def get_symbol(num_class,
num_level=3,
num_block=9,
num_filter=16,
bn_momentum=0.9,
pool_kernel=(8, 8)):
# data = mxc.Variable(name='data')
data = 'data'
# Simulate z-score normalization as that in
# https://github.com/gcr/torch-residual-networks/blob/master/data/cifar-dataset.lua
zscore = mxc.BatchNorm(name='zscore',
data=data,
fix_gamma=True,
momentum=bn_momentum)
conv = get_conv(name='conv0',
data=zscore,
num_filter=num_filter,
kernel=(3, 3),
stride=(1, 1),
pad=(1, 1),
with_relu=True,
bn_momentum=bn_momentum)
body = get_body(conv, num_level, num_block, num_filter, bn_momentum)
pool = mxc.Pooling(data=body,
name='pool',
kernel=pool_kernel,
pool_type='avg')
# The flatten layer seems superfluous
flat = mxc.Flatten(data=pool, name='flatten')
fc = mxc.FullyConnected(data=flat, num_hidden=num_class, name='fc')
return mxc.SoftmaxOutput(data=fc, name='softmax')
def resnet(units, num_stage, filter_list, num_class, data_type, bottle_neck=True, bn_mom=0.9, workspace=512, memonger=False):
"""Return ResNet symbol of cifar10 and imagenet
Parameters
----------
units : list
Number of units in each stage
num_stage : int
Number of stage
filter_list : list
Channel size of each stage
num_class : int
Ouput size of symbol
dataset : str
Dataset type, only cifar10 and imagenet supports
workspace : int
Workspace used in convolution operator
"""
num_unit = len(units)
assert(num_unit == num_stage)
# data = mxc.Variable(name='data')
data = 'data'
data = mxc.BatchNorm(data=data, fix_gamma=True, eps=2e-5, momentum=bn_mom, name='bn_data')
if data_type == 'cifar10':
body = mxc.Convolution(data=data, num_filter=filter_list[0], kernel=(3, 3), stride=(1,1), pad=(1, 1),
no_bias=True, name="conv0", workspace=workspace)
elif data_type == 'imagenet':
body = mxc.Convolution(data=data, num_filter=filter_list[0], kernel=(7, 7), stride=(2,2), pad=(3, 3),
no_bias=True, name="conv0", workspace=workspace)
body = mxc.BatchNorm(data=body, fix_gamma=False, eps=2e-5, momentum=bn_mom, name='bn0')
body = mxc.Activation(data=body, act_type='relu', name='relu0')
body = mxc.Pooling(data=body, name="pool0", kernel=(3, 3), stride=(2,2), pad=(1,1), pool_type='max')
else:
raise ValueError("do not support {} yet".format(data_type))
for i in range(num_stage):
body = residual_unit(body, filter_list[i+1], (1 if i==0 else 2, 1 if i==0 else 2), False,
name='stage%d_unit%d' % (i + 1, 1), bottle_neck=bottle_neck, workspace=workspace,
memonger=memonger)
for j in range(units[i]-1):
body = residual_unit(body, filter_list[i+1], (1,1), True, name='stage%d_unit%d' % (i + 1, j + 2),
bottle_neck=bottle_neck, workspace=workspace, memonger=memonger)
bn1 = mxc.BatchNorm(data=body, fix_gamma=False, eps=2e-5, momentum=bn_mom, name='bn1')
relu1 = mxc.Activation(data=bn1, act_type='relu', name='relu1')
