def __init__(self, num_channels, num_kp, block_expansion, max_features, num_down_blocks,
num_bottleneck_blocks, estimate_occlusion_map=False, dense_motion_params=None,
estimate_jacobian=False, scale_factor=0.25):
super(Generator, self).__init__()
self.source_first = AntiAliasInterpolation2d(num_channels, scale_factor)
first_input = int(block_expansion / scale_factor)
self.first = SameBlock2d(num_channels + 2, first_input, kernel_size=(7, 7), padding=(3, 3)) # +2 masks
down_blocks = []
for i in range(num_down_blocks):
in_features = min(max_features, block_expansion * (2 ** i))
out_features = min(max_features, block_expansion * (2 ** (i + 1)))
down_blocks.append(DownBlock2d(in_features, out_features, kernel_size=(3, 3), padding=(1, 1)))
self.down_blocks = nn.ModuleList(down_blocks)
up_blocks = []
for i in range(num_down_blocks):
in_features = min(max_features, block_expansion * (2 ** (num_down_blocks - i)))
out_features = min(max_features, block_expansion * (2 ** (num_down_blocks - i - 1)))
up_blocks.append(UpBlock2d(in_features, out_features, kernel_size=(3, 3), padding=(1, 1)))
self.up_blocks = nn.ModuleList(up_blocks)
self.bottleneck = torch.nn.Sequential()
in_features = min(max_features, block_expansion * (2 ** num_down_blocks))
for i in range(num_bottleneck_blocks):
self.bottleneck.add_module('r' + str(i), ResBlock2d(in_features, kernel_size=(3, 3), padding=(1, 1)))
self.final = nn.Conv2d(block_expansion, num_channels, kernel_size=(7, 7), padding=(3, 3))
self.num_channels = num_channels
self.hourglass = Hourglass(block_expansion=block_expansion, in_features=8, max_features=1024, num_blocks=5)
self.final_hourglass = nn.Conv2d(in_channels=self.hourglass.out_filters, out_channels=3, kernel_size=(7, 7),
padding=(3, 3))
def __init__(self, num_channels, block_expansion, max_features, num_down_blocks, num_bottleneck_blocks):
super(StylizerGenerator, self).__init__()
# first 维持输入和输出维度相同，channel数量不同
self.first = SameBlock2d(num_channels, block_expansion, kernel_size=(7, 7), padding=(3, 3))
# 声明下采样层
down_blocks = []
for i in range(num_down_blocks):
in_features = min(max_features, block_expansion * (2 ** i))
out_features = min(max_features, block_expansion * (2 ** (i + 1)))
down_blocks.append(DownBlock2d(in_features, out_features, kernel_size=(3, 3), padding=(1, 1)))
# 注：此处才是用列表声明网络层的正确用法
# 储存时会通过储存对应self的名字所对应的内容
self.down_blocks = nn.ModuleList(down_blocks)
# 声明上采样层
up_blocks = []
for i in range(num_down_blocks):
in_features = min(max_features, block_expansion * (2 ** (num_down_blocks - i)))
out_features = min(max_features, block_expansion * (2 ** (num_down_blocks - i - 1)))
up_blocks.append(UpBlock2d(in_features, out_features, kernel_size=(3, 3), padding=(1, 1)))
# 注：此处用列表声明模块同上
self.up_blocks = nn.ModuleList(up_blocks)
# 声明生成器中的瓶颈层
self.bottleneck = torch.nn.Sequential()
in_features = min(max_features, block_expansion * (2 ** num_down_blocks))
for i in range(num_bottleneck_blocks):
self.bottleneck.add_module('r' + str(i), ResBlock2d(in_features, kernel_size=(3, 3), padding=(1, 1)))
# 声明最后的输出层
self.final = nn.Conv2d(block_expansion, num_channels, kernel_size=(7, 7), padding=(3, 3))
self.num_channels = num_channels
def __init__(self, num_channels, num_kp, block_expansion, max_features, num_down_blocks,
