class DeepLabV3(nn.Module):
def __init__(self, configer):
self.inplanes = 128
super(DeepLabV3, self).__init__()
self.configer = configer
self.num_classes = self.configer.get('data', 'num_classes')
self.backbone = BackboneSelector(configer).get_backbone()
self.head = nn.Sequential(ASPPModule(self.backbone.get_num_features(),
norm_type=self.configer.get('network', 'norm_type')),
nn.Conv2d(512, self.num_classes, kernel_size=1, stride=1, padding=0, bias=True))
self.dsn = nn.Sequential(
nn.Conv2d(1024, 512, kernel_size=3, stride=1, padding=1),
ModuleHelper.BNReLU(512, norm_type=self.configer.get('network', 'norm_type')),
nn.Dropout2d(0.1),
nn.Conv2d(512, self.num_classes, kernel_size=1, stride=1, padding=0, bias=True)
)
self.valid_loss_dict = configer.get('loss', 'loss_weights', configer.get('loss.loss_type'))
def forward(self, data_dict):
x = self.backbone(data_dict['img'])
x_dsn = self.dsn(x[-2])
x = self.head(x[-1])
x_dsn = F.interpolate(x_dsn, size=(data_dict['img'].size(2), data_dict['img'].size(3)),
mode="bilinear", align_corners=True)
x = F.interpolate(x, size=(data_dict['img'].size(2), data_dict['img'].size(3)),
mode="bilinear", align_corners=True)
out_dict = dict(dsn_out=x_dsn, out=x)
if self.configer.get('phase') == 'test':
return out_dict
loss_dict = dict()
if 'dsn_ce_loss' in self.valid_loss_dict:
loss_dict['dsn_ce_loss'] = dict(
params=[x_dsn, data_dict['labelmap']],
type=torch.cuda.LongTensor([BASE_LOSS_DICT['ce_loss']]),
weight=torch.cuda.FloatTensor([self.valid_loss_dict['dsn_ce_loss']])
)
if 'ce_loss' in self.valid_loss_dict:
loss_dict['ce_loss'] = dict(
params=[x, data_dict['labelmap']],
type=torch.cuda.LongTensor([BASE_LOSS_DICT['ce_loss']]),
weight=torch.cuda.FloatTensor([self.valid_loss_dict['ce_loss']])
)
if 'ohem_ce_loss' in self.valid_loss_dict:
loss_dict['ohem_ce_loss'] = dict(
params=[x, data_dict['labelmap']],
type=torch.cuda.LongTensor([BASE_LOSS_DICT['ohem_ce_loss']]),
weight=torch.cuda.FloatTensor([self.valid_loss_dict['ohem_ce_loss']])
)
return out_dict, loss_dict
class NonLocalNet_nowd(nn.Sequential):
def __init__(self, configer):
super(NonLocalNet_nowd, self).__init__()
self.configer = configer
self.num_classes = self.configer.get('data', 'num_classes')
self.backbone = BackboneSelector(configer).get_backbone()
num_features = self.backbone.get_num_features()
self.dsn = nn.Sequential(
_ConvBatchNormReluBlock(num_features // 2, num_features // 4, 3, 1,
norm_type=self.configer.get('network', 'norm_type')),
nn.Dropout2d(0.1),
nn.Conv2d(num_features // 4, self.num_classes, 1, 1, 0)
)
self.nlm = NLModule_nowd(num_features, 512, self.num_classes, self.configer)
self.valid_loss_dict = configer.get('loss', 'loss_weights', configer.get('loss.loss_type'))
def forward(self, data_dict):
x = self.backbone(data_dict['img'])
aux_x = self.dsn(x[-2])
x = self.nlm(x[-1])
x_dsn = F.interpolate(aux_x, size=(data_dict['img'].size(2), data_dict['img'].size(3)),
mode="bilinear", align_corners=True)
x = F.interpolate(x, size=(data_dict['img'].size(2), data_dict['img'].size(3)),
mode="bilinear", align_corners=True)
out_dict = dict(dsn_out=x_dsn, out=x)
if self.configer.get('phase') == 'test':
return out_dict
loss_dict = dict()
if 'dsn_ce_loss' in self.valid_loss_dict:
loss_dict['dsn_ce_loss'] = dict(
params=[x_dsn, data_dict['labelmap']],
type=torch.cuda.LongTensor([BASE_LOSS_DICT['ce_loss']]),
weight=torch.cuda.FloatTensor([self.valid_loss_dict['dsn_ce_loss']])
)
if 'ce_loss' in self.valid_loss_dict:
loss_dict['ce_loss'] = dict(
params=[x, data_dict['labelmap']],
type=torch.cuda.LongTensor([BASE_LOSS_DICT['ce_loss']]),
weight=torch.cuda.FloatTensor([self.valid_loss_dict['ce_loss']])
)
if 'ohem_ce_loss' in self.valid_loss_dict:
loss_dict['ohem_ce_loss'] = dict(
params=[x, data_dict['labelmap']],
type=torch.cuda.LongTensor([BASE_LOSS_DICT['ohem_ce_loss']]),
weight=torch.cuda.FloatTensor([self.valid_loss_dict['ohem_ce_loss']])
)
return out_dict, loss_dict
class OpenPose(nn.Module):
def __init__(self, configer):
super(OpenPose, self).__init__()
self.configer = configer
self.backbone = BackboneSelector(configer).get_backbone()
self.pose_model = PoseModel(configer, self.backbone.get_num_features())
