def build_network(input, trainable):
is_trainable(trainable)
net = convb(input, 5, 5, 8, 2, name="Conv2d_0")
with tf.variable_scope('MV'):
# 128, 112
mv2_branch_0 = dwconvb(net, 5, 5, 1, name="Conv2d_1_dw")
mv2_branch_0 = slim.stack(mv2_branch_0,
inverted_bottleneck, [
(2, 16, 0, 5),
],
scope="part0")
# 64, 56
mv2_branch_1 = dwconvb(mv2_branch_0, 7, 7, 2, name="Conv2d_2_dw")
mv2_branch_1 = slim.stack(mv2_branch_1,
inverted_bottleneck, [
(2, 24, 0, 7),
],
scope="part1")
# 32, 28
mv2_branch_2 = dwconvb(mv2_branch_1, 7, 7, 2, name="Conv2d_3_dw")
mv2_branch_2 = slim.stack(mv2_branch_2,
inverted_bottleneck, [
(2, 32, 0, 7),
],
scope="part2")
# 16, 14
mv2_branch_3 = dwconvb(mv2_branch_2, 7, 7, 2, name="Conv2d_4_dw")
mv2_branch_3 = slim.stack(mv2_branch_3,
inverted_bottleneck, [
(3, 32, 0, 7),
(3, 32, 0, 7),
],
scope="part3")
# 8, 7
mv2_branch_4 = dwconvb(mv2_branch_3, 7, 7, 2, name="Conv2d_5_dw")
mv2_branch_4 = slim.stack(mv2_branch_4,
inverted_bottleneck, [
(4, 32, 0, 7),
(4, 32, 0, 7),
],
scope="part4")
cancat_mv2 = tf.concat([
max_pool(mv2_branch_0, 4, 4, 4, 4, name="mv2_0_max_pool"),
max_pool(mv2_branch_1, 2, 2, 2, 2, name="mv2_1_max_pool"),
mv2_branch_2,
upsample(mv2_branch_3, 2, name="mv2_3_upsample"),
upsample(mv2_branch_4, 4, name="mv2_4_upsample")
],
axis=3)
with tf.variable_scope("CPM"):
l2s = []
prev = None
for stage_number in range(STAGE_NUM):
if prev is not None:
inputs = tf.concat([cancat_mv2, prev], axis=3)
else:
inputs = cancat_mv2
#kernel_size = 7
lastest_channel_size = 256
if stage_number == 0:
# kernel_size = 7
lastest_channel_size = 192
_ = slim.stack(inputs,
inverted_bottleneck, [
(1, 24, 0, 5),
(1, 24, 0, 5),
],
scope="stage_%d_mv2" % stage_number)
else:
_ = slim.stack(inputs,
inverted_bottleneck, [
(1, 32, 0, 7),
(1, 32, 0, 7),
],
scope="stage_%d_mv2" % stage_number)
_ = slim.stack(_,
separable_conv, [(lastest_channel_size, 1, 1),
(N_KPOINTS, 1, 1)],
scope="stage_%d_mv1" % stage_number)
prev = _
cpm_out = upsample(_, 4, "stage_%d_out" % stage_number)
l2s.append(cpm_out)
return cpm_out, l2s
def build_network(input, trainable):
is_trainable(trainable)
#128*128*5*5*3*16=18.75M
net = convb(input, 5, 5, 16, 2, name="Conv2d_0")
net = dwconvb(net, 7, 7, 1, name="Conv2d_1_dw")
#4M
mv2_branch_0 = convb(net, 1, 1, 16, 1, name="Conv2d_1_sep")
with tf.variable_scope('MV2'):
# 64
mv2_branch_1 = slim.stack(mv2_branch_0, inverted_bottleneck,
[
(1, 16, 1, 7),
(1, 16, 0, 7),
], scope="part1")
# 32
mv2_branch_2 = slim.stack(mv2_branch_1, inverted_bottleneck,
[
(1, 32, 1, 7),
(1, 32, 0, 7),
], scope="part2")
# 16
mv2_branch_3 = slim.stack(mv2_branch_2, inverted_bottleneck,
[
(1, 48, 1, 7),
(1, 48, 0, 7),
], scope="part3")
# 8
mv2_branch_4 = slim.stack(mv2_branch_3, inverted_bottleneck,
[
(1, 64, 1, 5),
(1, 64, 0, 5),
], scope="part4")
