def testModelVariables(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
alexnet.alexnet_v2(inputs, num_classes)
expected_names = [
'alexnet_v2/conv1/weights',
'alexnet_v2/conv1/biases',
'alexnet_v2/conv2/weights',
'alexnet_v2/conv2/biases',
'alexnet_v2/conv3/weights',
'alexnet_v2/conv3/biases',
'alexnet_v2/conv4/weights',
'alexnet_v2/conv4/biases',
'alexnet_v2/conv5/weights',
'alexnet_v2/conv5/biases',
'alexnet_v2/fc6/weights',
'alexnet_v2/fc6/biases',
'alexnet_v2/fc7/weights',
'alexnet_v2/fc7/biases',
'alexnet_v2/fc8/weights',
'alexnet_v2/fc8/biases',
]
model_variables = [v.op.name for v in slim.get_model_variables()]
self.assertSetEqual(set(model_variables), set(expected_names))
def predict(models_path,image_path,labels_filename,labels_nums, data_format):
#[batch_size, resize_height, resize_width, depths] = data_format
tf.reset_default_graph()
#labels = np.loadtxt(labels_filename, str, delimiter='\t')
input_images = tf.placeholder(dtype=tf.float32, shape=[None, resize_height, resize_width, depths], name='input')
with slim.arg_scope(alaxnet.alexnet_v2_arg_scope()):
out, end_points = alaxnet.alexnet_v2(inputs=input_images, num_classes=labels_nums, dropout_keep_prob=1.0, is_training=False)
# 将输出结果进行softmax分布,再求最大概率所属类别
score = tf.nn.softmax(out,name='pre')
class_id = tf.argmax(score, 1)
#
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess, models_path)
im=read_image(image_path,resize_height,resize_width,normalization=True)
im=im[np.newaxis,:]
pre_score,pre_label = sess.run([score,class_id], feed_dict={input_images:im})
sess.close()
return pre_label[0]
def predict(models_path,image_dir,labels_filename,labels_nums, data_format):
[batch_size, resize_height, resize_width, depths] = data_format
labels = np.loadtxt(labels_filename, str, delimiter='\t')
input_images = tf.placeholder(dtype=tf.float32, shape=[None, resize_height, resize_width, depths], name='input')
with slim.arg_scope(alaxnet.alexnet_v2_arg_scope()):
out, end_points = alaxnet.alexnet_v2(inputs=input_images, num_classes=labels_nums, dropout_keep_prob=1.0, is_training=False)
# 将输出结果进行softmax分布,再求最大概率所属类别
score = tf.nn.softmax(out,name='pre')
class_id = tf.argmax(score, 1)
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess, models_path)
images_list=glob.glob(os.path.join(image_dir,'*.jpg'))
score_total = 0
for image_path in images_list:
im=read_image(image_path,resize_height,resize_width,normalization=True)
im=im[np.newaxis,:]
#pred = sess.run(f_cls, feed_dict={x:im, keep_prob:1.0})
pre_score,pre_label = sess.run([score,class_id], feed_dict={input_images:im})
max_score=pre_score[0,pre_label]
#print("{} is: pre labels:{},name:{} score: {}".format(image_path, pre_label, labels[pre_label], max_score))
if image_path.split(".jpg")[0].split("-")[2] == labels[pre_label]:
score_total += 1
print("{} is predicted as label::{} ".format(image_path, labels[pre_label]))
else:
print("{} is predicted as label::{} ".format(image_path,labels[pre_label]))
print("valuation accuracy is {}".format(score_total/len(images_list)))
sess.close()
def testForward(self):
batch_size = 1
height, width = 224, 224
with self.test_session() as sess:
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = alexnet.alexnet_v2(inputs)
sess.run(tf.global_variables_initializer())
output = sess.run(logits)
self.assertTrue(output.any())
def testBuild(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = alexnet.alexnet_v2(inputs, num_classes)
self.assertEquals(logits.op.name, 'alexnet_v2/fc8/squeezed')
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
def testFullyConvolutional(self):
batch_size = 1
height, width = 300, 400
num_classes = 1000
with self.test_session():
inputs = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = alexnet.alexnet_v2(inputs, num_classes, spatial_squeeze=False)
self.assertEquals(logits.op.name, 'alexnet_v2/fc8/BiasAdd')
