当前位置: 首页>>代码示例>>Python>>正文


Python init.orthogonal_方法代码示例

本文整理汇总了Python中torch.nn.init.orthogonal_方法的典型用法代码示例。如果您正苦于以下问题:Python init.orthogonal_方法的具体用法?Python init.orthogonal_怎么用?Python init.orthogonal_使用的例子?那么, 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torch.nn.init的用法示例。


在下文中一共展示了init.orthogonal_方法的15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 torch.nn import init [as 别名]
# 或者: from torch.nn.init import orthogonal_ [as 别名]
def init_weights(net, init_type, init_gain):
    def init_func(m):
        classname = m.__class__.__name__
        if hasattr(m, 'weight') and (classname.find('Conv') != -1 or classname.find('Linear') != -1):
            if init_type == 'normal':
                init.normal_(m.weight.data, 0.0, init_gain)
            elif init_type == 'xavier':
                init.xavier_normal_(m.weight.data, gain=init_gain)
            elif init_type == 'kaiming':
                init.kaiming_normal_(m.weight.data, a=0, mode='fan_in')
            elif init_type == 'orthogonal':
                init.orthogonal_(m.weight.data, gain=init_gain)
            else:
                raise NotImplementedError('initialization method [%s] is not implemented' % init_type)
        elif classname.find('BatchNorm2d') != -1:
            init.normal_(m.weight.data, 1.0, init_gain)
            init.constant_(m.bias.data, 0.0)
    net.apply(init_func) 
开发者ID:ranahanocka,项目名称:MeshCNN,代码行数:20,代码来源:networks.py

示例2: weights_init

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import orthogonal_ [as 别名]
def weights_init(m):
    '''
    Code from https://gist.github.com/jeasinema/ed9236ce743c8efaf30fa2ff732749f5
    Usage:
        model = Model()
        model.apply(weight_init)
    '''
    if isinstance(m, nn.Linear):
        init.xavier_normal_(m.weight.data)
        init.normal_(m.bias.data)
    elif isinstance(m, nn.GRUCell):
        for param in m.parameters():
            if len(param.shape) >= 2:
                init.orthogonal_(param.data)
            else:
                init.normal_(param.data) 
开发者ID:dmlc,项目名称:dgl,代码行数:18,代码来源:utils.py

示例3: init_weights

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import orthogonal_ [as 别名]
def init_weights(net, init_type='normal', gain=0.02):
    def init_func(m):
        # this will apply to each layer
        classname = m.__class__.__name__
        if hasattr(m, 'weight') and (classname.find('conv')!=-1 or classname.find('Linear')!=-1):
            if init_type=='normal':
                init.normal_(m.weight.data, 0.0, gain)
            elif init_type == 'xavier':
                init.xavier_normal_(m.weight.data, gain=gain)
            elif init_type == 'kaiming':
                init.kaiming_normal_(m.weight.data, a=0, mode='fan_in')#good for relu
            elif init_type == 'orthogonal':
                init.orthogonal_(m.weight.data, gain=gain)
            else:
                raise NotImplementedError('initialization method [%s] is not implemented' % init_type)
            
            if hasattr(m, 'bias') and m.bias is not None:
                init.constant_(m.bias.data, 0.0)
        elif classname.find('BatchNorm2d') != -1:
            init.normal_(m.weight.data, 1.0, gain)
            init.constant_(m.bias.data, 0.0)
    #print('initialize network with %s' % init_type)
    net.apply(init_func) 
开发者ID:songdejia,项目名称:Siamese-RPN-pytorch,代码行数:25,代码来源:train_siamrpn.py

示例4: init_weights

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import orthogonal_ [as 别名]
def init_weights(net, init_type='normal', gain=0.02):
    def init_func(m):
        classname = m.__class__.__name__
        if hasattr(m, 'weight') and (classname.find('Conv') != -1 or classname.find('Linear') != -1):
            if init_type == 'normal':
                init.normal_(m.weight.data, 0.0, gain)
            elif init_type == 'xavier':
                init.xavier_normal_(m.weight.data, gain=gain)
            elif init_type == 'kaiming':
                init.kaiming_normal_(m.weight.data, a=0, mode='fan_in')
            elif init_type == 'orthogonal':
                init.orthogonal_(m.weight.data, gain=gain)
            else:
                raise NotImplementedError('initialization method [%s] is not implemented' % init_type)
            if hasattr(m, 'bias') and m.bias is not None:
                init.constant_(m.bias.data, 0.0)
        elif classname.find('BatchNorm2d') != -1:
            init.normal_(m.weight.data, 1.0, gain)
            init.constant_(m.bias.data, 0.0)

    print('initialize network with %s' % init_type)
    net.apply(init_func) 
开发者ID:Lotayou,项目名称:densebody_pytorch,代码行数:24,代码来源:networks.py

