def evaluate(dataset):
"""Evaluate model on Dataset for a number of steps."""
with tf.Graph().as_default():
# Get images and labels from the dataset.
images, pitchs, yaws, rolls, names = image_processing.inputs(dataset)
p = tf.expand_dims(pitchs,1)
y = tf.expand_dims(yaws,1)
r = tf.expand_dims(rolls,1)
labels = tf.concat([p, y, r],1)
eval_output = model.inference(images,FLAGS.is_training)
# Calculate predictions.
error_op = tf.reduce_sum(tf.abs(eval_output-labels),0)
acc_op = tf.abs(eval_output-labels)
saver = tf.train.Saver()
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
graph_def = tf.get_default_graph().as_graph_def()
summary_writer = tf.summary.FileWriter(FLAGS.eval_dir,
graph_def=graph_def)
while True:
_eval_once(saver, summary_writer, error_op, summary_op, acc_op)
if FLAGS.run_once:
break
time.sleep(FLAGS.eval_interval_secs)
def tower_loss(scope, images, labels):
train_output = model.inference(images, FLAGS.is_training)
_ = model.losses(train_output, labels)
losses = tf.get_collection('losses', scope)
total_loss = tf.add_n(losses, name='total_loss')
return total_loss
def evaluate_one_image(image_array, _index):
label = index.index()
with tf.Graph().as_default():
BATCH_SIZE = 1
N_CLASSES = len(label)
image = tf.cast(image_array, tf.float32)
image = tf.image.per_image_standardization(image)
image = tf.reshape(image, [1, 112, 112, 3])
logit = model_2.inference(image, BATCH_SIZE, N_CLASSES)
logit = tf.nn.softmax(logit)
x = tf.placeholder(tf.float32, shape=[112, 112, 3])
# you need to change the directories to yours.
logs_train_dir = r'D:\MyProjects\understand\save_2'
logs_train_dir = os.path.join(os.getcwd(), '..\\', 'understand',
'save_2')
print(logs_train_dir)
saver = tf.train.Saver()
with tf.Session() as sess:
print("Reading checkpoints...")
ckpt = tf.train.get_checkpoint_state(logs_train_dir)
# ckpt = tf.train.get_checkpoint_state(r'D:\MyProjects\understand\save')
# if ckpt and ckpt.model_checkpoint_path:
if True:
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')
prediction = sess.run(logit, feed_dict={x: image_array})
max_index = np.argmax(prediction)
for i in range(len(label)):
if max_index == i:
# result = ('这是{}的可能性为：'.format(label[str(i)]) + '%.6f' % prediction[:, i])
print(label[str(i)] + '-' + str(_index))
def train(dataset):
"""Train on dataset for a number of steps."""
# with tf.Graph().as_default(), tf.device('/cpu:0'):
with tf.Graph().as_default():
# ckpt = tf.train.get_checkpoint_state(FLAGS.checkpoint_dir)
# if ckpt and ckpt.model_checkpoint_path:
# global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
global_step = tf.Variable(0,trainable=False)
# global_step = tf.contrib.framework.get_or_create_global_step()
num_preprocess_threads = FLAGS.num_preprocess_threads * FLAGS.num_gpus
with tf.device('/cpu:0'):
images, pitchs, yaws, rolls, names = image_processing.distorted_inputs(
dataset,
num_preprocess_threads=num_preprocess_threads)
p = tf.expand_dims(pitchs,1)
y = tf.expand_dims(yaws,1)
r = tf.expand_dims(rolls,1)
labels = tf.concat([p, y, r],1)
train_output = model.inference(images,FLAGS.is_training)
train_loss = model.losses(train_output, labels)
add_global = global_step.assign_add(1)
train_op = model.trainning(train_loss, FLAGS.learning_rate, global_step)
summary_op = tf.summary.merge_all()
sess = tf.Session()
train_writer = tf.summary.FileWriter(FLAGS.train_dir, sess.graph)
saver = tf.train.Saver()
# ckpt = tf.train.get_checkpoint_state(FLAGS.checkpoint_dir)
# if ckpt and ckpt.model_checkpoint_path:
# if os.path.isabs(ckpt.model_checkpoint_path):
# # Restores from checkpoint with absolute path.
# saver.restore(sess, ckpt.model_checkpoint_path)
# else:
# # Restores from checkpoint with relative path.
# saver.restore(sess, os.path.join(FLAGS.checkpoint_dir,
# ckpt.model_checkpoint_path))
# Assuming model_checkpoint_path looks something like:
# /my-favorite-path/imagenet_train/model.ckpt-0,
# extract global_step from it.
# global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
# print('Successfully loaded model from %s at step=%s.' %
# (ckpt.model_checkpoint_path, global_step))
# else:
# print('No checkpoint file found')
# return
sess.run(tf.global_variables_initializer())
"""
these codes get the variable in conv1
print(sess.run(tf.get_collection(tf.GraphKeys.REGULARIZATION_LOSSES)))
w = tf.contrib.framework.get_variables('conv1')
t = tf.nn.l2_loss(w[0])
print(sess.run(t))
"""
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
for step in np.arange(FLAGS.max_steps):
if coord.should_stop():
break
_, _, tra_loss= sess.run([add_global, 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) == FLAGS.max_steps:
checkpoint_path = os.path.join(FLAGS.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():
#for which data set to use
"""Train CIFAR-10 for a number of steps."""