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, 4, 7, num_classes])
def testGlobalPool(self):
batch_size = 1
height, width = 256, 256
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
logits, _ = alexnet.alexnet_v2(inputs, num_classes, spatial_squeeze=False,
global_pool=True)
self.assertEquals(logits.op.name, 'alexnet_v2/fc8/BiasAdd')
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, 1, 1, num_classes])
def testEvaluation(self):
batch_size = 2
height, width = 224, 224
num_classes = 1000
with self.test_session():
eval_inputs = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = alexnet.alexnet_v2(eval_inputs, is_training=False)
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
predictions = math_ops.argmax(logits, 1)
self.assertListEqual(predictions.get_shape().as_list(), [batch_size])
def testTrainEvalWithReuse(self):
train_batch_size = 2
eval_batch_size = 1
train_height, train_width = 224, 224
eval_height, eval_width = 300, 400
num_classes = 1000
with self.test_session():
train_inputs = random_ops.random_uniform(
(train_batch_size, train_height, train_width, 3))
logits, _ = alexnet.alexnet_v2(train_inputs)
self.assertListEqual(logits.get_shape().as_list(),
[train_batch_size, num_classes])
variable_scope.get_variable_scope().reuse_variables()
eval_inputs = random_ops.random_uniform(
(eval_batch_size, eval_height, eval_width, 3))
logits, _ = alexnet.alexnet_v2(
eval_inputs, is_training=False, spatial_squeeze=False)
self.assertListEqual(logits.get_shape().as_list(),
[eval_batch_size, 4, 7, num_classes])
logits = math_ops.reduce_mean(logits, [1, 2])
predictions = math_ops.argmax(logits, 1)
self.assertEquals(predictions.get_shape().as_list(), [eval_batch_size])
def testEndPoints(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
_, end_points = alexnet.alexnet_v2(inputs, num_classes)
expected_names = [
'alexnet_v2/conv1', 'alexnet_v2/pool1', 'alexnet_v2/conv2',
'alexnet_v2/pool2', 'alexnet_v2/conv3', 'alexnet_v2/conv4',
'alexnet_v2/conv5', 'alexnet_v2/pool5', 'alexnet_v2/fc6',
'alexnet_v2/fc7', 'alexnet_v2/fc8'
]
self.assertSetEqual(set(end_points.keys()), set(expected_names))
def testNoClasses(self):
batch_size = 5
height, width = 224, 224
num_classes = None
with self.test_session():
inputs = tf.random_uniform((batch_size, height, width, 3))
net, end_points = alexnet.alexnet_v2(inputs, num_classes)
expected_names = [
'alexnet_v2/conv1', 'alexnet_v2/pool1', 'alexnet_v2/conv2',
'alexnet_v2/pool2', 'alexnet_v2/conv3', 'alexnet_v2/conv4',
'alexnet_v2/conv5', 'alexnet_v2/pool5', 'alexnet_v2/fc6',
'alexnet_v2/fc7'
]
self.assertSetEqual(set(end_points.keys()), set(expected_names))
self.assertTrue(net.op.name.startswith('alexnet_v2/fc7'))
self.assertListEqual(net.get_shape().as_list(),
[batch_size, 1, 1, 4096])
def predict(image_dir, onset_frames, onsets_frames_strength, models_path):
class_nums = 2
onsets = []
onsets_strength = {}
batch_size = 1 #
resize_height = 224 # 指定存储图片高度
resize_width = 224 # 指定存储图片宽度
depths = 3
data_format = [batch_size, resize_height, resize_width, depths]
[batch_size, resize_height, resize_width, depths] = data_format
#labels = np.loadtxt(labels_filename, str, delimiter='\t')
input_images = tf.placeholder(
dtype=tf.float32,
shape=[None, resize_height, resize_width, depths],
name='input')
with slim.arg_scope(alaxnet.alexnet_v2_arg_scope()):
out, end_points = alaxnet.alexnet_v2(inputs=input_images,
num_classes=class_nums,
dropout_keep_prob=1.0,
is_training=False)
# 将输出结果进行softmax分布,再求最大概率所属类别
score = tf.nn.softmax(out, name='pre')
class_id = tf.argmax(score, 1)
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess, models_path)
images_list = sorted(glob.glob(os.path.join(image_dir, '*.jpg')),
key=os.path.getmtime)
#sorted(glob.glob('*.png'), key=os.path.getmtime)
score_total = 0
index = 0
for image_path in images_list:
im = read_image(image_path,
resize_height,
resize_width,
normalization=True)