示例5: init_weights

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import orthogonal_ [as 别名]
def init_weights(self):
    self.param_count = 0
    for module in self.modules():
      if (isinstance(module, nn.Conv2d) 
          or isinstance(module, nn.Linear) 
          or isinstance(module, nn.Embedding)):
        if self.init == 'ortho':
          init.orthogonal_(module.weight)
        elif self.init == 'N02':
          init.normal_(module.weight, 0, 0.02)
        elif self.init in ['glorot', 'xavier']:
          init.xavier_uniform_(module.weight)
        else:
          print('Init style not recognized...')
        self.param_count += sum([p.data.nelement() for p in module.parameters()])
    print('Param count for G''s initialized parameters: %d' % self.param_count)

  # Note on this forward function: we pass in a y vector which has
  # already been passed through G.shared to enable easy class-wise
  # interpolation later. If we passed in the one-hot and then ran it through
  # G.shared in this forward function, it would be harder to handle.
  # NOTE: The z vs y dichotomy here is for compatibility with not-y 
开发者ID:ajbrock,项目名称:BigGAN-PyTorch,代码行数:24,代码来源:BigGANdeep.py

示例6: init_weights

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import orthogonal_ [as 别名]
def init_weights(self):
    self.param_count = 0
    for module in self.modules():
      if (isinstance(module, nn.Conv2d) 
          or isinstance(module, nn.Linear) 
          or isinstance(module, nn.Embedding)):
        if self.init == 'ortho':
          init.orthogonal_(module.weight)
        elif self.init == 'N02':
          init.normal_(module.weight, 0, 0.02)
        elif self.init in ['glorot', 'xavier']:
          init.xavier_uniform_(module.weight)
        else:
          print('Init style not recognized...')
        self.param_count += sum([p.data.nelement() for p in module.parameters()])
    print('Param count for G''s initialized parameters: %d' % self.param_count)

  # Note on this forward function: we pass in a y vector which has
  # already been passed through G.shared to enable easy class-wise
  # interpolation later. If we passed in the one-hot and then ran it through
  # G.shared in this forward function, it would be harder to handle. 
开发者ID:ajbrock,项目名称:BigGAN-PyTorch,代码行数:23,代码来源:BigGAN.py

示例7: init_weights

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import orthogonal_ [as 别名]
def init_weights(net, init_type='normal', gain=0.02):
	def init_func(m):
		classname = m.__class__.__name__
		if hasattr(m, 'weight') and (classname.find('Conv') != -1 or classname.find('Linear') != -1):
			if init_type == 'normal':
				init.normal_(m.weight.data, 0.0, gain)
			elif init_type == 'xavier':
				init.xavier_normal_(m.weight.data, gain=gain)
			elif init_type == 'kaiming':
				init.kaiming_normal_(m.weight.data, a=0, mode='fan_in')
			elif init_type == 'orthogonal':
				init.orthogonal_(m.weight.data, gain=gain)
			else:
				raise NotImplementedError('initialization method [%s] is not implemented' % init_type)
			if hasattr(m, 'bias') and m.bias is not None:
				init.constant_(m.bias.data, 0.0)
		elif classname.find('BatchNorm2d') != -1:
			init.normal_(m.weight.data, 1.0, gain)
			init.constant_(m.bias.data, 0.0)
	
	print('initialize network with %s' % init_type)
	net.apply(init_func) 
开发者ID:Luodian,项目名称:MADAN,代码行数:24,代码来源:networks.py

示例8: reset_parameters

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import orthogonal_ [as 别名]
def reset_parameters(self):
        """
        Initialize parameters following the way proposed in the paper.
        """
        init.orthogonal_(self.weight_ih.data)
        init.orthogonal_(self.alpha_weight_ih.data)

        weight_hh_data = torch.eye(self.hidden_size)
        weight_hh_data = weight_hh_data.repeat(1, 3)
        self.weight_hh.data.set_(weight_hh_data)

        alpha_weight_hh_data = torch.eye(self.hidden_size)
        alpha_weight_hh_data = alpha_weight_hh_data.repeat(1, 1)
        self.alpha_weight_hh.data.set_(alpha_weight_hh_data)

        # The bias is just set to zero vectors.
        if self.use_bias:
            init.constant_(self.bias.data, val=0)
            init.constant_(self.alpha_bias.data, val=0) 
开发者ID:thunlp,项目名称:Chinese_NRE,代码行数:21,代码来源:mglattice.py

