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')
#其他模型预测请修改这里
with slim.arg_scope(inception_v1.inception_v1_arg_scope()):
out, end_points = inception_v1.inception_v1(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'))
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,list(labels_filename.keys())[list(labels_filename.values()).index(pre_label)], max_score))
sess.close()
def testTrainEvalWithReuse(self):
train_batch_size = 5
eval_batch_size = 2
height, width = 224, 224
num_classes = 1000
train_inputs = random_ops.random_uniform(
(train_batch_size, height, width, 3))
inception_v1.inception_v1(train_inputs, num_classes)
eval_inputs = random_ops.random_uniform(
(eval_batch_size, height, width, 3))
logits, _ = inception_v1.inception_v1(eval_inputs,
num_classes,
reuse=True)
predictions = math_ops.argmax(logits, 1)
with self.test_session() as sess:
sess.run(variables.global_variables_initializer())
output = sess.run(predictions)
self.assertEquals(output.shape, (eval_batch_size, ))
def testLogitsNotSqueezed(self):
num_classes = 25
images = random_ops.random_uniform([1, 224, 224, 3])
logits, _ = inception_v1.inception_v1(images,
num_classes=num_classes,
spatial_squeeze=False)
with self.test_session() as sess:
variables.global_variables_initializer().run()
logits_out = sess.run(logits)
self.assertListEqual(list(logits_out.shape),
[1, 1, 1, num_classes])
def testBuildClassificationNetwork(self):
batch_size = 5
height, width = 224, 224
num_classes = 1000
inputs = random_ops.random_uniform((batch_size, height, width, 3))
logits, end_points = inception_v1.inception_v1(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV1/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
self.assertTrue('Predictions' in end_points)
self.assertListEqual(end_points['Predictions'].get_shape().as_list(),
[batch_size, num_classes])
def predict_images():
models_path = './logs/model.ckpt-11999'
images_dir = './test_images'
labels_txt_file = './dataset/label.txt'
num_calsses = 5
resize_height = 224
resize_width = 224
channels = 3
images_list = glob.glob(os.path.join(images_dir,
'*.jpg')) # 返回匹配路径名模式的路径列表
# delimiter='\t'表示以空格隔开
labels = np.loadtxt(
labels_txt_file, str, delimiter='\t'
) # labels = ['flower' 'guitar' 'animal' 'houses' 'plane']
intput_images = tf.placeholder(
dtype=tf.float32,
shape=[None, resize_height, resize_width, channels],
name='input')
with slim.arg_scope(inception_v1.inception_v1_arg_scope()):
out, end_points = inception_v1.inception_v1(inputs=intput_images,
num_classes=num_calsses,
dropout_keep_prob=1.0,
is_training=False)
score = tf.nn.softmax(out)
class_id = tf.argmax(score, axis=1) # 最大score的id值
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
saver = tf.train.Saver()
saver.restore(sess, models_path)
for image_name in images_list:
image = read_image(image_name,
resize_height,
resize_width,
normalization=True)
image = image[np.newaxis, :] # 给数据增加一个新的维度
predict_score, predict_id = sess.run(
[score, class_id], feed_dict={intput_images: image})
max_score = predict_score[0, predict_id] # id相对应的得分(得到的score是二维的)
print("{} is: label:{},name:{} score: {}".format(
image_name, predict_id, labels[predict_id], max_score))
def testEvaluation(self):
batch_size = 2
height, width = 224, 224
num_classes = 1000
eval_inputs = random_ops.random_uniform((batch_size, height, width, 3))
logits, _ = inception_v1.inception_v1(eval_inputs,
num_classes,
is_training=False)
predictions = math_ops.argmax(logits, 1)
with self.test_session() as sess:
sess.run(variables.global_variables_initializer())
output = sess.run(predictions)
self.assertEquals(output.shape, (batch_size, ))
def testUnknownBatchSize(self):
batch_size = 1
height, width = 224, 224
num_classes = 1000
inputs = array_ops.placeholder(dtypes.float32,
(None, height, width, 3))
logits, _ = inception_v1.inception_v1(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV1/Logits'))
self.assertListEqual(logits.get_shape().as_list(), [None, num_classes])
images = random_ops.random_uniform((batch_size, height, width, 3))
with self.test_session() as sess:
sess.run(variables.global_variables_initializer())
output = sess.run(logits, {inputs: images.eval()})
self.assertEquals(output.shape, (batch_size, num_classes))
def testUnknownImageShape(self):
ops.reset_default_graph()
batch_size = 2
height, width = 224, 224
