def init_weights(self, pretrained=None):
if isinstance(self.fc, nn.Sequential):
for layer in self.fc:
if not hasattr(layer, 'weight'):
continue
normal_init(layer, std=self.init_std)
else:
normal_init(self.fc, std=self.init_std)
def init_weights(self, pretrained=None):
if isinstance(pretrained, str):
load_checkpoint(self, pretrained, strict=False)
elif pretrained is None:
for m in self.modules():
if isinstance(m, nn.Conv2d):
normal_init(m, std=self.init_gain)
elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
normal_init(m, mean=1, std=self.init_gain)
else:
raise TypeError('pretrained must be a str or None')
def init_weights(self, pretrained=None):
if isinstance(pretrained, str):
load_checkpoint(self, pretrained, strict=False)
elif pretrained is None:
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
normal_init(m, mean=0, std=math.sqrt(2. / n))
elif isinstance(m, nn.BatchNorm2d):
constant_init(m, 1)
else:
raise TypeError('pretrained must be str or None.')
def init_weights(self, pretrained=None):
normal_init(self.rpn_conv)
normal_init(self.rpn_cls)
normal_init(self.rpn_reg)
def init_weights(self, pretrained=None):
normal_init(self.fc, std=self.init_std)
def init_weights(self, pretrained=None):
normal_init(self.conv_seg, mean=0, std=0.01)