def map_out_conv(self, in_channels):
return cudafy(
HALNet.HALNetConvBlock(kernel_size=3,
stride=1,
filters=21,
in_channels=in_channels,
padding=1), self.use_cuda)
def forward_prior(self, conv4fout):
out_prior = self.map_out_conv_prior(conv4fout)
out_prior = self.main_loss_deconv_prior1(out_prior)
out_prior = out_prior.view(
(out_prior.shape[0], out_prior.shape[2], out_prior.shape[3]))
if self.cross_entropy:
out_prior = cudafy(self.softmax_1d(out_prior), self.use_cuda)
return out_prior
def __init__(self, params_dict):
super(HALNet_prior, self).__init__(params_dict)
if self.cross_entropy:
self.softmax_final = cudafy(HALNet.SoftmaxLogProbability2D(),
self.use_cuda)
self.softmax_final = cudafy(HALNet.SoftmaxLogProbability2D(),
self.use_cuda)
self.map_out_conv_prior = cudafy(
HALNet.HALNetConvBlock(kernel_size=3,
stride=1,
filters=1,
in_channels=256,
padding=1), self.use_cuda)
self.main_loss_deconv_prior1 = cudafy(
nn.Upsample(size=self.prior_size, mode='bilinear'), self.use_cuda)
self.softmax_1d = cudafy(SoftmaxLogProbability1D(), self.use_cuda)
def __init__(self, params_dict):
super(HALNet, self).__init__()
# initialize variables
self.joint_ixs = parse_model_param(params_dict,
'joint_ixs',
default_value="Mandatory")
self.use_cuda = parse_model_param(params_dict,
'use_cuda',
default_value=False)
self.num_joints = len(self.joint_ixs)
self.cross_entropy = parse_model_param(params_dict,
'cross_entropy',
default_value=False)
# build network
self.conv1 = cudafy(
HALNetConvBlock(kernel_size=7,
stride=1,
filters=64,
in_channels=4,
padding=3), self.use_cuda)
self.mp1 = cudafy(nn.MaxPool2d(kernel_size=3, stride=2, padding=1),
self.use_cuda)
self.res2a = cudafy(
HALNetResBlockConv(stride=1,
filters1=64,
filters2=256,
padding_right1=1), self.use_cuda)
self.res2b = cudafy(HALNetResBlockIDSkip(filters1=64, filters2=256),
self.use_cuda)
self.res2c = cudafy(HALNetResBlockIDSkip(filters1=64, filters2=256),
self.use_cuda)
self.res3a = cudafy(
HALNetResBlockConv(stride=2,
filters1=128,
filters2=512,
padding_right3=1,
first_in_channels=256), self.use_cuda)
self.interm_loss1 = cudafy(
HALNetConvBlock(kernel_size=3,
stride=1,
filters=self.num_joints,
in_channels=512,
padding=1), self.use_cuda)
self.interm_loss1_deconv = cudafy(
nn.Upsample(scale_factor=4, mode='bilinear', align_corners=True),
self.use_cuda)
self.interm_loss1_softmax = cudafy(SoftmaxLogProbability2D(),
self.use_cuda)
self.res3b = cudafy(HALNetResBlockIDSkip(filters1=128, filters2=512),
self.use_cuda)
self.res3c = cudafy(HALNetResBlockIDSkip(filters1=128, filters2=512),
self.use_cuda)
self.res4a = cudafy(
HALNetResBlockConv(stride=2,
filters1=256,
filters2=1024,
padding_right3=1,
first_in_channels=512), self.use_cuda)
self.interm_loss2 = cudafy(
HALNetConvBlock(kernel_size=3,
stride=1,
filters=self.num_joints,
in_channels=1024,
padding=1), self.use_cuda)
self.interm_loss2_deconv = cudafy(
nn.Upsample(scale_factor=8, mode='bilinear', align_corners=True),
self.use_cuda)
self.interm_loss2_softmax = cudafy(SoftmaxLogProbability2D(),
self.use_cuda)
self.res4b = cudafy(HALNetResBlockIDSkip(filters1=256, filters2=1024),
self.use_cuda)
self.res4c = cudafy(HALNetResBlockIDSkip(filters1=256, filters2=1024),
self.use_cuda)
self.res4d = cudafy(HALNetResBlockIDSkip(filters1=256, filters2=1024),
self.use_cuda)
self.conv4e = cudafy(
HALNetConvBlock(kernel_size=3,
stride=1,
filters=512,
in_channels=1024,
padding=1), self.use_cuda)
self.interm_loss3 = cudafy(
HALNetConvBlock(kernel_size=3,
stride=1,
filters=self.num_joints,
in_channels=512,
padding=1), self.use_cuda)
self.interm_loss3_deconv = cudafy(
nn.Upsample(scale_factor=8, mode='bilinear', align_corners=True),
self.use_cuda)
self.interm_loss3_softmax = cudafy(SoftmaxLogProbability2D(),
self.use_cuda)
self.conv4f = cudafy(
HALNetConvBlock(kernel_size=3,
stride=1,
filters=256,
in_channels=512,
padding=1), self.use_cuda)
self.main_loss_conv = cudafy(
HALNetConvBlock(kernel_size=3,
stride=1,
filters=self.num_joints,
in_channels=256,
padding=1), self.use_cuda)
self.main_loss_deconv = cudafy(
nn.Upsample(scale_factor=8, mode='bilinear', align_corners=True),
self.use_cuda)
if self.cross_entropy:
self.softmax_final = cudafy(SoftmaxLogProbability2D(),
self.use_cuda)
def __init__(self, params_dict):
super(JORNet, self).__init__(params_dict)
self.num_joints = 20
self.main_loss_conv = cudafy(
HALNet.HALNetConvBlock(kernel_size=3,
stride=1,
filters=21,
in_channels=256,
padding=1), self.use_cuda)
self.main_loss_deconv1 = cudafy(
nn.Upsample(size=self.crop_res, mode='bilinear'), self.use_cuda)
#self.main_loss_deconv2 = cudafy(nn.Upsample(scale_factor=1, mode='bilinear'),
# self.use_cuda)
if self.cross_entropy:
self.softmax_final = cudafy(HALNet.SoftmaxLogProbability2D(),
self.use_cuda)
self.innerproduct1_joint1 = cudafy(
nn.Linear(in_features=524288, out_features=200), self.use_cuda)
self.innerproduct2_joint1 = cudafy(
nn.Linear(in_features=200, out_features=self.num_joints * 3),
self.use_cuda)
self.innerproduct1_joint2 = cudafy(
nn.Linear(in_features=262144, out_features=200), self.use_cuda)
self.innerproduct2_joint2 = cudafy(
nn.Linear(in_features=200, out_features=self.num_joints * 3),
self.use_cuda)
self.innerproduct1_joint3 = cudafy(
nn.Linear(in_features=131072, out_features=200), self.use_cuda)
self.innerproduct2_joint3 = cudafy(
nn.Linear(in_features=200, out_features=self.num_joints * 3),
self.use_cuda)
self.innerproduct1_joint_main = cudafy(
nn.Linear(in_features=65536, out_features=200), self.use_cuda)
self.innerproduct2_join_main = cudafy(
nn.Linear(in_features=200, out_features=self.num_joints * 3),
self.use_cuda)
def map_out_to_loss(self, innerprod1_size):
return cudafy(nn.Linear(in_features=innerprod1_size, out_features=200),
self.use_cuda)