def res_block_with_n_conv_layers(self,
input_,
output_dim,
num_repeat,
name="res_block"):
output_ = layers.conv2d_same_repeat(input_,
output_dim,
num_repeat=num_repeat,
activation_fn=self.act_fn,
name=name)
return self.skip_connection(input_, output_)
def inference(self, input_):
conv1 = layers.conv2d_same_repeat(input_,
self.kernel_num,
num_repeat=2,
name="down1")
pool1 = layers.max_pool(conv1, name="pool1")
conv2 = layers.conv2d_same_repeat(pool1,
self.kernel_num * 2,
num_repeat=2,
name="down2")
pool2 = layers.max_pool(conv2, name="pool2")
conv3 = layers.conv2d_same_repeat(pool2,
self.kernel_num * 4,
num_repeat=3,
name="down3")
pool3 = layers.max_pool(conv3, name="pool3")
conv4 = layers.conv2d_same_repeat(pool3,
self.kernel_num * 8,
num_repeat=3,
name="down4")
pool4 = layers.max_pool(conv4, name="pool4")
conv5 = layers.conv2d_same_repeat(pool4,
self.kernel_num * 8,
num_repeat=3,
name="down5")
pool5 = layers.max_pool(conv5, name="pool5")
flat = layers.flatten(pool5, 'flat')
linear = layers.linear(flat,
flat.get_shape().as_list()[-1],
name='linear')
logits = layers.linear(linear, self.num_class, name='logits')
return logits
def res_block(self,
input_,
output_dim,
is_downsizing=True,
name="res_block"):
with tf.variable_scope(name):
act1 = self.res_act(input_, name='act1')
if is_downsizing:
skip2 = layers.bottleneck_layer(act1,
output_dim,
d_h=2,
d_w=2,
name='skip1')
_, conv1 = layers.conv2d_same_act(
act1,
output_dim,
d_h=2,
d_w=2,
activation_fn=self.activation_fn,
with_logit=True,
name='conv1')
else:
skip2 = layers.bottleneck_layer(act1,
output_dim,
d_h=1,
d_w=1,
name='skip1')
_, conv1 = layers.conv2d_same_act(
act1,
output_dim,
d_h=1,
d_w=1,
activation_fn=self.activation_fn,
with_logit=True,
name='conv1')
conv2 = layers.conv2d_same(conv1, output_dim, name='conv2')
res1 = tf.add(skip2, conv2, name='res1')
act2 = self.res_act(res1, name='act2')
_, conv3 = layers.conv2d_same_repeat(
act2,
output_dim,
num_repeat=2,
d_h=1,
d_w=1,
activation_fn=self.activation_fn,
with_logit=True,
name='conv3')
res2 = tf.add(res1, conv3, name='res2')
return res2
def inference(self, input_):
conv1 = layers.conv2d_same_repeat(input_, self.kernel_num, num_repeat=2, activation_fn=self.act_fn, name="down1")
pool1 = layers.max_pool(conv1, name="pool1")
conv2 = layers.conv2d_same_repeat(pool1, self.kernel_num * 2, num_repeat=2, activation_fn=self.act_fn, name="down2")
pool2 = layers.max_pool(conv2, name="pool2")
conv3 = layers.conv2d_same_repeat(pool2, self.kernel_num * 4, num_repeat=3, activation_fn=self.act_fn, name="down3")
pool3 = layers.max_pool(conv3, name="pool3")
conv4 = layers.conv2d_same_repeat(pool3, self.kernel_num * 8, num_repeat=3, activation_fn=self.act_fn, name="down4")
pool4 = layers.max_pool(conv4, name="pool4")
conv5 = layers.conv2d_same_repeat(pool4, self.kernel_num * 8, num_repeat=3, activation_fn=self.act_fn, name="down5")
pool5 = layers.global_avg_pool(conv5, name="pool5")
conv6 = layers.bottleneck_act(pool5, self.kernel_num * 8, activation_fn=self.act_fn, name="down6")
conv7 = layers.bottleneck_layer(conv6, self.num_class, name="down7")
logits = layers.flatten(conv7, 'flat')
return logits
def encoder(self, input_):
self.down1 = layers.conv2d_same_repeat(input_,
self.kernel_num,
num_repeat=2,
name="down1")
pool1 = layers.max_pool(self.down1, name="pool1")
self.down2 = layers.conv2d_same_repeat(pool1,
self.kernel_num * 2,
num_repeat=2,
name="down2")
pool2 = layers.max_pool(self.down2, name="pool2")
self.down3 = layers.conv2d_same_repeat(pool2,
self.kernel_num * 4,
num_repeat=2,
name="down3")
pool3 = layers.max_pool(self.down3, name="pool3")
self.down4 = layers.conv2d_same_repeat(pool3,
self.kernel_num * 8,
num_repeat=2,
name="down4")
pool4 = layers.max_pool(self.down4, name="pool4")
if self.log == 1:
print("encoder input : ", input_.get_shape())
print("conv1 : ", self.down1.get_shape())
print("pool1 : ", pool1.get_shape())
print("conv2 : ", self.down2.get_shape())
print("pool2 : ", pool2.get_shape())
print("conv3 : ", self.down3.get_shape())
print("pool3 : ", pool3.get_shape())
print("conv4 : ", self.down4.get_shape())
print("pool4 : ", pool4.get_shape())
return pool4
def inference(self, input_):
encode_vec = self.encoder(input_)
bridge = layers.conv2d_same_repeat(encode_vec,
self.kernel_num * 16,
num_repeat=2,
name="bridge")
decode_vec = self.decoder(bridge)
output = layers.bottleneck_layer(decode_vec,
self.output_dim,
name="output")
if self.log == 1:
print("output : ", output.get_shape())
print("Complete!!")