# Although kernel is not used here when global_pool=True, we should put one
# pool1 = mxc.Pooling(data=relu1, global_pool=True, kernel=(7, 7), pool_type='avg', name='pool1')
pool1 = mxc.Pooling(data=relu1, kernel=(7, 7), pool_type='avg', name='pool1')
flat = mxc.Flatten(data=pool1, name='flatten')
fc1 = mxc.FullyConnected(data=flat, num_hidden=num_class, name='fc1')
def Inception7B(data,
num_3x3,
num_d3x3_red, num_d3x3_1, num_d3x3_2,
pool,
name):
tower_3x3 = Conv(data, num_3x3, kernel=(3, 3), pad=(0, 0), stride=(2, 2), name=('%s_conv' % name))
tower_d3x3 = Conv(data, num_d3x3_red, name=('%s_tower' % name), suffix='_conv')
tower_d3x3 = Conv(tower_d3x3, num_d3x3_1, kernel=(3, 3), pad=(1, 1), stride=(1, 1), name=('%s_tower' % name), suffix='_conv_1')
tower_d3x3 = Conv(tower_d3x3, num_d3x3_2, kernel=(3, 3), pad=(0, 0), stride=(2, 2), name=('%s_tower' % name), suffix='_conv_2')
pooling = mxc.Pooling(data=data, kernel=(3, 3), stride=(2, 2), pad=(0,0), pool_type="max", name=('max_pool_%s_pool' % name))
concat = mxc.Concat(bottoms=[tower_3x3, tower_d3x3, pooling], name='ch_concat_%s_chconcat' % name)
return concat
def InceptionFactoryB(data, num_3x3red, num_3x3, num_d3x3red, num_d3x3, name):
# 3x3 reduce + 3x3
c3x3r = ConvFactory(data=data, num_filter=num_3x3red, kernel=(1, 1), name=('%s_3x3' % name), suffix='_reduce')
c3x3 = ConvFactory(data=c3x3r, num_filter=num_3x3, kernel=(3, 3), pad=(1, 1), stride=(2, 2), name=('%s_3x3' % name))
# double 3x3 reduce + double 3x3
cd3x3r = ConvFactory(data=data, num_filter=num_d3x3red, kernel=(1, 1), name=('%s_double_3x3' % name), suffix='_reduce')
cd3x3 = ConvFactory(data=cd3x3r, num_filter=num_d3x3, kernel=(3, 3), pad=(1, 1), stride=(1, 1), name=('%s_double_3x3_0' % name))
cd3x3 = ConvFactory(data=cd3x3, num_filter=num_d3x3, kernel=(3, 3), pad=(1, 1), stride=(2, 2), name=('%s_double_3x3_1' % name))
# pool + proj
pooling = mxc.Pooling(data=data, kernel=(3, 3), stride=(2, 2), pool_type="max", name=('max_pool_%s_pool' % name))
# concat
concat = mxc.Concat(bottoms=[c3x3, cd3x3, pooling], name='ch_concat_%s_chconcat' % name)
return concat
def Inception7D(data,
num_3x3_red, num_3x3,
num_d7_3x3_red, num_d7_1, num_d7_2, num_d7_3x3,
pool,
name):
tower_3x3 = Conv(data=data, num_filter=num_3x3_red, name=('%s_tower' % name), suffix='_conv')
tower_3x3 = Conv(data=tower_3x3, num_filter=num_3x3, kernel=(3, 3), pad=(0,0), stride=(2, 2), name=('%s_tower' % name), suffix='_conv_1')
tower_d7_3x3 = Conv(data=data, num_filter=num_d7_3x3_red, name=('%s_tower_1' % name), suffix='_conv')
tower_d7_3x3 = Conv(data=tower_d7_3x3, num_filter=num_d7_1, kernel=(1, 7), pad=(0, 3), name=('%s_tower_1' % name), suffix='_conv_1')
tower_d7_3x3 = Conv(data=tower_d7_3x3, num_filter=num_d7_2, kernel=(7, 1), pad=(3, 0), name=('%s_tower_1' % name), suffix='_conv_2')