im = im[np.newaxis, :]
#pred = sess.run(f_cls, feed_dict={x:im, keep_prob:1.0})
pre_score, pre_label = sess.run([score, class_id],
feed_dict={input_images: im})
max_score = pre_score[0, pre_label]
#print("{} is: pre labels:{},name:{} score: {}".format(image_path, pre_label, labels[pre_label], max_score))
print("{} is predicted as label::{} ".format(image_path, pre_label[0]))
if 1 == pre_label[0]:
#score_total += 1
onsets.append(onset_frames[index])
onsets_strength[onset_frames[index]] = onsets_frames_strength.get(
onset_frames[index])
else:
pass
index += 1
print("valuation accuracy is {}".format(score_total / len(images_list)))
sess.close()
return onsets, onsets_strength
def train(train_record_file, train_log_step, train_param, val_record_file,
val_log_step, labels_nums, data_shape, snapshot, snapshot_prefix):
'''
:param train_record_file: 训练的tfrecord文件
:param train_log_step: 显示训练过程log信息间隔
:param train_param: train参数
:param val_record_file: 验证的tfrecord文件
:param val_log_step: 显示验证过程log信息间隔
:param val_param: val参数
:param labels_nums: labels数
:param data_shape: 输入数据shape
:param snapshot: 保存模型间隔
:param snapshot_prefix: 保存模型文件的前缀名
:return:
'''
[base_lr, max_steps] = train_param
[batch_size, resize_height, resize_width, depths] = data_shape
# 获得训练和测试的样本数
print('train nums:%d,val nums:%d' % (train_nums, val_nums))
# 从record中读取图片和labels数据
# train数据,训练数据一般要求打乱顺序shuffle=True
train_images_batch, train_labels_batch = get_batch_images(
train_record_file)
# val数据,验证数据可以不需要打乱数据
val_images_batch, val_labels_batch = get_batch_images(val_record_file)
# Define the model:
with slim.arg_scope(alexnet.alexnet_v2_arg_scope()):
out, end_points = alexnet.alexnet_v2(inputs=input_images,
num_classes=labels_nums,
dropout_keep_prob=keep_prob,
is_training=is_training)
# Specify the loss function: tf.losses定义的loss函数都会自动添加到loss函数,不需要add_loss()了
tf.losses.softmax_cross_entropy(onehot_labels=input_labels,
logits=out) #添加交叉熵损失loss=1.6
# slim.losses.add_loss(my_loss)
loss = tf.losses.get_total_loss(
add_regularization_losses=True) #添加正则化损失loss=2.2
accuracy = tf.reduce_mean(
tf.cast(tf.equal(tf.argmax(out, 1), tf.argmax(input_labels, 1)),
tf.float32))
# Specify the optimization scheme:
optimizer = tf.train.GradientDescentOptimizer(learning_rate=base_lr)
# create_train_op that ensures that when we evaluate it to get the loss,
# the update_ops are done and the gradient updates are computed.
train_op = slim.learning.create_train_op(total_loss=loss,
optimizer=optimizer)
# global_step = tf.Variable(0, trainable=False)
# learning_rate = tf.train.exponential_decay(0.05, global_step, 150, 0.9)
#
# optimizer = tf.train.MomentumOptimizer(learning_rate, 0.9)
# # train_op = optimizer.minimize(loss, global_step)
# train_op = slim.learning.create_train_op(loss, optimizer,global_step=global_step)
saver = tf.train.Saver()
max_acc = 0.0
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
sess.run(tf.local_variables_initializer())
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
for i in range(max_steps + 1):
batch_input_images, batch_input_labels = sess.run(
[train_images_batch, train_labels_batch])
_, train_loss = sess.run(
[train_op, loss],
feed_dict={
input_images: batch_input_images,
input_labels: batch_input_labels,
keep_prob: 0.5,
is_training: True
})
# train测试(这里仅测试训练集的一个batch)
if i % train_log_step == 0:
train_acc = sess.run(accuracy,
feed_dict={
input_images: batch_input_images,
input_labels: batch_input_labels,
keep_prob: 1.0,
is_training: False
})
print(
"%s: Step [%d] train Loss : %f, training accuracy : %g" %
(datetime.now(), i, train_loss, train_acc))
# val测试(测试全部val数据)
if i % val_log_step == 0:
mean_loss, mean_acc = net_evaluation(sess, loss, accuracy,
val_images_batch,
val_labels_batch,
val_nums)
print("%s: Step [%d] val Loss : %f, val accuracy : %g" %
(datetime.now(), i, mean_loss, mean_acc))
# 模型保存:每迭代snapshot次或者最后一次保存模型
if (i % snapshot == 0 and i > 0) or i == max_steps:
