本文整理汇总了Python中mmcv.cnn.kaiming_init方法的典型用法代码示例。如果您正苦于以下问题：Python cnn.kaiming_init方法的具体用法？Python cnn.kaiming_init怎么用？Python cnn.kaiming_init使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类mmcv.cnn的用法示例。
在下文中一共展示了cnn.kaiming_init方法的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: init_weights
# 需要导入模块: from mmcv import cnn [as 别名]
# 或者: from mmcv.cnn import kaiming_init [as 别名]
def init_weights(self, pretrained=None):
print("init hrnet weights")
# if isinstance(pretrained, str):
# logger = logging.getLogger()
# load_checkpoint(self, pretrained, strict=False, logger=logger)
# elif pretrained is None:
# for m in self.modules():
# if isinstance(m, nn.Conv2d):
# kaiming_init(m)
# elif isinstance(m, (_BatchNorm, nn.GroupNorm)):
# constant_init(m, 1)
# if self.zero_init_residual:
# for m in self.modules():
# if isinstance(m, Bottleneck):
# constant_init(m.norm3, 0)
# elif isinstance(m, BasicBlock):
# constant_init(m.norm2, 0)
# else:
# raise TypeError('pretrained must be a str or None') 示例2: init_weights
# 需要导入模块: from mmcv import cnn [as 别名]
# 或者: from mmcv.cnn import kaiming_init [as 别名]
def init_weights(self):
for m in self.modules():
if hasattr(m, 'kaiming_init') and m.kaiming_init:
kaiming_init(
m,
mode='fan_in',
nonlinearity='leaky_relu',
bias=0,
distribution='uniform',
a=1) 示例3: _make_stage
# 需要导入模块: from mmcv import cnn [as 别名]
# 或者: from mmcv.cnn import kaiming_init [as 别名]
def _make_stage(self, layer_config, in_channels, multiscale_output=True):
num_modules = layer_config['num_modules']
num_branches = layer_config['num_branches']
num_blocks = layer_config['num_blocks']
num_channels = layer_config['num_channels']
block = self.blocks_dict[layer_config['block']]
hr_modules = []
for i in range(num_modules):
# multi_scale_output is only used for the last module
if not multiscale_output and i == num_modules - 1:
reset_multiscale_output = False
else:
reset_multiscale_output = True
hr_modules.append(
HRModule(
num_branches,
block,
num_blocks,
in_channels,
num_channels,
reset_multiscale_output,
with_cp=self.with_cp,
norm_cfg=self.norm_cfg,
conv_cfg=self.conv_cfg))
return nn.Sequential(*hr_modules), in_channels
# def init_weights(self, pretrained=None):
# if isinstance(pretrained, str):
# logger = logging.getLogger()
# load_checkpoint(self, pretrained, strict=False, logger=logger)
# elif pretrained is None:
# for m in self.modules():
# if isinstance(m, nn.Conv2d):
# kaiming_init(m)
# elif isinstance(m, (_BatchNorm, nn.GroupNorm)):
# constant_init(m, 1)
# if self.zero_init_residual:
# for m in self.modules():
# if isinstance(m, Bottleneck):
# constant_init(m.norm3, 0)
# elif isinstance(m, BasicBlock):
# constant_init(m.norm2, 0)
# else:
# raise TypeError('pretrained must be a str or None')