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
val_image_batch, val_label_batch = input_train_val_split.get_batch(
val, val_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
x = tf.placeholder(tf.float32, shape=[BATCH_SIZE, IMG_W, IMG_H, 3])
y_ = tf.placeholder(tf.int16, shape=[BATCH_SIZE, N_CLASSES])
logits = VGG.VGG16N(x, N_CLASSES, IS_PRETRAIN)
loss = tools.loss(logits, y_)
accuracy = tools.accuracy(logits, y_)
my_global_step = tf.Variable(0, name='global_step', trainable=False)
train_op = tools.optimize(loss, learning_rate, my_global_step)
saver = tf.train.Saver(tf.global_variables())
summary_op = tf.summary.merge_all()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
tools.load_with_skip(pre_trained_weights, sess, ['fc8'])
print("load weights done")
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
tra_summary_writer = tf.summary.FileWriter(train_log_dir, sess.graph)
val_summary_writer = tf.summary.FileWriter(val_log_dir, sess.graph)
try:
for step in np.arange(MAX_STEP):
if coord.should_stop():
break
tra_images, tra_labels = sess.run(
[tra_image_batch, tra_label_batch])
_, tra_loss, tra_acc = sess.run([train_op, loss, accuracy],
feed_dict={
x: tra_images,
y_: tra_labels
})
if step % 2 == 0 or (step + 1) == MAX_STEP:
print('Step: %d, loss: %.4f, accuracy: %.4f%%' %
(step, tra_loss, tra_acc))
_, summary_str = sess.run([train_op, summary_op],
feed_dict={
x: tra_images,
y_: tra_labels
})
tra_summary_writer.add_summary(summary_str, step)
if step % 4 == 0 or (step + 1) == MAX_STEP:
val_images, val_labels = sess.run(
[val_image_batch, val_label_batch])
val_loss, val_acc = sess.run([loss, accuracy],
feed_dict={
x: val_images,
y_: val_labels
})
print(
'** Step %d, val loss = %.2f, val accuracy = %.2f%% **'
% (step, val_loss, val_acc))
_, summary_str = sess.run([train_op, summary_op],
feed_dict={
x: val_images,
y_: val_labels
})
val_summary_writer.add_summary(summary_str, step)
if step % 8 == 0 or (step + 1) == MAX_STEP:
checkpoint_path = os.path.join(train_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)
BATCH_SIZE = 16
CAPACITY = 2000
RATIO = 0.2
MAX_STEP = 1000 # 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
# In[4]:
# you need to change the directories to yours.
train_dir = 'C:/MIGUEL/ML/dogs and cats/train/'
logs_train_dir = 'C:/MIGUEL/ML/dogs and cats/logs/train/retrain/saveretrain'
logs_val_dir = 'C:/MIGUEL/ML/dogs and cats/logs/val/'
train, train_label, val, val_label = input_train_val_split.get_files(
train_dir, RATIO)
train_batch, train_label_batch = input_train_val_split.get_batch(
train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
val_batch, val_label_batch = input_train_val_split.get_batch(
val, val_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY)
# In[5]:
train_writer = tf.summary.FileWriter(logs_train_dir, tf.get_default_graph())
val_writer = tf.summary.FileWriter(logs_val_dir, tf.get_default_graph())
# In[6]:
with tf.Session() as sess:
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
saver.restore(sess, "C:/MIGUEL/ML/dogs and cats/logs/train/model.ckpt-40")