concat_mv2 = tf.concat(
[
max_pool(mv2_branch_0, 4, 4, 4, 4, name="mv2_0_max_pool"),
max_pool(mv2_branch_1, 2, 2, 2, 2, name="mv2_1_max_pool"),
mv2_branch_2,
upsample(mv2_branch_3, 2, name="mv2_3_upsample"),
upsample(mv2_branch_4, 4, name="mv2_4_upsample")
]
, axis=3)
with tf.variable_scope("CPM"):
l2s = []
prev = None
for stage_number in range(STAGE_NUM):
if prev is not None:
inputs = tf.concat([concat_mv2, prev], axis=3)
else:
inputs = concat_mv2
kernel_size = 7
lastest_channel_size = 256
if stage_number == 0:
kernel_size = 7
lastest_channel_size = 256
_ = slim.stack(inputs, inverted_bottleneck,
[
(1, 64, 0, kernel_size),
(1, 64, 0, kernel_size),
(1, 64, 0, kernel_size),
], scope="stage_%d_mv2" % stage_number)
_ = convb(_, 1, 1, lastest_channel_size, 1, "stage_%d_mv1_0"%stage_number, relu=True)
_ = convb(_, 1, 1, N_KPOINTS, 1, "stage_%d_mv1_1"%stage_number, relu=True)
prev = _
cpm_out = upsample(_, 2, "stage_%d_out" % stage_number)
l2s.append(cpm_out)
return cpm_out, l2s
def build_network(input, trainable):
is_trainable(trainable)
net = convb(input, 7, 7, 16, 2, name="Conv2d_0")
with tf.variable_scope('MV'):
# 128
mv2_branch_0 = dwconvb(net, 7, 7, 1, name="Conv2d_1_dw")
mv2_branch_0 = slim.stack(mv2_branch_0,
inverted_bottleneck, [
(2, 16, 0, 7),
(2, 32, 0, 7),
],
scope="part0")
# 64
mv2_branch_1 = dwconvb(mv2_branch_0, 7, 7, 2, name="Conv2d_2_dw")
mv2_branch_1 = slim.stack(mv2_branch_1,
inverted_bottleneck, [
(2, 32, 0, 7),
(2, 32, 0, 7),
],
scope="part1")
# 32
mv2_branch_2 = dwconvb(mv2_branch_1, 7, 7, 2, name="Conv2d_3_dw")
mv2_branch_2 = slim.stack(mv2_branch_2,
inverted_bottleneck, [
(2, 32, 0, 7),
(2, 32, 0, 7),
(2, 32, 0, 7),
],
scope="part2")
# 16
mv2_branch_3 = dwconvb(mv2_branch_2, 7, 7, 2, name="Conv2d_4_dw")
mv2_branch_3 = slim.stack(mv2_branch_3,
inverted_bottleneck, [
(4, 32, 0, 7),
(4, 32, 0, 7),
(4, 32, 0, 7),
(4, 32, 0, 7),
],
scope="part3")
# 8
mv2_branch_4 = dwconvb(mv2_branch_3, 7, 7, 2, name="Conv2d_5_dw")
mv2_branch_4 = slim.stack(mv2_branch_4,
inverted_bottleneck, [
(6, 32, 0, 7),
(6, 32, 0, 7),
(6, 32, 0, 7),
(6, 32, 0, 7),
],
scope="part4")
cancat_mv2 = tf.concat([
max_pool(mv2_branch_0, 4, 4, 4, 4, name="mv2_0_max_pool"),
max_pool(mv2_branch_1, 2, 2, 2, 2, name="mv2_1_max_pool"),
mv2_branch_2,
upsample(mv2_branch_3, 2, name="mv2_3_upsample"),
upsample(mv2_branch_4, 4, name="mv2_4_upsample")
],
axis=3)
with tf.variable_scope("CPM"):
l2s = []
prev = None
inputs = cancat_mv2
for stage_number in range(STAGE_NUM):
if prev is not None:
inputs = tf.concat([inputs, prev], axis=3)
_ = slim.stack(inputs,
inverted_bottleneck, [
(1, 64, 0, 7),
(1, 64, 0, 7),
(1, 64, 0, 7),
(4, 21, 0, 7),
],
scope="stage_%d_mv2" % stage_number)
prev = _
cpm_out = upsample(_, 4, "stage_%d_out" % stage_number)
l2s.append(cpm_out)
return cpm_out, l2s