print('-----save:{}-{}'.format(snapshot_prefix, i))
saver.save(sess, snapshot_prefix, global_step=i)
# 保存val准确率最高的模型
if mean_acc > max_acc and mean_acc > 0.5:
max_acc = mean_acc
path = os.path.dirname(snapshot_prefix)
best_models = os.path.join(
path, 'best_models_{}_{:.4f}.ckpt'.format(i, max_acc))
print('------save:{}'.format(best_models))
saver.save(sess, best_models)
coord.request_stop()
coord.join(threads)
def predict(filename,image_dir,onset_frames,onsets_frames_strength,models_path,f_range):
if onset_frames:
class_nums = 2
onsets = []
onsets_strength = {}
tf.reset_default_graph()
batch_size = 1 #
resize_height = 224 # 指定存储图片高度
resize_width = 224 # 指定存储图片宽度
depths = 3
data_format = [batch_size, resize_height, resize_width, depths]
[batch_size, resize_height, resize_width, depths] = data_format
#labels = np.loadtxt(labels_filename, str, delimiter='\t')
input_images = tf.placeholder(dtype=tf.float32, shape=[None, resize_height, resize_width, depths], name='input')
with slim.arg_scope(alaxnet.alexnet_v2_arg_scope()):
out, end_points = alaxnet.alexnet_v2(inputs=input_images, num_classes=class_nums, dropout_keep_prob=1.0, is_training=False)
# 将输出结果进行softmax分布,再求最大概率所属类别
score = tf.nn.softmax(out,name='pre')
class_id = tf.argmax(score, 1)
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess, models_path)
images_list=sorted(glob.glob(os.path.join(image_dir,'*.png')), key=os.path.getmtime)
# images_list = glob.glob(os.path.join(image_dir, '*.png'))
#sorted(glob.glob('*.png'), key=os.path.getmtime)
score_total = 0
index = 0
key_type = type(list(onsets_frames_strength.keys())[0])
for image_path in images_list:
im=read_image(image_path,resize_height,resize_width,normalization=True)
im=im[np.newaxis,:]
#pred = sess.run(f_cls, feed_dict={x:im, keep_prob:1.0})
pre_score,pre_label = sess.run([score,class_id], feed_dict={input_images:im})
max_score=pre_score[0,pre_label]
#print("{} is: pre labels:{},name:{} score: {}".format(image_path, pre_label, labels[pre_label], max_score))
print("{} is predicted as label::{} ".format(image_path,pre_label[0]))
# 将判断为yes的节拍加入onsets
if 1 == pre_label[0]:
#score_total += 1
onsets.append(onset_frames[index])
onsets_strength[key_type(onset_frames[index])] = onsets_frames_strength.get(key_type(onset_frames[index]))
else:
pass
index += 1
#accuracy = 0
#print("valuation accuracy is {}".format(accuracy))
sess.close()
# if len(onsets)!=0:
# y, sr = librosa.load(filename)
# rms = librosa.feature.rmse(y=y)[0]
# rms = [x / np.std(rms) for x in rms]
# onsets,onsets_strength = remove_crowded_frames_by_rms(onsets,onsets_strength,rms,int(f_range*2)+2)
return onsets,onsets_strength#,accuracy
return [],{}
def train(train_record_file, train_log_step, train_param, val_record_file,
val_log_step, labels_nums, data_shape, snapshot, snapshot_prefix):
'''
:param train_record_file: 训练的tfrecord文件
:param train_log_step: 显示训练过程log信息间隔
:param train_param: train参数
:param val_record_file: 验证的tfrecord文件
:param val_log_step: 显示验证过程log信息间隔
:param val_param: val参数
:param labels_nums: labels数
:param data_shape: 输入数据shape
:param snapshot: 保存模型间隔
:param snapshot_prefix: 保存模型文件的前缀名
:return:
'''
[base_lr, max_steps] = train_param
[batch_size, resize_height, resize_width, depths] = data_shape
# 获得训练和测试的样本数
train_nums = get_example_nums(train_record_file)
val_nums = get_example_nums(val_record_file)
print('train nums:%d,val nums:%d' % (train_nums, val_nums))
regularizer = slim.l2_regularizer(0.0005)
# 从record中读取图片和labels数据
# train数据,训练数据一般要求打乱顺序shuffle=True
train_images, train_labels = read_records(train_record_file,
resize_height,
resize_width,
type='normalization')
train_images_batch, train_labels_batch = get_batch_images(
train_images,
train_labels,
batch_size=batch_size,
labels_nums=labels_nums,
one_hot=True,
shuffle=True)
# val数据,验证数据可以不需要打乱数据
val_images, val_labels = read_records(val_record_file,
