Python init.uniform_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 uniform_ [as 别名]
def __init__(self, features, orthogonal_initialization=True, using_cache=False):
        """Constructor.

        Args:
            features: int, number of input features.
            orthogonal_initialization: bool, if True initialize weights to be a random
                orthogonal matrix.

        Raises:
            TypeError: if `features` is not a positive integer.
        """
        super().__init__(features, using_cache)

        if orthogonal_initialization:
            self._weight = nn.Parameter(utils.random_orthogonal(features))
        else:
            self._weight = nn.Parameter(torch.empty(features, features))
            stdv = 1.0 / np.sqrt(features)
            init.uniform_(self._weight, -stdv, stdv) 

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import uniform_ [as 别名]
def assert_and_infer_cfg(make_immutable=True):
    """Call this function in your script after you have finished setting all cfg
    values that are necessary (e.g., merging a config from a file, merging
    command line config options, etc.). By default, this function will also
    mark the global cfg as immutable to prevent changing the global cfg settings
    during script execution (which can lead to hard to debug errors or code
    that's harder to understand than is necessary).
    """
    if __C.MODEL.LOAD_IMAGENET_PRETRAINED_WEIGHTS:
        assert __C.VGG.IMAGENET_PRETRAINED_WEIGHTS, \
            "Path to the weight file must not be empty to load imagenet pertrained resnets."
    if version.parse(torch.__version__) < version.parse('0.4.0'):
        __C.PYTORCH_VERSION_LESS_THAN_040 = True
        # create alias for PyTorch version less than 0.4.0
        init.uniform_ = init.uniform
        init.normal_ = init.normal
        init.constant_ = init.constant
        nn.GroupNorm = mynn.GroupNorm
    if make_immutable:
        cfg.immutable(True) 

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import uniform_ [as 别名]
def __init__(self,
                 features,
                 context_features,
                 activation=F.relu,
                 dropout_probability=0.,
                 use_batch_norm=False,
                 zero_initialization=True):
        super().__init__()
        self.activation = activation

        self.use_batch_norm = use_batch_norm
        if use_batch_norm:
            self.batch_norm_layers = nn.ModuleList([
                nn.BatchNorm1d(features, eps=1e-3)
                for _ in range(2)
            ])
        if context_features is not None:
            self.context_layer = nn.Linear(context_features, features)
        self.linear_layers = nn.ModuleList([
            nn.Linear(features, features)
            for _ in range(2)
        ])
        self.dropout = nn.Dropout(p=dropout_probability)
        if zero_initialization:
            init.uniform_(self.linear_layers[-1].weight, -1e-3, 1e-3)
            init.uniform_(self.linear_layers[-1].bias, -1e-3, 1e-3) 

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import uniform_ [as 别名]
def _initialize(self, identity_init):
        init.zeros_(self.bias)

        if identity_init:
            init.zeros_(self.lower_entries)
            init.zeros_(self.upper_entries)
            constant = np.log(np.exp(1 - self.eps) - 1)
            init.constant_(self.unconstrained_upper_diag, constant)
        else:
            stdv = 1.0 / np.sqrt(self.features)
            init.uniform_(self.lower_entries, -stdv, stdv)
            init.uniform_(self.upper_entries, -stdv, stdv)
            init.uniform_(self.unconstrained_upper_diag, -stdv, stdv) 

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import uniform_ [as 别名]
def _initialize(self):
        stdv = 1.0 / np.sqrt(self.features)
        init.uniform_(self.upper_entries, -stdv, stdv)
        init.uniform_(self.log_upper_diag, -stdv, stdv)
        init.constant_(self.bias, 0.0) 

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import uniform_ [as 别名]
def _initialize(self):
        stdv = 1.0 / np.sqrt(self.features)
        init.uniform_(self.log_diagonal, -stdv, stdv)
        init.constant_(self.bias, 0.0) 

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import uniform_ [as 别名]
def reset_parameters(self):
        stdv = 1.0 / math.sqrt(self.hidden_size)
        for weight in self.parameters():
            init.uniform_(weight, -stdv, stdv) 

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import uniform_ [as 别名]
def reset_parameters(self):
        init.kaiming_uniform_(self.weight, a=math.sqrt(5))
        if self.bias is not None:
            fan_in, _ = init._calculate_fan_in_and_fan_out(self.weight)
            bound = 1 / math.sqrt(fan_in)
            init.uniform_(self.bias, -bound, bound) 

