def init_weights(self, pretrained='caffemodel'):
""" Two ways to init weights:
1) by copying pretrained weights.
2) by filling empirical weights. (e.g. gaussian, xavier, uniform, constant, bilinear).
"""
if pretrained is None:
print(
'initialize weights by filling (Fc:gaussian, Conv:kaiming_normal).'
)
init_weights_by_filling(self)
elif pretrained == 'caffemodel':
print(
"Initializing weights by copying (pretrained caffe weights).")
src2dsts = dict(conv1='Convs.0',
conv2='Convs.4',
conv3='Convs.8',
conv4='Convs.10',
conv5='Convs.12',
fc6='Fcs.0',
fc7='Fcs.3')
copy_weights(self.state_dict(),
'caffemodel.alexnet',
src2dsts=src2dsts)
elif pretrained == 'torchmodel':
raise NotImplementedError
else:
raise NotImplementedError
return self
def init_weights(self, pretrained='caffemodel'):
""" Two ways to init weights:
1) by copying pretrained weights.
2) by filling empirical weights. (e.g. gaussian, xavier, uniform, constant, bilinear).
"""
if pretrained is None:
print('Initializing weights by filling (with gaussian).')
init_weights_by_filling(self)
elif pretrained=='caffemodel':
print("Initializing weights by copying (pretrained caffe weights).")
src2dsts= odict(conv1_1='conv1.conv.0' , conv1_2='conv1.conv.2' ,
conv2_1='conv2.conv.0' , conv2_2='conv2.conv.2' ,
conv3_1='conv3.conv.0' , conv3_2='conv3.conv.2', conv3_3='conv3.conv.4',
conv4_1='conv4.conv.0' , conv4_2='conv4.conv.2', conv4_3='conv4.conv.4',
conv5_1='conv5.conv.0' , conv5_2='conv5.conv.2', conv5_3='conv5.conv.4',)
copy_weights(self.state_dict(), 'caffemodel.%s'%(self.net_arch), src2dsts=src2dsts)
elif pretrained=='torchmodel':
src2dsts= odict([('features.0' ,'conv1.conv.0') , ('features.2' ,'conv1.conv.2'),
('features.5' ,'conv2.conv.0') , ('features.7' ,'conv2.conv.2'),
('features.10','conv3.conv.0') , ('features.12','conv3.conv.2'), ('features.14','conv3.conv.4'),
('features.17','conv4.conv.0') , ('features.19','conv4.conv.2'), ('features.21','conv4.conv.4'),
('features.24','conv5.conv.0') , ('features.26','conv5.conv.2'), ('features.28','conv5.conv.4'),])
copy_weights(self.state_dict(), 'torchmodel.%s'%(self.net_arch), strict=False, src2dsts=src2dsts)
else:
raise NotImplementedError
for name, m in self.named_modules():
if isinstance(m, nn.ConvTranspose2d):
print ('>>>>>>>>>>>', name)
assert m.kernel_size[0] == m.kernel_size[1]
try:
initial_weight = get_upsampling_weight(
m.in_channels, m.out_channels, m.kernel_size[0])
print (m.weight.shape, initial_weight.shape)
m.weight.data.copy_(initial_weight)
except:
print ('pass')
pass
elif isinstance(m, nn.BatchNorm2d): # classname.find('BatchNorm') != -1:
print ('>>>>>>>>>>>', name)
m.weight.data.normal_(1.0, 0.02)
m.bias.data.fill_(0)
return self
def init_weights(self, pretrained='caffemodel'):
""" Two ways to init weights:
1) by copying pretrained weights.
2) by filling empirical weights. (e.g. gaussian, xavier, uniform, constant, bilinear).
"""
if pretrained is None:
print(
'initialize weights by filling (Fc:gaussian, Conv:kaiming_normal).'
)
init_weights_by_filling(self)
elif pretrained == 'caffemodel':
print(
"Initializing weights by copying (pretrained caffe weights).")
src2dsts = get_caffeSrc2Dst(self.net_arch)
copy_weights(self.state_dict(),
'caffemodel.%s' % (self.net_arch),
src2dsts=src2dsts)
elif pretrained == 'torchmodel':
raise NotImplementedError
else:
raise NotImplementedError
return self
def init_weights(self, pretrained='caffemodel'):
""" Two ways to init weights:
1) by copying pretrained weights.
2) by filling empirical weights. (e.g. gaussian, xavier, uniform, constant, bilinear).
"""
# if net_arch=='vgg16':
#fc6='classifier.0', fc7='classifier.3')
if pretrained is None:
print('Initializing weights by filling (with gaussian).')
init_weights_by_filling(self)
elif pretrained == 'caffemodel':
print(
"Initializing weights by copying (pretrained caffe weights).")
src2dsts = odict(
conv1_1='conv1.conv.0',
conv1_2='conv1.conv.2',
conv2_1='conv2.conv.0',
conv2_2='conv2.conv.2',
conv3_1='conv3.conv.0',
conv3_2='conv3.conv.2',
conv3_3='conv3.conv.4',
conv4_1='conv4.conv.0',
conv4_2='conv4.conv.2',
conv4_3='conv4.conv.4',
conv5_1='conv5.conv.0',
conv5_2='conv5.conv.2',
conv5_3='conv5.conv.4',
)
copy_weights(self.state_dict(),
'caffemodel.%s' % (self.net_arch),
src2dsts=src2dsts)
elif pretrained == 'torchmodel':
src2dsts = odict([
map(str.strip, x.split('=')) for x in map(
str.strip,
open(this_dir + '/src2dsts.vgg16_bn.txt').readlines())
if not x.startswith('=')
])
copy_weights(self.state_dict(),
'torchmodel.%s' % (self.net_arch),
strict=False,
src2dsts=src2dsts)
else:
print("[Error] unrecognized pretrained type: ", pretrained)
raise NotImplementedError
for name, m in self.named_modules():
if isinstance(m, nn.ConvTranspose2d):
print('>>>>>>>>>>>',
name) #, m.in_channels, m.out_channels, m.kernel_size[0]
assert m.kernel_size[0] == m.kernel_size[1]
try:
initial_weight = get_upsampling_weight(
m.in_channels, m.out_channels, m.kernel_size[0])
print(m.weight.shape, initial_weight.shape)
m.weight.data.copy_(initial_weight)
except:
print('pass')
pass
elif isinstance(
m, nn.BatchNorm2d): # classname.find('BatchNorm') != -1:
print('>>>>>>>>>>>', name)
m.weight.data.normal_(1.0, 0.02)
m.bias.data.fill_(0)
return self
def init_weights(self):
copy_weights(self.state_dict(), 'torchmodel.alexnet', strict=False)
return self