def run_training():
# you need to change this to your data directory
train_dir = "D://Documents//PySpace//dataset//cats_vs_dogs//train//"
logs_train_dir = ".//logs//train"
logs_val_dir = ".//logs//val"
tra_images, tra_labels, val_images, val_images = input.get_files(
train_dir, RATIO)
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 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)
def train():
train_dir = './data'
logs_train_dir = './logs/train/'
logs_val_dir = './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_OneHot(train,
train_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY,
CHANNEL)
val_batch, val_label_batch = input_train_val_split.get_batch_OneHot(val,
val_label,
IMG_W,
IMG_H,
BATCH_SIZE,
CAPACITY,
CHANNEL)
with tf.name_scope('input'):
x = tf.placeholder(tf.float32, shape=[BATCH_SIZE, IMG_W, IMG_H, CHANNEL], name='x-input')
y_ = tf.placeholder(tf.float32, shape=[BATCH_SIZE, N_CLASSES], name='y-input')
keep_prob = tf.placeholder(tf.float32)
# To run nicely in jupyter notebook
#sess = tf.InteractiveSession()
hidden5 = model.inference(
images = x,
IMG_W = IMG_W,
IMG_H = IMG_H,
keep_prob = keep_prob,
BATCH_SIZE = BATCH_SIZE,
N_CLASSES = N_CLASSES,
CHANNEL = CHANNEL)
# Probabilities - output from model (not the same as logits)
y = tf.nn.softmax(hidden5)#?
# Loss and optimizer
with tf.name_scope('cross_entropy'):
# The raw formulation of cross-entropy,
diff = tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=hidden5)
with tf.name_scope('total'):
cross_entropy = tf.reduce_mean(diff)
tf.summary.scalar('cross_entropy', cross_entropy)
with tf.name_scope('train'):
train_step = tf.train.AdamOptimizer(learning_rate).minimize(cross_entropy)
# Setup to test accuracy of model
with tf.name_scope('accuracy'):
with tf.name_scope('correct_prediction'):
#tf.equal: Returns the truth value of (x == y) element-wise.
#print('tf.argmax(y, 1) = {}'.format(tf.argmax(y, 1)))
#print('tf.argmax(y_, 1) = {}'.format(tf.argmax(y_, 1)))
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
with tf.name_scope('accuracy'):
#tf.cast: Casts a tensor to a new type.
#tf.reduce_mean: Computes the mean of elements across dimensions of a tensor.
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.summary.scalar('accuracy', accuracy)
saver = tf.train.Saver()
with tf.Session() as sess:
# Merge all the summaries and write them out to /tmp/tensorflow/mnist/logs/mnist_with_summaries (by default)
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph)
test_writer = tf.summary.FileWriter(logs_val_dir)
#tf.global_variables_initializer().run()#?
## Initilize all global variables
sess.run(tf.global_variables_initializer())
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess = sess, coord = coord)
#bTrain=True: data is batch of train data
#bTrain=False: data is all of test data
def feed_dict(bTrain):
"""Make a TensorFlow feed_dict: maps data onto Tensor placeholders."""
if bTrain:
xs, ys = tra_images, tra_labels#mnist.train.next_batch(100, fake_data=fake_data)
k = dropout
else:
xs, ys = val_images, val_labels
k = 1.0
#print('len(xs) = {}'.format(len(xs)))
#print('len(ys) = {}'.format(len(ys)))
#print('ys[0] = {}'.format(ys[0]))
#print('k = {}'.format(k))
return {x: xs, y_: ys, keep_prob: k}
# Train model
# Run once to get the model to a good confidence level
for i in range(max_steps):
if i % 100 == 0:
val_images, val_labels = sess.run([val_batch, val_label_batch])
#print('len(val_labels) = {}'.format(len(val_labels)))
#print('len(val_labels[0]) = {}'.format(len(val_labels[0])))
#print('val_labels[0] = {}'.format(val_labels[0]))
summary, acc = sess.run([merged, accuracy], feed_dict=feed_dict(False))
test_writer.add_summary(summary, i)
print('Accuracy at step %s: %s' % (i, acc))
if i % 2000 == 0 or (i + 1) == max_steps:
checkpoint_path = os.path.join(logs_train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step = i)
else: # Record train set summaries, and train
tra_images, tra_labels = sess.run([train_batch, train_label_batch])
if i % 200 == 199:
run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
run_metadata = tf.RunMetadata()
summary, _ = sess.run([merged, train_step],
feed_dict=feed_dict(True),
options=run_options,
run_metadata=run_metadata)
train_writer.add_run_metadata(run_metadata, 'step%03d' % i)
train_writer.add_summary(summary, i)
#print('Adding run metadata for', i)
else: # Record a summary
summary, _ = sess.run([merged, train_step], feed_dict=feed_dict(True))
train_writer.add_summary(summary, i)
train_writer.close()
test_writer.close()
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)
IMG_W = 208 # resize the image, if the input image is too large, training will be very slow.
IMG_H = 208
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)