tower_d7_3x3 = Conv(data=tower_d7_3x3, num_filter=num_d7_3x3, kernel=(3, 3), stride=(2, 2), name=('%s_tower_1' % name), suffix='_conv_3')
pooling = mxc.Pooling(data=data, kernel=(3, 3), stride=(2, 2), pool_type=pool, name=('%s_pool_%s_pool' % (pool, name)))
# concat
concat = mxc.Concat(bottoms=[tower_3x3, tower_d7_3x3, pooling], name='ch_concat_%s_chconcat' % name)
return concat
def InceptionFactoryA(data, num_1x1, num_3x3red, num_3x3, num_d3x3red, num_d3x3, pool, proj, name):
# 1x1
c1x1 = ConvFactory(data=data, num_filter=num_1x1, kernel=(1, 1), name=('%s_1x1' % name))
# 3x3 reduce + 3x3
c3x3r = ConvFactory(data=data, num_filter=num_3x3red, kernel=(1, 1), name=('%s_3x3' % name), suffix='_reduce')
c3x3 = ConvFactory(data=c3x3r, num_filter=num_3x3, kernel=(3, 3), pad=(1, 1), name=('%s_3x3' % name))
# double 3x3 reduce + double 3x3
cd3x3r = ConvFactory(data=data, num_filter=num_d3x3red, kernel=(1, 1), name=('%s_double_3x3' % name), suffix='_reduce')
cd3x3 = ConvFactory(data=cd3x3r, num_filter=num_d3x3, kernel=(3, 3), pad=(1, 1), name=('%s_double_3x3_0' % name))
cd3x3 = ConvFactory(data=cd3x3, num_filter=num_d3x3, kernel=(3, 3), pad=(1, 1), name=('%s_double_3x3_1' % name))
# pool + proj
pooling = mxc.Pooling(data=data, kernel=(3, 3), stride=(1, 1), pad=(1, 1), pool_type=pool, name=('%s_pool_%s_pool' % (pool, name)))
cproj = ConvFactory(data=pooling, num_filter=proj, kernel=(1, 1), name=('%s_proj' % name))
# concat
concat = mxc.Concat(bottoms=[c1x1, c3x3, cd3x3, cproj], name='ch_concat_%s_chconcat' % name)
return concat
def Inception7A(data,
num_1x1,
num_3x3_red, num_3x3_1, num_3x3_2,
num_5x5_red, num_5x5,
pool, proj,
name):
tower_1x1 = Conv(data, num_1x1, name=('%s_conv' % name))
tower_5x5 = Conv(data, num_5x5_red, name=('%s_tower' % name), suffix='_conv')
tower_5x5 = Conv(tower_5x5, num_5x5, kernel=(5, 5), pad=(2, 2), name=('%s_tower' % name), suffix='_conv_1')
tower_3x3 = Conv(data, num_3x3_red, name=('%s_tower_1' % name), suffix='_conv')
tower_3x3 = Conv(tower_3x3, num_3x3_1, kernel=(3, 3), pad=(1, 1), name=('%s_tower_1' % name), suffix='_conv_1')
tower_3x3 = Conv(tower_3x3, num_3x3_2, kernel=(3, 3), pad=(1, 1), name=('%s_tower_1' % name), suffix='_conv_2')
pooling = mxc.Pooling(data=data, kernel=(3, 3), stride=(1, 1), pad=(1, 1), pool_type=pool, name=('%s_pool_%s_pool' % (pool, name)))
cproj = Conv(pooling, proj, name=('%s_tower_2' % name), suffix='_conv')
concat = mxc.Concat(bottoms=[tower_1x1, tower_5x5, tower_3x3, cproj], name='ch_concat_%s_chconcat' % name)
return concat
def Inception7E(data,
num_1x1,
num_d3_red, num_d3_1, num_d3_2,
num_3x3_d3_red, num_3x3, num_3x3_d3_1, num_3x3_d3_2,
pool, proj,
name):
tower_1x1 = Conv(data=data, num_filter=num_1x1, kernel=(1, 1), name=('%s_conv' % name))
tower_d3 = Conv(data=data, num_filter=num_d3_red, name=('%s_tower' % name), suffix='_conv')
