def __init__(self, builder: ConvBuilder, deps):
super(LeNet5, self).__init__()
self.bd = builder
stem = builder.Sequential()
stem.add_module(
'conv1',
builder.Conv2d(in_channels=1,
out_channels=LENET5_DEPS[0],
kernel_size=5,
bias=True))
stem.add_module('relu1', builder.ReLU())
stem.add_module('maxpool1', builder.Maxpool2d(kernel_size=2))
stem.add_module(
'conv2',
builder.Conv2d(in_channels=LENET5_DEPS[0],
out_channels=LENET5_DEPS[1],
kernel_size=5,
bias=True))
stem.add_module('relu2', builder.ReLU())
stem.add_module('maxpool2', builder.Maxpool2d(kernel_size=2))
self.stem = stem
self.flatten = builder.Flatten()
self.linear1 = builder.Linear(in_features=LENET5_DEPS[1] * 16,
out_features=LENET5_DEPS[2])
self.relu1 = builder.ReLU()
self.linear2 = builder.Linear(in_features=LENET5_DEPS[2],
out_features=10)
def __init__(self, builder:ConvBuilder):
super(LeNet300, self).__init__()
self.flatten = builder.Flatten()
self.linear1 = builder.Linear(in_features=28*28, out_features=300, bias=True)
self.relu1 = builder.ReLU()
self.linear2 = builder.Linear(in_features=300, out_features=100, bias=True)
self.relu2 = builder.ReLU()
self.linear3 = builder.Linear(in_features=100, out_features=10, bias=True)
def __init__(self, builder: ConvBuilder, in_planes, stage_deps, stride=1):
super(ResNetBottleneckStage, self).__init__()
print('building stage: in {}, deps {}'.format(in_planes, stage_deps))
assert (len(stage_deps) - 1) % 3 == 0
self.num_blocks = (len(stage_deps) - 1) // 3
stage_out_channels = stage_deps[3]
for i in range(2, self.num_blocks):
assert stage_deps[3 * i] == stage_out_channels
self.relu = builder.ReLU()
self.projection = builder.Conv2dBN(in_channels=in_planes,
out_channels=stage_deps[0],
kernel_size=1,
stride=stride)
self.align_opr = builder.ResNetAlignOpr(channels=stage_deps[0])
for i in range(self.num_blocks):
in_c = in_planes if i == 0 else stage_out_channels
block_stride = stride if i == 0 else 1
self.__setattr__(
'block{}'.format(i),
BottleneckBranch(builder=builder,
in_channels=in_c,
deps=stage_deps[1 + i * 3:4 + i * 3],
stride=block_stride))
def __init__(self, num_classes, builder: ConvBuilder, deps):
super(VCNet, self).__init__()
self.stem = _create_vgg_stem(builder=builder, deps=deps)
self.flatten = builder.Flatten()
self.linear1 = builder.IntermediateLinear(in_features=deps[12],
out_features=512)
self.relu = builder.ReLU()
self.linear2 = builder.Linear(in_features=512,
out_features=num_classes)
def __init__(self, builder:ConvBuilder, deps):
super(LeNet5BN, self).__init__()
self.bd = builder
stem = builder.Sequential()
stem.add_module('conv1', builder.Conv2dBNReLU(in_channels=1, out_channels=deps[0], kernel_size=5))
stem.add_module('maxpool1', builder.Maxpool2d(kernel_size=2))
stem.add_module('conv2', builder.Conv2dBNReLU(in_channels=deps[0], out_channels=deps[1], kernel_size=5))
stem.add_module('maxpool2', builder.Maxpool2d(kernel_size=2))
self.stem = stem
self.flatten = builder.Flatten()
self.linear1 = builder.IntermediateLinear(in_features=deps[1] * 16, out_features=500)
self.relu1 = builder.ReLU()
self.linear2 = builder.Linear(in_features=500, out_features=10)
def __init__(self,
conv_idx,
builder: ConvBuilder,
preced_layer_idx,
in_features,
out_features,
bias=True):
super(AOFPFCReluLayer, self).__init__()
self.conv_idx = conv_idx
self.base_path = builder.Linear(in_features=in_features,
out_features=out_features,
bias=bias)
self.relu = builder.ReLU()
self.register_buffer('t_value', torch.zeros(1))
self.preced_layer_idx = preced_layer_idx
def __init__(self, builder:ConvBuilder, deps=SIMPLE_ALEXNET_DEPS):
super(AlexBN, self).__init__()
# self.bd = builder
stem = builder.Sequential()
stem.add_module('conv1', builder.Conv2dBNReLU(in_channels=3, out_channels=deps[0], kernel_size=11, stride=4, padding=2))
stem.add_module('maxpool1', builder.Maxpool2d(kernel_size=3, stride=2))
stem.add_module('conv2', builder.Conv2dBNReLU(in_channels=deps[0], out_channels=deps[1], kernel_size=5, padding=2))
stem.add_module('maxpool2', builder.Maxpool2d(kernel_size=3, stride=2))
stem.add_module('conv3',
builder.Conv2dBNReLU(in_channels=deps[1], out_channels=deps[2], kernel_size=3, padding=1))
stem.add_module('conv4',
builder.Conv2dBNReLU(in_channels=deps[2], out_channels=deps[3], kernel_size=3, padding=1))
stem.add_module('conv5',
builder.Conv2dBNReLU(in_channels=deps[3], out_channels=deps[4], kernel_size=3, padding=1))
stem.add_module('maxpool3', builder.Maxpool2d(kernel_size=3, stride=2))