self.valid_loss_dict = configer.get('loss', 'loss_weights',
configer.get('loss.loss_type'))
def forward(self, data_dict):
x = self.backbone(data_dict['img'])
paf_out, heatmap_out = self.pose_model(x)
out_dict = dict(paf=paf_out[-1], heatmap=heatmap_out[-1])
if self.configer.get('phase') == 'test':
return out_dict
loss_dict = dict()
for i in range(len(paf_out)):
if 'paf_loss{}'.format(i) in self.valid_loss_dict:
loss_dict['paf_loss{}'.format(i)] = dict(
params=[
paf_out[i] * data_dict['maskmap'],
data_dict['vecmap'] * data_dict['maskmap']
],
type=torch.cuda.LongTensor([BASE_LOSS_DICT['mse_loss']]),
weight=torch.cuda.FloatTensor(
[self.valid_loss_dict['paf_loss{}'.format(i)]]))
for i in range(len(heatmap_out)):
if 'heatmap_loss{}'.format(i) in self.valid_loss_dict:
loss_dict['heatmap_loss{}'.format(i)] = dict(
params=[
heatmap_out[i] * data_dict['maskmap'],
data_dict['heatmap'] * data_dict['maskmap']
],
type=torch.cuda.LongTensor([BASE_LOSS_DICT['mse_loss']]),
weight=torch.cuda.FloatTensor(
[self.valid_loss_dict['heatmap_loss{}'.format(i)]]))
return out_dict, loss_dict
class DenseASPP(nn.Module):
"""
* output_scale can only set as 8 or 16
"""
def __init__(self, configer):
super(DenseASPP, self).__init__()
self.configer = configer
dropout0 = MODEL_CONFIG['dropout0']
dropout1 = MODEL_CONFIG['dropout1']
d_feature0 = MODEL_CONFIG['d_feature0']
d_feature1 = MODEL_CONFIG['d_feature1']
self.backbone = BackboneSelector(configer).get_backbone()
num_features = self.backbone.get_num_features()
self.trans = _Transition(num_input_features=self.num_features,
num_output_features=self.num_features // 2,
norm_type=self.configer.get(
'network', 'norm_type'))
self.num_features = self.num_features // 2
self.ASPP_3 = _DenseAsppBlock(input_num=num_features,
num1=d_feature0,
num2=d_feature1,
dilation_rate=3,
drop_out=dropout0,
norm_type=self.configer.get(
'network', 'norm_type'))
self.ASPP_6 = _DenseAsppBlock(input_num=num_features + d_feature1 * 1,
num1=d_feature0,
num2=d_feature1,
dilation_rate=6,
drop_out=dropout0,
norm_type=self.configer.get(
'network', 'norm_type'))
self.ASPP_12 = _DenseAsppBlock(input_num=num_features + d_feature1 * 2,
num1=d_feature0,
num2=d_feature1,
dilation_rate=12,
drop_out=dropout0,
norm_type=self.configer.get(
'network', 'norm_type'))
self.ASPP_18 = _DenseAsppBlock(input_num=num_features + d_feature1 * 3,
num1=d_feature0,
num2=d_feature1,
dilation_rate=18,
drop_out=dropout0,
norm_type=self.configer.get(
'network', 'norm_type'))
self.ASPP_24 = _DenseAsppBlock(input_num=num_features + d_feature1 * 4,
num1=d_feature0,
num2=d_feature1,
dilation_rate=24,
drop_out=dropout0,
norm_type=self.configer.get(
'network', 'norm_type'))
num_features = num_features + 5 * d_feature1
self.classification = nn.Sequential(
nn.Dropout2d(p=dropout1),
nn.Conv2d(num_features,
self.configer.get('data', 'num_classes'),
kernel_size=1,
padding=0))
self.valid_loss_dict = configer.get('loss', 'loss_weights',
configer.get('loss.loss_type'))
def forward(self, data_dict):
x = self.backbone(data_dict['img'])
feature = self.trans(x)
aspp3 = self.ASPP_3(feature)
feature = torch.cat((aspp3, feature), dim=1)
aspp6 = self.ASPP_6(feature)
feature = torch.cat((aspp6, feature), dim=1)
aspp12 = self.ASPP_12(feature)
feature = torch.cat((aspp12, feature), dim=1)
aspp18 = self.ASPP_18(feature)
feature = torch.cat((aspp18, feature), dim=1)
aspp24 = self.ASPP_24(feature)
feature = torch.cat((aspp24, feature), dim=1)
x = self.classification(feature)
x = F.interpolate(x,
size=(data_dict['img'].size(2),
data_dict['img'].size(3)),
mode="bilinear",
align_corners=True)
out_dict = dict(out=x)
if self.configer.get('phase') == 'test':
return out_dict
loss_dict = dict()
if 'ce_loss' in self.valid_loss_dict:
loss_dict['ce_loss'] = dict(params=[x, data_dict['labelmap']],
type=torch.cuda.LongTensor(
[BASE_LOSS_DICT['ce_loss']]),
weight=torch.cuda.FloatTensor(
[self.valid_loss_dict['ce_loss']]))
if 'ohem_ce_loss' in self.valid_loss_dict:
loss_dict['ohem_ce_loss'] = dict(
params=[x, data_dict['labelmap']],
type=torch.cuda.LongTensor([BASE_LOSS_DICT['ohem_ce_loss']]),
weight=torch.cuda.FloatTensor(
[self.valid_loss_dict['ohem_ce_loss']]))
return out_dict, loss_dict