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import uniform_ [as 别名]
def reset_parameters(self, zero_init=False):
        init.kaiming_uniform_(self.weight, a=math.sqrt(5))
        if zero_init:
            # normalize cannot handle zero weight in some cases.
            self.weight.data.div_(1000)
        if self.bias is not None:
            fan_in, _ = init._calculate_fan_in_and_fan_out(self.weight)
            bound = 1 / math.sqrt(fan_in)
            init.uniform_(self.bias, -bound, bound) 

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import uniform_ [as 别名]
def reset_parameters(self):
        n = self.in_channels
        init.kaiming_uniform_(self.weight, a=math.sqrt(5))
        if self.bias is not None:
            fan_in, _ = init._calculate_fan_in_and_fan_out(self.weight)
            bound = 1 / math.sqrt(fan_in)
            init.uniform_(self.bias, -bound, bound) 

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import uniform_ [as 别名]
def __init__(self, emb_size, emb_dimension):
        super(SkipGramModel, self).__init__()
        self.emb_size = emb_size
        self.emb_dimension = emb_dimension
        self.u_embeddings = nn.Embedding(emb_size, emb_dimension, sparse=True)
        self.v_embeddings = nn.Embedding(emb_size, emb_dimension, sparse=True)

        initrange = 1.0 / self.emb_dimension
        init.uniform_(self.u_embeddings.weight.data, -initrange, initrange)
        init.constant_(self.v_embeddings.weight.data, 0) 

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import uniform_ [as 别名]
def init(self, emb_init):
        """Initializing the embeddings.

        Parameters
        ----------
        emb_init : float
            The intial embedding range should be [-emb_init, emb_init].
        """
        INIT.uniform_(self.emb, -emb_init, emb_init)
        INIT.zeros_(self.state_sum) 

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import uniform_ [as 别名]
def reset_parameters(self):
        """
        This method initializes or reset all the parameters of the cell.
        The paramaters are initiated following a uniform distribution.
        """
        std = 1.0 / np.sqrt(self.hidden_size)
        for w in self.parameters():
            init.uniform_(w, -std, std) 

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import uniform_ [as 别名]
def XavierFill(tensor):
    """Caffe2 XavierFill Implementation"""
    size = reduce(operator.mul, tensor.shape, 1)
    fan_in = size / tensor.shape[0]
    scale = math.sqrt(3 / fan_in)
    return init.uniform_(tensor, -scale, scale) 

# 需要导入模块: from torch.nn import init [as 别名]
# 或者: from torch.nn.init import uniform_ [as 别名]
def assert_and_infer_cfg(make_immutable=True):
    """Call this function in your script after you have finished setting all cfg
    values that are necessary (e.g., merging a config from a file, merging
    command line config options, etc.). By default, this function will also
    mark the global cfg as immutable to prevent changing the global cfg settings
    during script execution (which can lead to hard to debug errors or code
    that's harder to understand than is necessary).
    """
    if __C.MODEL.RPN_ONLY or __C.MODEL.FASTER_RCNN:
        __C.RPN.RPN_ON = True
    if __C.RPN.RPN_ON or __C.RETINANET.RETINANET_ON:
        __C.TEST.PRECOMPUTED_PROPOSALS = False
    if __C.MODEL.LOAD_IMAGENET_PRETRAINED_WEIGHTS:
        assert __C.RESNETS.IMAGENET_PRETRAINED_WEIGHTS, \
            "Path to the weight file must not be empty to load imagenet pertrained resnets."
    if set([__C.MRCNN.ROI_MASK_HEAD, __C.KRCNN.ROI_KEYPOINTS_HEAD]) & _SHARE_RES5_HEADS:
        __C.MODEL.SHARE_RES5 = True
    if version.parse(torch.__version__) < version.parse('0.4.0'):
        __C.PYTORCH_VERSION_LESS_THAN_040 = True
        # create alias for PyTorch version less than 0.4.0
        init.uniform_ = init.uniform
        init.normal_ = init.normal
        init.constant_ = init.constant
        nn.GroupNorm = mynn.GroupNorm
    if make_immutable:
        cfg.immutable(True)