self.stem = stem
self.flatten = builder.Flatten()
self.linear1 = builder.Linear(in_features=deps[4] * 6 * 6, out_features=4096)
self.relu1 = builder.ReLU()
self.drop1 = builder.Dropout(0.5)
self.linear2 = builder.Linear(in_features=4096, out_features=4096)
self.relu2 = builder.ReLU()
self.drop2 = builder.Dropout(0.5)
self.linear3 = builder.Linear(in_features=4096, out_features=1000)
def __init__(self,
builder: ConvBuilder,
in_planes,
stage_deps,
stride=1,
is_first=False):
super(ResNetBasicStage, self).__init__()
print('building stage: in {}, deps {}'.format(in_planes, stage_deps))
self.num_blocks = len(stage_deps) // 2
stage_out_channels = stage_deps[0]
for i in range(0, self.num_blocks):
assert stage_deps[i * 2 + 2] == stage_out_channels
if is_first:
self.conv1 = builder.Conv2dBN(in_channels=in_planes,
out_channels=stage_out_channels,
kernel_size=3,
stride=1,
padding=1)
# self.projection = builder.ResIdentity(num_channels=stage_out_channels)
else:
self.projection = builder.Conv2dBN(in_channels=in_planes,
out_channels=stage_out_channels,
kernel_size=1,
stride=stride)
self.relu = builder.ReLU()
self.align_opr = builder.ResNetAlignOpr(channels=stage_out_channels)
for i in range(self.num_blocks):
if i == 0 and is_first:
in_c = stage_deps[0]
elif i == 0:
in_c = in_planes
else:
in_c = stage_out_channels
block_stride = stride if i == 0 else 1
self.__setattr__(
'block{}'.format(i),
BasicBranch(builder=builder,
in_channels=in_c,
deps=stage_deps[1 + i * 2:3 + i * 2],
stride=block_stride))
def __init__(self, builder: ConvBuilder, in_planes, planes, stride=1):
super(BasicBlock, self).__init__()
self.bd = builder
self.relu = builder.ReLU()
if stride != 1 or in_planes != self.expansion * planes:
self.shortcut = builder.Conv2dBN(in_channels=in_planes,
out_channels=self.expansion *
planes,
kernel_size=1,
stride=stride)
else:
self.shortcut = builder.ResIdentity(num_channels=in_planes)
self.conv1 = builder.Conv2dBNReLU(in_channels=in_planes,
out_channels=planes,
kernel_size=3,
stride=stride,
padding=1)
self.conv2 = builder.Conv2dBN(in_channels=planes,
out_channels=self.expansion * planes,
kernel_size=3,
stride=1,
padding=1)
def __init__(self, num_classes, builder: ConvBuilder, deps):
super(VANet, self).__init__()
sq = builder.Sequential()
sq.add_module(
'conv1',
builder.Conv2dBNReLU(in_channels=3,
out_channels=deps[0],
kernel_size=3,
stride=1,
padding=1))
sq.add_module(
'conv2',
builder.Conv2dBNReLU(in_channels=deps[0],
out_channels=deps[1],
kernel_size=3,
stride=1,
padding=1))
sq.add_module('maxpool1', builder.Maxpool2d(kernel_size=2))
sq.add_module(
'conv3',
builder.Conv2dBNReLU(in_channels=deps[1],
out_channels=deps[2],
kernel_size=3,
stride=1,
padding=1))
sq.add_module(
'conv4',
builder.Conv2dBNReLU(in_channels=deps[2],
out_channels=deps[3],
kernel_size=3,
stride=1,
padding=1))
sq.add_module('maxpool2', builder.Maxpool2d(kernel_size=2))
sq.add_module(
'conv5',
builder.Conv2dBNReLU(in_channels=deps[3],
out_channels=deps[4],
kernel_size=3,
stride=1,
padding=1))
sq.add_module(
'conv6',
builder.Conv2dBNReLU(in_channels=deps[4],
out_channels=deps[5],
kernel_size=3,
stride=1,
padding=1))
sq.add_module(
'conv7',
builder.Conv2dBNReLU(in_channels=deps[5],
out_channels=deps[6],
kernel_size=3,
stride=1,
padding=1))
sq.add_module('maxpool3', builder.Maxpool2d(kernel_size=2))
sq.add_module(
'conv8',
builder.Conv2dBNReLU(in_channels=deps[6],
out_channels=deps[7],
kernel_size=3,
stride=1,
padding=1))
sq.add_module(
'conv9',
builder.Conv2dBNReLU(in_channels=deps[7],
out_channels=deps[8],
kernel_size=3,
stride=1,
padding=1))
sq.add_module(
'conv10',
builder.Conv2dBNReLU(in_channels=deps[8],
out_channels=deps[9],
kernel_size=3,
stride=1,
padding=1))
sq.add_module('maxpool4', builder.Maxpool2d(kernel_size=2))
sq.add_module(
'conv11',
builder.Conv2dBNReLU(in_channels=deps[9],
out_channels=deps[10],
kernel_size=3,
stride=1,
padding=1))
sq.add_module(
'conv12',
builder.Conv2dBNReLU(in_channels=deps[10],
out_channels=deps[11],
kernel_size=3,
stride=1,
padding=1))
sq.add_module(
'conv13',
builder.Conv2dBNReLU(in_channels=deps[11],
out_channels=deps[12],
kernel_size=3,
stride=1,
padding=1))
sq.add_module('maxpool5', builder.Maxpool2d(kernel_size=2))
self.stem = sq
self.flatten = builder.Flatten()
self.linear1 = builder.IntermediateLinear(in_features=deps[12],
out_features=512)
self.relu = builder.ReLU()
self.linear2 = builder.Linear(in_features=512,
out_features=num_classes)