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False, name='global_step')
# Get images and labels
images, labels = drd.distorted_inputs()
#get validation data
val_images, val_labels = drd.inputs(False)
#get drop out probability
print(images.get_shape(), val_images.get_shape())
#logits1= drd.inference(images, FLAGS.n_residual_blocks)
logits = model_2.inference(images,
n=4,
reuse=tf.AUTO_REUSE,
is_training=True)
val_logits = model_2.inference(images,
n=4,
reuse=tf.AUTO_REUSE,
is_training=False)
#logits = drd.resnet_v1_50(images, training=True)
#val_logits = drd.resnet_v1_50(val_images, training = False)
#softmx logits
soft_max_logits = tf.nn.softmax(logits)
soft_max_logits_val = tf.nn.softmax(val_logits)
# calculate predictions
predictions = tf.cast(tf.argmax(soft_max_logits, axis=1), tf.int32)
val_predictions = tf.cast(tf.argmax(soft_max_logits_val, axis=1),
tf.int32)
# ops for batch accuracy calcultion
correct_prediction = tf.equal(predictions, labels)
val_correct_prediction = tf.equal(val_predictions, labels)
batch_accuracy = tf.reduce_mean(tf.cast(correct_prediction,
tf.float32))
val_batch_accuracy = tf.reduce_mean(
tf.cast(val_correct_prediction, tf.float32))
# Calculate loss, which includes softmax cross entropy and L2 regularization.
cross_entropy = tf.losses.sparse_softmax_cross_entropy(logits=logits,
labels=labels)
# Create a tensor named cross_entropy for logging purposes.
tf.identity(cross_entropy, name='cross_entropy')
tf.summary.scalar('cross_entropy', cross_entropy)
# If no loss_filter_fn is passed, assume we want the default behavior,
# which is that batch_normalization variables are excluded from loss.
def exclude_batch_norm(name):
return 'batch_normalization' not in name
loss_filter_fn = None or exclude_batch_norm
# Add weight decay to the loss.
l2_loss = weight_decay * tf.add_n(
# loss is computed using fp32 for numerical stability.
[
tf.nn.l2_loss(tf.cast(v, tf.float32))
for v in tf.trainable_variables() if loss_filter_fn(v.name)
])
tf.summary.scalar('l2_loss', l2_loss)
loss = cross_entropy + l2_loss
global_step = tf.train.get_or_create_global_step()
#list of lr decay factors
lr_decay_factors = [1, 0.1, 0.01, 0.001, 0.0001]
learning_rate = 0.001
# Create a tensor named learning_rate for logging purposes
tf.identity(learning_rate, name='learning_rate')
tf.summary.scalar('learning_rate', learning_rate)
optimizer = tf.train.MomentumOptimizer(learning_rate=learning_rate,
momentum=momentum)
minimize_op = optimizer.minimize(loss, global_step)
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
train_op = tf.group(minimize_op, update_ops)
# calculate training accuracy
# Calculate loss.
#loss = drd.loss(logits, labels)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
#train_op = drd.train(loss, global_step)
# Create a saver.
saver = tf.train.Saver(tf.global_variables())
#variables = slim.get_variables_to_restore()
#variables_to_restore = [v for v in variables if not v.name.split('/')[-1] != 'weights:0']
# Add ops to save and restore all the variables.
#saver_pre = tf.train.Saver(variables_to_restore[0:-2]) # exclude logits layer
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.summary.merge_all()
# # Build an initialization operation to run below.
init = tf.global_variables_initializer()
# Start running operations on the Graph.
sess = tf.Session(config=tf.ConfigProto(
log_device_placement=FLAGS.log_device_placement))
# sess.run(init)
# Start the queue runners.
tf.train.start_queue_runners(sess=sess)
summary_writer = tf.summary.FileWriter(FLAGS.save_dir, sess.graph)
step_start = 0
try:
####Trying to find last checkpoint file fore full final model exist###
print("Trying to restore last checkpoint ...")