num_bottleneck_blocks, estimate_occlusion_map=False, dense_motion_params=None, estimate_jacobian=False):
super(OcclusionAwareGenerator, self).__init__()
if dense_motion_params is not None:
self.dense_motion_network = DenseMotionNetwork(num_kp=num_kp, num_channels=num_channels,
estimate_occlusion_map=estimate_occlusion_map,
**dense_motion_params)
else:
self.dense_motion_network = None
self.first = SameBlock2d(num_channels, block_expansion, kernel_size=(7, 7), padding=(3, 3))
down_blocks = []
for i in range(num_down_blocks):
in_features = min(max_features, block_expansion * (2 ** i))
out_features = min(max_features, block_expansion * (2 ** (i + 1)))
down_blocks.append(DownBlock2d(in_features, out_features, kernel_size=(3, 3), padding=(1, 1)))
self.down_blocks = nn.ModuleList(down_blocks)
up_blocks = []
for i in range(num_down_blocks):
in_features = min(max_features, block_expansion * (2 ** (num_down_blocks - i)))
out_features = min(max_features, block_expansion * (2 ** (num_down_blocks - i - 1)))
up_blocks.append(UpBlock2d(in_features, out_features, kernel_size=(3, 3), padding=(1, 1)))
self.up_blocks = nn.ModuleList(up_blocks)
self.bottleneck = torch.nn.Sequential()
in_features = min(max_features, block_expansion * (2 ** num_down_blocks))
for i in range(num_bottleneck_blocks):
self.bottleneck.add_module('r' + str(i), ResBlock2d(in_features, kernel_size=(3, 3), padding=(1, 1)))
self.final = nn.Conv2d(block_expansion, num_channels, kernel_size=(7, 7), padding=(3, 3))
self.estimate_occlusion_map = estimate_occlusion_map
self.num_channels = num_channels
def __init__(self,
num_channels,
block_expansion,
max_features,
num_down_blocks,
num_bottleneck_blocks,
num_segments,
estimate_visibility=False,
**kwargs):
super(ReconstructionModule, self).__init__()
self.first = SameBlock2d(num_channels,
block_expansion,
kernel_size=(7, 7),
padding=(3, 3))
down_blocks = []
for i in range(num_down_blocks):
in_features = min(max_features, block_expansion * (2**i))
out_features = min(max_features, block_expansion * (2**(i + 1)))
down_blocks.append(
DownBlock2d(in_features,
out_features,
kernel_size=(3, 3),
padding=(1, 1)))
self.down_blocks = nn.ModuleList(down_blocks)
up_blocks = []
for i in range(num_down_blocks):
in_features = min(max_features,
block_expansion * (2**(num_down_blocks - i)))
out_features = min(
max_features, block_expansion * (2**(num_down_blocks - i - 1)))
up_blocks.append(
UpBlock2d(in_features,
out_features,
kernel_size=(3, 3),
padding=(1, 1)))
self.up_blocks = nn.ModuleList(up_blocks)
self.bottleneck = torch.nn.Sequential()
in_features = min(max_features, block_expansion * (2**num_down_blocks))
for i in range(num_bottleneck_blocks):
self.bottleneck.add_module(
'r' + str(i),
ResBlock2d(in_features, kernel_size=(3, 3), padding=(1, 1)))
self.final = nn.Conv2d(block_expansion,
num_channels,
kernel_size=(7, 7),
padding=(3, 3))
self.estimate_visibility = estimate_visibility
self.num_channels = num_channels
self.num_segments = num_segments
def __init__(self, num_channels, num_kp, block_expansion, max_features, num_down_blocks,
num_bottleneck_blocks, estimate_occlusion_map=False, dense_motion_params=None, estimate_jacobian=False):
super(OcclusionAwareGenerator, self).__init__()