resize_height,
resize_width,
type='normalization')
val_images_batch, val_labels_batch = get_batch_images(
val_images,
val_labels,
batch_size=batch_size,
labels_nums=labels_nums,
one_hot=True,
shuffle=False)
# Define the model:
with slim.arg_scope(alaxnet.alexnet_v2_arg_scope()):
out, end_points = alaxnet.alexnet_v2(inputs=input_images,
num_classes=labels_nums,
dropout_keep_prob=keep_prob,
is_training=is_training)
# Specify the loss function: tf.losses定义的loss函数都会自动添加到loss函数,不需要add_loss()了
tf.losses.softmax_cross_entropy(onehot_labels=input_labels,
logits=out) #添加交叉熵损失loss=1.6
# slim.losses.add_loss(my_loss)
loss = tf.losses.get_total_loss(
add_regularization_losses=True) #添加正则化损失loss=2.2
accuracy = tf.reduce_mean(
tf.cast(tf.equal(tf.argmax(out, 1), tf.argmax(input_labels, 1)),
tf.float32))
score = tf.nn.softmax(out, name='score')
classIds = tf.argmax(out, 1)
# Specify the optimization scheme:
# optimizer = tf.train.GradientDescentOptimizer(learning_rate=base_lr)
# global_step = tf.Variable(0, trainable=False)
# learning_rate = tf.train.exponential_decay(0.05, global_step, 150, 0.9)
#
optimizer = tf.train.MomentumOptimizer(learning_rate=base_lr, momentum=0.9)
# # train_tensor = optimizer.minimize(loss, global_step)
# train_op = slim.learning.create_train_op(loss, optimizer,global_step=global_step)
# 在定义训练的时候, 注意到我们使用了`batch_norm`层时,需要更新每一层的`average`和`variance`参数,
# 更新的过程不包含在正常的训练过程中, 需要我们去手动像下面这样更新
# 通过`tf.get_collection`获得所有需要更新的`op`
update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS)
# 使用`tensorflow`的控制流, 先执行更新算子, 再执行训练
with tf.control_dependencies(update_ops):
# create_train_op that ensures that when we evaluate it to get the loss,
# the update_ops are done and the gradient updates are computed.
# train_op = slim.learning.create_train_op(total_loss=loss,optimizer=optimizer)
train_op = slim.learning.create_train_op(total_loss=loss,
optimizer=optimizer)
# 循环迭代过程
step_train(train_op, loss, accuracy, score, classIds, train_images_batch,
train_labels_batch, train_nums, train_log_step,
val_images_batch, val_labels_batch, val_nums, val_log_step,
snapshot_prefix, snapshot)
def __init__(self):
batch_size = 1
height, width = 224, 224
inputs = tf.random_uniform((batch_size, height, width, 3))
self.logits, _ = alexnet.alexnet_v2(inputs)
def predict(models_path, labels_nums, image_dir):
#[batch_size, resize_height, resize_width, depths] = data_format
resize_height = 224 # 指定存储图片高度
resize_width = 224 # 指定存储图片宽度
depths = 3
tf.reset_default_graph()
#labels = np.loadtxt(labels_filename, str, delimiter='\t')
input_images = tf.placeholder(
dtype=tf.float32,
shape=[None, resize_height, resize_width, depths],
name='input')
with slim.arg_scope(alaxnet.alexnet_v2_arg_scope()):
out, end_points = alaxnet.alexnet_v2(inputs=input_images,
num_classes=labels_nums,
dropout_keep_prob=1.0,
is_training=False)
# 将输出结果进行softmax分布,再求最大概率所属类别
score = tf.nn.softmax(out, name='pre')
class_id = tf.argmax(score, 1)
#
sess = tf.InteractiveSession()
# sess.list_devices()
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(sess, models_path)
image_list = os.listdir(image_dir)
error_list = []
correct_list = []
all_indexs = get_indexs_from_filename(image_list)
c = 0
for i in all_indexs:
image_name = str(i) + ".jpg"
image_path = image_dir + image_name
index = int(image_name.split('.jpg')[0])
# image_path = image_path.replace("\\",os.altsep).replace("/",os.altsep)
# print("index is {}".format(index))
if c == 0 or index > c:
# if True:
im = read_image(image_path,
resize_height,
resize_width,
normalization=True)
im = im[np.newaxis, :]
pre_score, pre_label = sess.run([score, class_id],
feed_dict={input_images: im})
if pre_label == 1:
correct_list.append(index)
c, middle_position = get_last_nearly_index(index, all_indexs)
# print("=============")
else:
error_list.append(image_name)
correct_list.sort()
sess.close()
return correct_list