tower_d3_a = Conv(data=tower_d3, num_filter=num_d3_1, kernel=(1, 3), pad=(0, 1), name=('%s_tower' % name), suffix='_mixed_conv')
tower_d3_b = Conv(data=tower_d3, num_filter=num_d3_2, kernel=(3, 1), pad=(1, 0), name=('%s_tower' % name), suffix='_mixed_conv_1')
tower_3x3_d3 = Conv(data=data, num_filter=num_3x3_d3_red, name=('%s_tower_1' % name), suffix='_conv')
tower_3x3_d3 = Conv(data=tower_3x3_d3, num_filter=num_3x3, kernel=(3, 3), pad=(1, 1), name=('%s_tower_1' % name), suffix='_conv_1')
tower_3x3_d3_a = Conv(data=tower_3x3_d3, num_filter=num_3x3_d3_1, kernel=(1, 3), pad=(0, 1), name=('%s_tower_1' % name), suffix='_mixed_conv')
tower_3x3_d3_b = Conv(data=tower_3x3_d3, num_filter=num_3x3_d3_2, kernel=(3, 1), pad=(1, 0), name=('%s_tower_1' % name), suffix='_mixed_conv_1')
pooling = mxc.Pooling(data=data, kernel=(3, 3), stride=(1, 1), pad=(1, 1), pool_type=pool, name=('%s_pool_%s_pool' % (pool, name)))
cproj = Conv(data=pooling, num_filter=proj, kernel=(1, 1), name=('%s_tower_2' % name), suffix='_conv')
# concat
concat = mxc.Concat(bottoms=[tower_1x1, tower_d3_a, tower_d3_b, tower_3x3_d3_a, tower_3x3_d3_b, cproj], name='ch_concat_%s_chconcat' % name)
return concat
def Inception7C(data,
num_1x1,
num_d7_red, num_d7_1, num_d7_2,
num_q7_red, num_q7_1, num_q7_2, num_q7_3, num_q7_4,
pool, proj,
name):
tower_1x1 = Conv(data=data, num_filter=num_1x1, kernel=(1, 1), name=('%s_conv' % name))
tower_d7 = Conv(data=data, num_filter=num_d7_red, name=('%s_tower' % name), suffix='_conv')
tower_d7 = Conv(data=tower_d7, num_filter=num_d7_1, kernel=(1, 7), pad=(0, 3), name=('%s_tower' % name), suffix='_conv_1')
tower_d7 = Conv(data=tower_d7, num_filter=num_d7_2, kernel=(7, 1), pad=(3, 0), name=('%s_tower' % name), suffix='_conv_2')
tower_q7 = Conv(data=data, num_filter=num_q7_red, name=('%s_tower_1' % name), suffix='_conv')
tower_q7 = Conv(data=tower_q7, num_filter=num_q7_1, kernel=(7, 1), pad=(3, 0), name=('%s_tower_1' % name), suffix='_conv_1')
tower_q7 = Conv(data=tower_q7, num_filter=num_q7_2, kernel=(1, 7), pad=(0, 3), name=('%s_tower_1' % name), suffix='_conv_2')
tower_q7 = Conv(data=tower_q7, num_filter=num_q7_3, kernel=(7, 1), pad=(3, 0), name=('%s_tower_1' % name), suffix='_conv_3')
tower_q7 = Conv(data=tower_q7, num_filter=num_q7_4, kernel=(1, 7), pad=(0, 3), name=('%s_tower_1' % name), suffix='_conv_4')
pooling = mxc.Pooling(data=data, kernel=(3, 3), stride=(1, 1), pad=(1, 1), pool_type=pool, name=('%s_pool_%s_pool' % (pool, name)))
cproj = Conv(data=pooling, num_filter=proj, kernel=(1, 1), name=('%s_tower_2' % name), suffix='_conv')
# concat
concat = mxc.Concat(bottoms=[tower_1x1, tower_d7, tower_q7, cproj], name='ch_concat_%s_chconcat' % name)
return concat
cd3x3r = ConvFactory(data=data, num_filter=num_d3x3red, kernel=(1, 1), name=('%s_double_3x3' % name), suffix='_reduce')