num_classes = 1000
input_np = np.random.uniform(0, 1, (batch_size, height, width, 3))
with self.test_session() as sess:
inputs = array_ops.placeholder(dtypes.float32,
shape=(batch_size, None, None, 3))
logits, end_points = inception_v1.inception_v1(inputs, num_classes)
self.assertTrue(logits.op.name.startswith('InceptionV1/Logits'))
self.assertListEqual(logits.get_shape().as_list(),
[batch_size, num_classes])
pre_pool = end_points['Mixed_5c']
feed_dict = {inputs: input_np}
variables.global_variables_initializer().run()
pre_pool_out = sess.run(pre_pool, feed_dict=feed_dict)
self.assertListEqual(list(pre_pool_out.shape),
[batch_size, 7, 7, 1024])
def train(train_tfrecords_file, base_lr, max_steps, val_tfrecords_file,
num_classes, data_shape, train_log_dir, val_nums):
"""
:param train_tfrecords_file: 训练数据集的tfrecords文件
:param base_lr: 学习率
:param max_steps: 迭代次数
:param val_tfrecords_file: 验证数据集的tfrecords文件
:param num_classes: 分类个数
:param data_shape: 数据形状[batch_size, resize_height, resize_width, channels]
:param train_log_dir: 模型文件的存放位置
:return:
"""
[batch_size, resize_height, resize_width, channels] = data_shape
# 读取训练数据
train_images, train_labels = read_tfrecords(train_tfrecords_file,
resize_height,
resize_width,
output_model='normalization')
train_batch_images, train_batch_labels = get_batch_images(
train_images,
train_labels,
batch_size=batch_size,
num_classes=num_classes,
one_hot=True,
shuffle=True)
# 读取验证数据,验证数据集可以不用打乱
val_images, val_labels = read_tfrecords(val_tfrecords_file,
resize_height,
resize_width,
output_model='normalization')
val_batch_images, val_batch_labels = get_batch_images(
val_images,
val_labels,
batch_size=batch_size,
num_classes=num_classes,
one_hot=True,
shuffle=False)
with slim.arg_scope(inception_v1.inception_v1_arg_scope()
): # inception_v1.inception_v1_arg_scope()括号不能掉，表示一个函数
out, end_points = inception_v1.inception_v1(
inputs=input_images,
num_classes=num_classes,
is_training=is_training,
dropout_keep_prob=keep_prob)
loss = tf.losses.softmax_cross_entropy(onehot_labels=input_labels,
logits=out)
accuracy = tf.reduce_mean(
tf.cast(tf.equal(tf.argmax(out, 1), tf.argmax(input_labels, 1)),
tf.float32)) * 100.0
optimizer = tf.train.MomentumOptimizer(learning_rate=base_lr,
momentum=0.9) # 这里可以使用不同的优化函数
# 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,
# 正常的训练过程不包括更新，需要我们去手动像下面这样更新
with tf.control_dependencies(tf.get_collection(
tf.GraphKeys.UPDATE_OPS)): # 执行完更新操作之后，再进行训练操作
train_op = slim.learning.create_train_op(total_loss=loss,
optimizer=optimizer)
saver = tf.train.Saver()
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
for steps in np.arange(max_steps):
input_batch_images, input_batch_labels = sess.run(
[train_batch_images, train_batch_labels])
_, train_loss = sess.run(
[train_op, loss],
feed_dict={
input_images: input_batch_images,
input_labels: input_batch_labels,
keep_prob: 0.8,
is_training: True
})
# 得到训练过程中的loss， accuracy值
if steps % 50 == 0 or (steps + 1) == max_steps:
train_acc = sess.run(accuracy,
feed_dict={
input_images: input_batch_images,
input_labels: input_batch_labels,
keep_prob: 1.0,
is_training: False
})
print('Step: %d, loss: %.4f, accuracy: %.4f' %
(steps, train_loss, train_acc))
# 在验证数据集上得到loss, accuracy值
if steps % 200 == 0 or (steps + 1) == max_steps:
val_images_batch, val_labels_batch = sess.run(
[val_batch_images, val_batch_labels])
val_loss, val_acc = sess.run(
[loss, accuracy],
feed_dict={
input_images: val_images_batch,
input_labels: val_labels_batch,
keep_prob: 1.0,
is_training: False
})
val_loss, val_acc = evaluation(sess, loss, accuracy,
val_batch_images,
val_batch_labels, val_nums)
print(
'** Step %d, val loss = %.2f, val accuracy = %.2f%% **' %
(steps, val_loss, val_acc))
# 每隔2000步储存一下模型文件
if steps % 2000 == 0 or (steps + 1) == max_steps:
checkpoint_path = os.path.join(train_log_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=steps)
coord.request_stop()
coord.join(threads)
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))
# 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(inception_v1.inception_v1_arg_scope()):
out, end_points = inception_v1.inception_v1(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=False)#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)
# 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,
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)