import tensorflow as tf
import tensorflow.contrib.slim as slim
WEIGHT_DECAY = 0.01
# 这段是我之前看别人的帖子上做的，但是后来我做的过程中我发现其实并没有什么用，
# 改变featuremap的大小用卷积也完全可以实现，所以我把它注释掉，发现也是正常的
# 但是由于tensorflow老大哥最近又开始迭代更新了，所以可能会有warning，但是
# 没什么大影响
# def sampling(input_tensor,
# ksize=1,
# stride=2):
# data = input_tensor
# if stride > 1:
# data = slim.max_pool2d(data, ksize, stride=stride)
# print('sampling', 2)
# return data
def conv2d_same(input_tensor,
num_outputs,
kernel_size,
stride,
is_train=True,
activation_fn=tf.nn.relu,
normalizer_fc=True
):
data = input_tensor
if stride is 1:
data = slim.conv2d(inputs=data,
num_outputs=num_outputs,
kernel_size=kernel_size,
stride=stride,
weights_regularizer=slim.l2_regularizer(WEIGHT_DECAY),
activation_fn=None,
padding='SAME',
)
else:
pad_total = kernel_size - 1
pad_begin = pad_total // 2
pad_end = pad_total - pad_begin
data = tf.pad(data, [[0, 0], [pad_begin, pad_end], [pad_begin, pad_end], [0, 0]])
data = slim.conv2d(data,
num_outputs=num_outputs,
kernel_size=kernel_size,
stride=stride,
weights_regularizer=slim.l2_regularizer(WEIGHT_DECAY),
activation_fn=None,
padding='VALID',
)
if normalizer_fc:
data = tf.layers.batch_normalization(data, training=is_train)
if activation_fn is not None:
data = activation_fn(data)
return data
def bottle_net(input_tensor, output_depth, is_train, stride=1):
data = input_tensor
depth = input_tensor.get_shape().as_list()[-1]
if depth == output_depth:
shortcut_tensor = input_tensor
else:
shortcut_tensor = conv2d_same(input_tensor, output_depth, 1, stride, is_train=is_train, activation_fn=None,
normalizer_fc=True)
data = conv2d_same(data, output_depth // 4, 1, 1, is_train=is_train)
data = conv2d_same(data, output_depth // 4, 3, stride, is_train=is_train)
data = conv2d_same(data, output_depth, 1, 1, is_train=is_train, activation_fn=None, normalizer_fc=False)
# 生成残差
data = data + shortcut_tensor
data = tf.nn.relu(data)
return data
def create_block(input_tensor, output_depth, block_nums, init_stride=1, is_train=True, scope='block'):
with tf.variable_scope(scope):
data = bottle_net(input_tensor, output_depth, is_train=is_train, stride=init_stride)
for i in range(1, block_nums):
data = bottle_net(data, output_depth, is_train=is_train)
return data
def ResNet(input_tensor, num_output, is_train, scope='resnet50'):
data = input_tensor
with tf.variable_scope(scope):
data = conv2d_same(data, 64, 7, 2, is_train=is_train, normalizer_fc=True)
data = slim.max_pool2d(data, 3, 2, padding='SAME', scope='pool_1')
# 第一个残差块组
data = create_block(data, 256, 3, init_stride=1, is_train=is_train, scope='block1')
# 第二个残差块组
data = create_block(data, 512, 4, init_stride=2, is_train=is_train, scope='block2')
# 第三个残差块组
data = create_block(data, 1024, 6, init_stride=2, is_train=is_train, scope='block3')
# 第四个残差块组
data = create_block(data, 2048, 3, init_stride=2, is_train=is_train, scope='block4')
# 接下来就是池化层和全连接层
data = slim.avg_pool2d(data, 7)
data = slim.conv2d(data, num_output, 1, activation_fn=None, scope='final_conv')
data_shape = data.get_shape().as_list()
nodes = data_shape[1] * data_shape[2] * data_shape[3]
data = tf.reshape(data, [-1, nodes])
return data
if __name__ == '__main__':
x = tf.random_normal([32, 224, 224, 3])
data = ResNet(x, 1000, True)
print(data)