# 初始化一个稠密运动场网络模块
if dense_motion_params is not None:
self.dense_motion_network = DenseMotionNetwork(num_kp=num_kp, num_channels=num_channels,
estimate_occlusion_map=estimate_occlusion_map,
**dense_motion_params)
else:
self.dense_motion_network = None
# first 维持输入和输出维度相同，channel数量不同
self.first = SameBlock2d(num_channels, block_expansion, kernel_size=(7, 7), padding=(3, 3))
# 声明下采样层
down_blocks = []
for i in range(num_down_blocks):
in_features = min(max_features, block_expansion * (2 ** i))
out_features = min(max_features, block_expansion * (2 ** (i + 1)))
down_blocks.append(DownBlock2d(in_features, out_features, kernel_size=(3, 3), padding=(1, 1)))
# 注：此处才是用列表声明网络层的正确用法
# 储存时会通过储存对应self的名字所对应的内容
self.down_blocks = nn.ModuleList(down_blocks)
# 声明上采样层
up_blocks = []
for i in range(num_down_blocks):
in_features = min(max_features, block_expansion * (2 ** (num_down_blocks - i)))
out_features = min(max_features, block_expansion * (2 ** (num_down_blocks - i - 1)))
up_blocks.append(UpBlock2d(in_features, out_features, kernel_size=(3, 3), padding=(1, 1)))
# 注：此处用列表声明模块同上
self.up_blocks = nn.ModuleList(up_blocks)
# 声明生成器中的瓶颈层
self.bottleneck = torch.nn.Sequential()
in_features = min(max_features, block_expansion * (2 ** num_down_blocks))
for i in range(num_bottleneck_blocks):
self.bottleneck.add_module('r' + str(i), ResBlock2d(in_features, kernel_size=(3, 3), padding=(1, 1)))
# 声明最后的输出层
self.final = nn.Conv2d(block_expansion, num_channels, kernel_size=(7, 7), padding=(3, 3))
self.estimate_occlusion_map = estimate_occlusion_map
self.num_channels = num_channels
def __init__(self,
num_channels,
num_regions,
block_expansion,
max_features,
num_down_blocks,
num_bottleneck_blocks,
pixelwise_flow_predictor_params=None,
skips=False,
revert_axis_swap=True):
super(Generator, self).__init__()
if pixelwise_flow_predictor_params is not None:
self.pixelwise_flow_predictor = PixelwiseFlowPredictor(
num_regions=num_regions,
num_channels=num_channels,
revert_axis_swap=revert_axis_swap,
**pixelwise_flow_predictor_params)
else:
self.pixelwise_flow_predictor = None
self.first = SameBlock2d(num_channels,
block_expansion,
kernel_size=(7, 7),
padding=(3, 3))
down_blocks = []
for i in range(num_down_blocks):
in_features = min(max_features, block_expansion * (2**i))
out_features = min(max_features, block_expansion * (2**(i + 1)))
down_blocks.append(
DownBlock2d(in_features,
out_features,
kernel_size=(3, 3),
padding=(1, 1)))
self.down_blocks = nn.ModuleList(down_blocks)
up_blocks = []
for i in range(num_down_blocks):
in_features = min(max_features,
block_expansion * (2**(num_down_blocks - i)))
out_features = min(
max_features, block_expansion * (2**(num_down_blocks - i - 1)))
up_blocks.append(
UpBlock2d(in_features,
out_features,
kernel_size=(3, 3),
padding=(1, 1)))
self.up_blocks = nn.ModuleList(up_blocks)
self.bottleneck = torch.nn.Sequential()
in_features = min(max_features, block_expansion * (2**num_down_blocks))
for i in range(num_bottleneck_blocks):
self.bottleneck.add_module(
'r' + str(i),
ResBlock2d(in_features, kernel_size=(3, 3), padding=(1, 1)))
self.final = nn.Conv2d(block_expansion,
num_channels,
kernel_size=(7, 7),
padding=(3, 3))
self.num_channels = num_channels
self.skips = skips