示例9: init_weights

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import orthogonal_ [as 别名]
def init_weights(net, init_type='normal', init_gain=0.02):
    def init_func(m):
        name = m.__class__.__name__
        if hasattr(m, 'weight') and ('Conv' in name or 'Linear' in name):
            if init_type == 'normal':
                init.normal_(m.weight.data, 0.0, init_gain)
            elif init_type == 'xavier':
                init.xavier_normal_(m.weight.data, gain=init_gain)
            elif init_type == 'kaiming':
                init.kaiming_normal_(m.weight.data, a=0, mode='fan_in')
            elif init_type == 'orthogonal':
                init.orthogonal_(m.weight.data, gain=init_gain)
            else:
                raise NotImplementedError(
                    f'initialization method [{init_type}] is not implemented')
            if hasattr(m, 'bias') and m.bias is not None:
                init.constant_(m.bias.data, 0.0)
        elif 'BatchNorm2d' in name:
            init.normal_(m.weight.data, 1.0, init_gain)
            init.constant_(m.bias.data, 0.0)

    net.apply(init_func) 
开发者ID:S-aiueo32,项目名称:srntt-pytorch,代码行数:24,代码来源:__init__.py

示例10: init_weights_multi

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import orthogonal_ [as 别名]
def init_weights_multi(m, init_type, gain=1.):
    classname = m.__class__.__name__
    if hasattr(m, 'weight') and (classname.find('Conv') != -1 or classname.find('Linear') != -1):
        if init_type == 'normal':
            init.normal_(m.weight.data, 0.0, gain)
        elif init_type == 'xavier':
            init.xavier_normal_(m.weight.data, gain=gain)
        elif init_type == 'kaiming':
            init.kaiming_normal_(m.weight.data, a=0, mode='fan_in')
        elif init_type == 'orthogonal':
            init.orthogonal_(m.weight.data, gain=gain)
        else:
            raise NotImplementedError('initialization method [%s] is not implemented' % init_type)
        if hasattr(m, 'bias') and m.bias is not None:
            init.constant_(m.bias.data, 0.0)
    elif classname.find('BatchNorm') != -1:
        init.normal_(m.weight.data, 1.0, gain)
        init.constant_(m.bias.data, 0.0)


# ---------------- Pretty sure the following functions/classes are common ---------------- 
开发者ID:laoreja,项目名称:HPLFlowNet,代码行数:23,代码来源:main_utils.py

示例11: init_weights

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import orthogonal_ [as 别名]
def init_weights(net, init_type='normal', gain=0.02):
    def init_func(m):
        # this will apply to each layer
        classname = m.__class__.__name__
        if hasattr(m, 'weight') and (classname.find('conv')!=-1 or classname.find('Linear')!=-1):
            if init_type=='normal':
                init.normal_(m.weight.data, 0.0, gain)
            elif init_type == 'xavier':
                init.xavier_normal_(m.weight.data, gain=gain)
            elif init_type == 'kaiming':
                init.kaiming_normal_(m.weight.data, a=0, mode='fan_in')#good for relu
            elif init_type == 'orthogonal':
                init.orthogonal_(m.weight.data, gain=gain)
            else:
                raise NotImplementedError('initialization method [%s] is not implemented' % init_type)
            
            if hasattr(m, 'bias') and m.bias is not None:
                init.constant_(m.bias.data, 0.0)
        elif classname.find('BatchNorm2d') != -1:
            init.normal_(m.weight.data, 1.0, gain)
            init.constant_(m.bias.data, 0.0)
    print("EAST <==> Prepare <==> Init Network'{}' <==> Begin".format(init_type))

    net.apply(init_func) 
开发者ID:songdejia,项目名称:EAST,代码行数:26,代码来源:init.py

示例12: init_weights

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import orthogonal_ [as 别名]
def init_weights(net, init_type='xavier', gain=0.02):
    def init_func(m):
        classname = m.__class__.__name__
        if hasattr(m, 'weight') and (classname.find('Conv') != -1 or classname.find('Linear') != -1):
            if init_type == 'normal':
                init.normal_(m.weight.data, 0.0, gain)
            elif init_type == 'xavier':
                init.xavier_normal_(m.weight.data, gain=gain)
            elif init_type == 'kaiming':
                init.kaiming_normal_(m.weight.data, a=0, mode='fan_in')
            elif init_type == 'orthogonal':
                init.orthogonal_(m.weight.data, gain=gain)
            else:
                raise NotImplementedError('initialization method [%s] is not implemented' % init_type)
            if hasattr(m, 'bias') and m.bias is not None:
                init.constant_(m.bias.data, 0.0)
        elif classname.find('BatchNorm2d') != -1:
            init.normal_(m.weight.data, 1.0, gain)
            init.constant_(m.bias.data, 0.0)

    print('initialize network with %s' % init_type)
    net.apply(init_func) 
开发者ID:richzhang,项目名称:colorization-pytorch,代码行数:24,代码来源:networks.py