cd3x3 = ConvFactory(data=cd3x3r, num_filter=num_d3x3, kernel=(3, 3), pad=(1, 1), stride=(1, 1), name=('%s_double_3x3_0' % name))
cd3x3 = ConvFactory(data=cd3x3, num_filter=num_d3x3, kernel=(3, 3), pad=(1, 1), stride=(2, 2), name=('%s_double_3x3_1' % name))
# pool + proj
pooling = mxc.Pooling(data=data, kernel=(3, 3), stride=(2, 2), pool_type="max", name=('max_pool_%s_pool' % name))
# concat
concat = mxc.Concat(bottoms=[c3x3, cd3x3, pooling], name='ch_concat_%s_chconcat' % name)
return concat
num_classes=1000
# data
# data = mxc.Variable(name="data")
data = 'data'
# stage 1
conv1 = ConvFactory(data=data, num_filter=64, kernel=(7, 7), stride=(2, 2), pad=(3, 3), name='conv1')
pool1 = mxc.Pooling(data=conv1, kernel=(3, 3), stride=(2, 2), name='pool1', pool_type='max')
# stage 2
conv2red = ConvFactory(data=pool1, num_filter=64, kernel=(1, 1), stride=(1, 1), name='conv2red')
conv2 = ConvFactory(data=conv2red, num_filter=192, kernel=(3, 3), stride=(1, 1), pad=(1, 1), name='conv2')
pool2 = mxc.Pooling(data=conv2, kernel=(3, 3), stride=(2, 2), name='pool2', pool_type='max')
# stage 2
in3a = InceptionFactoryA(pool2, 64, 64, 64, 64, 96, "avg", 32, '3a')
in3b = InceptionFactoryA(in3a, 64, 64, 96, 64, 96, "avg", 64, '3b')
in3c = InceptionFactoryB(in3b, 128, 160, 64, 96, '3c')
# stage 3
in4a = InceptionFactoryA(in3c, 224, 64, 96, 96, 128, "avg", 128, '4a')
in4b = InceptionFactoryA(in4a, 192, 96, 128, 96, 128, "avg", 128, '4b')
in4c = InceptionFactoryA(in4b, 160, 128, 160, 128, 160, "avg", 128, '4c')
in4d = InceptionFactoryA(in4c, 96, 128, 192, 160, 192, "avg", 128, '4d')
in4e = InceptionFactoryB(in4d, 128, 192, 192, 256, '4e')
# stage 4
pooling = mxc.Pooling(data=data, kernel=(3, 3), stride=(1, 1), pad=(1, 1), pool_type=pool, name=('%s_pool_%s_pool' % (pool, name)))
cproj = Conv(data=pooling, num_filter=proj, kernel=(1, 1), name=('%s_tower_2' % name), suffix='_conv')
# concat
concat = mxc.Concat(bottoms=[tower_1x1, tower_d3_a, tower_d3_b, tower_3x3_d3_a, tower_3x3_d3_b, cproj], name='ch_concat_%s_chconcat' % name)
return concat
# In[49]:
num_classes=1000
# data = mxc.Variable(name="data")
data = 'data'
# stage 1
conv = Conv(data, 32, kernel=(3, 3), stride=(2, 2), name="conv")
conv_1 = Conv(conv, 32, kernel=(3, 3), name="conv_1")
conv_2 = Conv(conv_1, 64, kernel=(3, 3), pad=(1, 1), name="conv_2")
pool = mxc.Pooling(data=conv_2, kernel=(3, 3), stride=(2, 2), pool_type="max", name="pool")
# stage 2
conv_3 = Conv(pool, 80, kernel=(1, 1), name="conv_3")
conv_4 = Conv(conv_3, 192, kernel=(3, 3), name="conv_4")
pool1 = mxc.Pooling(data=conv_4, kernel=(3, 3), stride=(2, 2), pool_type="max", name="pool1")
# stage 3
in3a = Inception7A(pool1, 64,
64, 96, 96,
48, 64,
"avg", 32, "mixed")
in3b = Inception7A(in3a, 64,
64, 96, 96,
48, 64,
"avg", 64, "mixed_1")
in3c = Inception7A(in3b, 64,
64, 96, 96,