return output
def _inference(self, input_):
conv1 = layers.conv2d_same_act(input_,
16,
activation_fn=self.activation_fn,
name='conv1')
skip1 = layers.bottleneck_layer(conv1, 32, name='skip1')
_, conv2 = layers.conv2d_same_repeat(conv1,
32,
num_repeat=2,
activation_fn=self.activation_fn,
with_logit=True,
name='conv2')
res1 = tf.add(skip1, conv2, name='res1')
res_act1 = self.res_act(res1)
_, conv3 = layers.conv2d_same_repeat(res_act1,
32,
num_repeat=2,
activation_fn=self.activation_fn,
with_logit=True,
name='conv3')
res2 = tf.add(conv3, res1, name='res2')
res_act2 = self.res_act(res2)
skip2 = layers.bottleneck_layer(res_act2,
64,
d_h=2,
d_w=2,
name='skip2')
conv4 = layers.conv2d_same_act(res_act2,
64,
d_h=2,
d_w=2,
activation_fn=self.activation_fn,
name='conv4')
conv5 = layers.conv2d_same(conv4, 64, name='conv5')
res3 = tf.add(skip2, conv5, name='res3')
res_act3 = self.res_act(res3)
_, conv6 = layers.conv2d_same_repeat(res_act1,
64,
num_repeat=2,
activation_fn=self.activation_fn,
with_logit=True,
name='conv3')
res4 = tf.add(res3, conv6, name='res4')
res_act4 = self.res_act(res4)
skip3 = layers.bottleneck_layer(res_act4,
128,
d_h=2,
d_w=2,
name='skip3')
conv7 = layers.conv2d_same_act(res_act4,
128,
d_h=2,
d_w=2,
activation_fn=self.activation_fn,
name='conv7')
conv8 = layers.conv2d_same(conv7, 128, name='conv8')
res5 = tf.add(skip3, conv8, name='res5')
res_act5 = self.res_act(res5)
_, conv9 = layers.conv2d_same_repeat(res_act5,
128,
num_repeat=2,
activation_fn=self.activation_fn,
with_logit=True,
name='conv9')
res6 = tf.add(res5, conv9, name='res6')
res_act6 = self.res_act(res6)
pool = layers.avg_pool(res_act6,
k_h=8,
k_w=8,
d_h=1,
d_w=1,
name='pool')
flat = layers.flatten(pool, 'flat')
linear = layers.linear(flat, self.num_class, name='linear')
return linear
def decoder(self, input_):
conv_trans4 = layers.conv2dTrans_same_act(input_,
self.down4.get_shape(),
activation_fn=self.act_fn,
with_logit=False,
name="unpool4")
skip4 = self.skip_connection(conv_trans4, self.down4)
up4 = layers.conv2d_same_repeat(skip4,
self.kernel_num * 8,
num_repeat=2,
name="up4")
conv_trans3 = layers.conv2dTrans_same_act(up4,
self.down3.get_shape(),
activation_fn=self.act_fn,
with_logit=False,
name="unpool3")
skip3 = self.skip_connection(conv_trans3, self.down3)
up3 = layers.conv2d_same_repeat(skip3,
self.kernel_num * 4,
num_repeat=2,
name="up3")
conv_trans2 = layers.conv2dTrans_same_act(up3,
self.down2.get_shape(),
activation_fn=self.act_fn,
with_logit=False,
name="unpool2")
skip2 = self.skip_connection(conv_trans2, self.down2)
up2 = layers.conv2d_same_repeat(skip2,
self.kernel_num * 2,
num_repeat=2,
name="up2")
conv_trans1 = layers.conv2dTrans_same_act(up2,
self.down1.get_shape(),
activation_fn=self.act_fn,
with_logit=False,
name="unpool1")
skip1 = self.skip_connection(conv_trans1, self.down1)
up1 = layers.conv2d_same_repeat(skip1,
self.kernel_num,
num_repeat=2,
name="up1")
if self.log == 1:
print("dncoder input : ", input_.get_shape())
print("convT1 : ", conv_trans4.get_shape())
print("res1 : ", skip4.get_shape())
print("up1 : ", up4.get_shape())
print("convT2 : ", conv_trans3.get_shape())
print("res2 : ", skip3.get_shape())
print("up2 : ", up3.get_shape())
print("convT3 : ", conv_trans2.get_shape())
print("res3 : ", skip2.get_shape())
print("up3 : ", up2.get_shape())
print("convT4 : ", conv_trans1.get_shape())
print("res4 : ", skip1.get_shape())
print("up4 : ", up1.get_shape())
return up1