示例13: reset_parameters

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import orthogonal_ [as 别名]
def reset_parameters(self):
        if self.use_leaf_rnn:
            init.kaiming_normal_(self.leaf_rnn_cell.weight_ih.data)
            init.orthogonal_(self.leaf_rnn_cell.weight_hh.data)
            init.constant_(self.leaf_rnn_cell.bias_ih.data, val=0)
            init.constant_(self.leaf_rnn_cell.bias_hh.data, val=0)
            # Set forget bias to 1
            self.leaf_rnn_cell.bias_ih.data.chunk(4)[1].fill_(1)
            if self.bidirectional:
                init.kaiming_normal_(self.leaf_rnn_cell_bw.weight_ih.data)
                init.orthogonal_(self.leaf_rnn_cell_bw.weight_hh.data)
                init.constant_(self.leaf_rnn_cell_bw.bias_ih.data, val=0)
                init.constant_(self.leaf_rnn_cell_bw.bias_hh.data, val=0)
                # Set forget bias to 1
                self.leaf_rnn_cell_bw.bias_ih.data.chunk(4)[1].fill_(1)
        else:
            init.kaiming_normal_(self.word_linear.weight.data)
            init.constant_(self.word_linear.bias.data, val=0)
        self.treelstm_layer.reset_parameters()
        init.normal_(self.comp_query.data, mean=0, std=0.01) 
开发者ID:BangLiu,项目名称:QANet-PyTorch,代码行数:22,代码来源:treelstm.py

示例14: init_weights

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import orthogonal_ [as 别名]
def init_weights(net, init_type='normal', gain=0.02):
    def init_func(m):
        # this will apply to each layer
        classname = m.__class__.__name__
        if hasattr(m, 'weight') and (classname.find('conv')!=-1 or classname.find('Linear')!=-1):
            if init_type=='normal':
                init.normal_(m.weight.data, 0.0, gain)
            elif init_type == 'xavier':
                init.xavier_normal_(m.weight.data, gain=gain)
            elif init_type == 'kaiming':
                init.kaiming_normal_(m.weight.data, a=0, mode='fan_in')#good for relu
            elif init_type == 'orthogonal':
                init.orthogonal_(m.weight.data, gain=gain)
            else:
                raise NotImplementedError('initialization method [%s] is not implemented' % init_type)
            
            if hasattr(m, 'bias') and m.bias is not None:
                init.constant_(m.bias.data, 0.0)
        elif classname.find('BatchNorm2d') != -1:
            init.normal_(m.weight.data, 1.0, gain)
            init.constant_(m.bias.data, 0.0)
    #print('initialize network with %s' % init_type)
    net.apply(init_func)


############################################
# save checkpoint and resume
############################################ 
开发者ID:songdejia,项目名称:DeepLab_v3_plus,代码行数:30,代码来源:util.py

示例15: init_weights

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import orthogonal_ [as 别名]
def init_weights(net, init_type='normal', init_gain=0.02):
    """Initialize network weights.

    Parameters:
        net (network)   -- network to be initialized
        init_type (str) -- the name of an initialization method: normal | xavier | kaiming | orthogonal
        init_gain (float)    -- scaling factor for normal, xavier and orthogonal.

    We use 'normal' in the original pix2pix and CycleGAN paper. But xavier and kaiming might
    work better for some applications. Feel free to try yourself.
    """
    def init_func(m):  # define the initialization function
        classname = m.__class__.__name__
        if hasattr(m, 'weight') and (classname.find('Conv') != -1 or classname.find('Linear') != -1):
            if init_type == 'normal':
                init.normal_(m.weight.data, 0.0, init_gain)
            elif init_type == 'xavier':
                init.xavier_normal_(m.weight.data, gain=init_gain)
            elif init_type == 'kaiming':
                init.kaiming_normal_(m.weight.data, a=0, mode='fan_in')
            elif init_type == 'orthogonal':
                init.orthogonal_(m.weight.data, gain=init_gain)
            else:
                raise NotImplementedError('initialization method [%s] is not implemented' % init_type)
            if hasattr(m, 'bias') and m.bias is not None:
                init.constant_(m.bias.data, 0.0)
        elif classname.find('BatchNorm2d') != -1:  # BatchNorm Layer's weight is not a matrix; only normal distribution applies.
            init.normal_(m.weight.data, 1.0, init_gain)
            init.constant_(m.bias.data, 0.0)

    print('initialize network with %s' % init_type)
    net.apply(init_func)  # apply the initialization function <init_func> 
开发者ID:Mingtzge,项目名称:2019-CCF-BDCI-OCR-MCZJ-OCR-IdentificationIDElement,代码行数:34,代码来源:networks.py


注:本文中的torch.nn.init.orthogonal_方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。