save_dir = FLAGS.save_dir
# Use TensorFlow to find the latest checkpoint - if any.
last_chk_path = tf.train.latest_checkpoint(checkpoint_dir=save_dir)
# Try and load the data in the checkpoint.
saver.restore(sess, save_path=last_chk_path)
# If we get to this point, the checkpoint was successfully loaded.
print("Restored checkpoint from:", last_chk_path)
# get the step integer from restored path to start step from there
uninitialized_vars = []
for var in tf.global_variables():
try:
sess.run(var)
except tf.errors.FailedPreconditionError:
print("not init")
print(var)
uninitialized_vars.append(var)
# create init op for the still unitilized variables
init_new_vars_op = tf.variables_initializer(uninitialized_vars)
sess.run(init_new_vars_op)
except:
# If all the above failed for some reason, simply
# initialize all the variables for the TensorFlow graph.
print(
"Failed to restore any checkpoints. Initializing variables instead."
)
sess.run(init)
accuracy_dev = []
val_accuracy_dev = []
step_start = 0
for step in range(step_start, FLAGS.max_steps):
start_time = time.time()
#run train op
_, loss_value, accuracy, gs = sess.run(
[train_op, loss, batch_accuracy, global_step])
#setting up a learning rate decay scheme
if ((gs * FLAGS.batch_size) / NUM_IMAGES) == 30:
learning_rate = learning_rate * lr_decay_factors[1]
if ((gs * FLAGS.batch_size) / NUM_IMAGES) == 60:
learning_rate = learning_rate * lr_decay_factors[2]
if ((gs * FLAGS.batch_size) / NUM_IMAGES) == 90:
learning_rate = learning_rate * lr_decay_factors[3]
if ((gs * FLAGS.batch_size) / NUM_IMAGES) == 120:
learning_rate = learning_rate * lr_decay_factors[4]
accuracy_dev.append(accuracy)
duration = time.time() - start_time
assert not np.isnan(loss_value), 'Model diverged with loss = NaN'
if step % 10 == 0:
val_acc = sess.run([val_batch_accuracy])
val_accuracy_dev.append(val_acc)
num_examples_per_step = FLAGS.batch_size
examples_per_sec = num_examples_per_step / duration
sec_per_batch = float(duration)
format_str = (
'%s: step %d, loss = %.2f, avg_batch_accuracy = %.2f, (%.1f examples/sec; %.3f '
'sec/batch), validation accuracy %.2f')
# take averages of all the accuracies from the previous bathces
print(format_str % (datetime.now(), step, loss_value,
np.mean(accuracy_dev), examples_per_sec,
sec_per_batch, np.mean(val_accuracy_dev)))
if step % 10 == 0:
summary_str = sess.run(summary_op)
summary_writer.add_summary(summary_str, step)
# Save the model checkpoint periodically.
if step % 100 == 0 or (step + 1) == FLAGS.max_steps:
#set paths and saving ops for the full and sub_network
checkpoint_path = os.path.join(FLAGS.save_dir, 'model.ckpt')
#pre_trained_path = os.path.join(FLAGS.pre_trained_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
# train_dir = r'D:\MyProjects\inpute_date_2' # 训练样本的读入路径 train_dir = os.path.join(os.getcwd(),'input_data_2') # 训练样本的读入路径 # logs_train_dir = r'D:\MyProjects\understand\save_2' # logs存储路径 logs_train_dir = os.path.join(os.getcwd(),'understand','save_2') # logs存储路径 # logs_test_dir = r'D:\PyCharm\KinZhang_First_ImageDetection\generate_data_2' logs_test_dir = os.path.join(os.getcwd(),'understand','generate_data_2') # train, train_label = input_data.get_files(train_dir) train, train_label, val, val_label = inpute_date_2.get_files(train_dir, 0.2) # print(val) # 训练数据及标签 train_batch, train_label_batch = inpute_date_2.get_batch(train, train_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY) # 测试数据及标签 val_batch, val_label_batch = inpute_date_2.get_batch(val, val_label, IMG_W, IMG_H, BATCH_SIZE, CAPACITY) # 训练操作定义 train_logits = model_2.inference(train_batch, BATCH_SIZE, N_CLASSES) train_loss = model_2.losses(train_logits, train_label_batch) train_op = model_2.trainning(train_loss, learning_rate) train_acc = model_2.evaluation(train_logits, train_label_batch) # 测试操作定义 test_logits = model_2.inference(val_batch, BATCH_SIZE, N_CLASSES) test_loss = model_2.losses(test_logits, val_label_batch) test_acc = model_2.evaluation(test_logits, val_label_batch) test_op = model_2.trainning(test_loss,learning_rate) # 这个是log汇总记录 summary_op = tf.summary.merge_all() # 产生一个会话 sess = tf.Session()