Python init.orthogonal_方法代码示例

# 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) 

# 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) 

# 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) 

# 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) 

# 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 

# 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. 

# 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) 

# 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) 

# 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) 

# 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 ---------------- 

# 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) 

# 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) 

# 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) 

# 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
############################################ 

# 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>