def get_base_network(inputs,
name='resnet50',
weight_decay=1e-6,
training=True):
if name == 'resnet50':
with slim.arg_scope(
resnet_v2.resnet_arg_scope(weight_decay=weight_decay)):
logits, end_points = resnet_v2.resnet_v2_50(inputs,
is_training=training)
elif name == 'inception-resnet':
with slim.arg_scope(
inception_resnet_v2.inception_resnet_v2_arg_scope(
weight_decay=weight_decay)):
logits, end_points = inception_resnet_v2.inception_resnet_v2(
inputs, is_training=training)
else:
with slim.arg_scope(
resnet_v2.resnet_arg_scope(weight_decay=weight_decay)):
logits, end_points = resnet_v2.resnet_v2_101(inputs,
is_training=training)
var_list_restore = {}
for i in end_points:
name = i.replace('generator/', '')
var_list_restore[i] = name
return var_list_restore, end_points
def _extract_proposal_features(self, preprocessed_inputs, scope):
"""Extracts first stage RPN features.
Extracts features using the first half of the Inception Resnet v2 network.
We construct the network in `align_feature_maps=True` mode, which means
that all VALID paddings in the network are changed to SAME padding so that
the feature maps are aligned.
Args:
preprocessed_inputs: A [batch, height, width, channels] float32 tensor
representing a batch of images.
scope: A scope name.
Returns:
rpn_feature_map: A tensor with shape [batch, height, width, depth]
Raises:
InvalidArgumentError: If the spatial size of `preprocessed_inputs`
(height or width) is less than 33.
ValueError: If the created network is missing the required activation.
"""
if len(preprocessed_inputs.get_shape().as_list()) != 4:
raise ValueError(
'`preprocessed_inputs` must be 4 dimensional, got a '
'tensor of shape %s' % preprocessed_inputs.get_shape())
with slim.arg_scope(
inception_resnet_v2.inception_resnet_v2_arg_scope(
weight_decay=self._weight_decay)):
# Forces is_training to False to disable batch norm update.
with slim.arg_scope([slim.batch_norm],
is_training=self._train_batch_norm):
with tf.variable_scope('InceptionResnetV2',
reuse=self._reuse_weights) as scope:
rpn_feature_map, _ = (
inception_resnet_v2.inception_resnet_v2_base(
preprocessed_inputs,
final_endpoint='PreAuxLogits',
scope=scope,
output_stride=self._first_stage_features_stride,
align_feature_maps=True))
return rpn_feature_map
def _extract_box_classifier_features(self, proposal_feature_maps, scope):
"""Extracts second stage box classifier features.
This function reconstructs the "second half" of the Inception ResNet v2
network after the part defined in `_extract_proposal_features`.
Args:
proposal_feature_maps: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, crop_height, crop_width, depth]
representing the feature map cropped to each proposal.
scope: A scope name.
Returns:
proposal_classifier_features: A 4-D float tensor with shape
[batch_size * self.max_num_proposals, height, width, depth]
representing box classifier features for each proposal.
"""
with tf.variable_scope('InceptionResnetV2', reuse=self._reuse_weights):
with slim.arg_scope(
inception_resnet_v2.inception_resnet_v2_arg_scope(
weight_decay=self._weight_decay)):
# Forces is_training to False to disable batch norm update.
with slim.arg_scope([slim.batch_norm],
is_training=self._train_batch_norm):
with slim.arg_scope(
[slim.conv2d, slim.max_pool2d, slim.avg_pool2d],
stride=1,
padding='SAME'):
with tf.variable_scope('Mixed_7a'):
with tf.variable_scope('Branch_0'):
tower_conv = slim.conv2d(proposal_feature_maps,
256,
1,
scope='Conv2d_0a_1x1')
tower_conv_1 = slim.conv2d(
tower_conv,
384,
3,
stride=2,
padding='VALID',
scope='Conv2d_1a_3x3')
with tf.variable_scope('Branch_1'):
tower_conv1 = slim.conv2d(
proposal_feature_maps,
256,
1,
scope='Conv2d_0a_1x1')
tower_conv1_1 = slim.conv2d(
tower_conv1,
288,
3,
stride=2,
padding='VALID',
scope='Conv2d_1a_3x3')
with tf.variable_scope('Branch_2'):
tower_conv2 = slim.conv2d(
proposal_feature_maps,
256,
1,
scope='Conv2d_0a_1x1')
tower_conv2_1 = slim.conv2d(
tower_conv2, 288, 3, scope='Conv2d_0b_3x3')
tower_conv2_2 = slim.conv2d(
tower_conv2_1,
320,
3,
stride=2,
padding='VALID',
scope='Conv2d_1a_3x3')
with tf.variable_scope('Branch_3'):
tower_pool = slim.max_pool2d(
proposal_feature_maps,
3,
stride=2,
padding='VALID',
scope='MaxPool_1a_3x3')
net = tf.concat([
tower_conv_1, tower_conv1_1, tower_conv2_2,
tower_pool
], 3)
net = slim.repeat(net,
9,
inception_resnet_v2.block8,
scale=0.20)
net = inception_resnet_v2.block8(net,
activation_fn=None)
proposal_classifier_features = slim.conv2d(
net, 1536, 1, scope='Conv2d_7b_1x1')
return proposal_classifier_features
variables_to_restore =[]
for var in slim.get_model_variables():
exluded = False
for exlusion in exlusions:
if var.op.name.startswith(exlusion):
exluded = True
break
if not exluded:
variables_to_restore.append(var)
return slim.assign_from_checkpoint_fn(
'/home/long/pretrained_model/inception-resnet/inception_resnet_v2_2016_08_30.ckpt',
variables_to_restore
)
with tf.Graph().as_default():
image = np.ones((1, image_size, image_size, channels), np.uint8)
with slim.arg_scope(inception_resnet_v2.inception_resnet_v2_arg_scope()):
logit, _ = inception_resnet_v2.inception_resnet_v2(image, 1001, False)
optimizer = tf.train.AdamOptimizer(learning_rate=0.01)
train_op = slim.learning.create_train_op(logit, optimizer)
slim.learning.train(train_op,
init_fn=get_init_fn(),
number_of_steps=2)
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_resnet_v2.inception_resnet_v2_arg_scope()):
out, end_points = inception_resnet_v2.inception_resnet_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)
# 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_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)
