def __init__(self, input_channels, block_channels, stride,
projection_shortcut, use_dropout, builder: ConvBuilder):
super(WRNCifarBlock, self).__init__()
assert len(block_channels) == 2
if projection_shortcut:
self.proj = builder.BNReLUConv2d(in_channels=input_channels,
out_channels=block_channels[1],
kernel_size=1,
stride=stride,
padding=0)
else:
self.proj = builder.ResIdentity(num_channels=block_channels[1])
self.conv1 = builder.BNReLUConv2d(in_channels=input_channels,
out_channels=block_channels[0],
kernel_size=3,
stride=stride,
padding=1)
if use_dropout:
self.dropout = builder.Dropout(keep_prob=0.7)
print('use dropout for WRN')
else:
self.dropout = builder.Identity()
self.conv2 = builder.BNReLUConv2d(in_channels=block_channels[0],
out_channels=block_channels[1],
kernel_size=3,
stride=1,
padding=1)
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)
