Python torch.nn.init.normal() Examples

def define_D(input_nc, ndf, which_model_netD,
             n_layers_D=3, norm='batch', use_sigmoid=False, init_type='normal', gpu_ids=[]):
    netD = None
    use_gpu = len(gpu_ids) > 0
    norm_layer = get_norm_layer(norm_type=norm)

    if use_gpu:
        assert(torch.cuda.is_available())
    if which_model_netD == 'basic':
        netD = NLayerDiscriminator(input_nc, ndf, n_layers=3, norm_layer=norm_layer, use_sigmoid=use_sigmoid, gpu_ids=gpu_ids)
    elif which_model_netD == 'n_layers':
        netD = NLayerDiscriminator(input_nc, ndf, n_layers_D, norm_layer=norm_layer, use_sigmoid=use_sigmoid, gpu_ids=gpu_ids)
    else:
        raise NotImplementedError('Discriminator model name [%s] is not recognized' %
                                  which_model_netD)
    if use_gpu:
        netD.cuda(gpu_ids[0])
    init_weights(netD, init_type=init_type)
    return netD 

def weights_init(init_type='xavier'):
    def init_fun(m):
        classname = m.__class__.__name__
        if (classname.find('Conv') == 0 or classname.find('Linear') == 0) and hasattr(m, 'weight'):
            if init_type == 'normal':
                init.normal(m.weight.data, 0.0, 0.02)
            elif init_type == 'xavier':
                init.xavier_normal(m.weight.data, gain=math.sqrt(2))
            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=math.sqrt(2))
            elif init_type == 'default':
                pass
            else:
                assert 0, "Unsupported initialization: {}".format(init_type)
            if hasattr(m, 'bias') and m.bias is not None:
                init.constant(m.bias.data, 0.0)
        elif (classname.find('Norm') == 0):
            if hasattr(m, 'weight') and m.weight is not None:
                init.constant(m.weight.data, 1.0)
            if hasattr(m, 'bias') and m.bias is not None:
                init.constant(m.bias.data, 0.0)
    return init_fun 

def __init__(self, input_nc, ngf=64, n_layers=3, norm_layer=nn.BatchNorm2d, use_dropout=False):
        super(FeatureExtraction, self).__init__()
        downconv = nn.Conv2d(input_nc, ngf, kernel_size=4, stride=2, padding=1)
        model = [downconv, nn.ReLU(True), norm_layer(ngf)]
        for i in range(n_layers):
            in_ngf = 2**i * ngf if 2**i * ngf < 512 else 512
            out_ngf = 2**(i+1) * ngf if 2**i * ngf < 512 else 512
            downconv = nn.Conv2d(in_ngf, out_ngf, kernel_size=4, stride=2, padding=1)
            model += [downconv, nn.ReLU(True)]
            model += [norm_layer(out_ngf)]
        model += [nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1), nn.ReLU(True)]
        model += [norm_layer(512)]
        model += [nn.Conv2d(512, 512, kernel_size=3, stride=1, padding=1), nn.ReLU(True)]
        
        self.model = nn.Sequential(*model)
        init_weights(self.model, init_type='normal') 

def define_D(input_nc, ndf, which_model_netD,
             n_layers_D=3, norm='batch', use_sigmoid=False, init_type='normal', gpu_ids=[]):
    netD = None
    use_gpu = len(gpu_ids) > 0
    norm_layer = get_norm_layer(norm_type=norm)

    if use_gpu:
        assert(torch.cuda.is_available())
    if which_model_netD == 'basic':
        netD = NLayerDiscriminator(input_nc, ndf, n_layers=3, norm_layer=norm_layer, use_sigmoid=use_sigmoid, gpu_ids=gpu_ids)
    elif which_model_netD == 'n_layers':
        netD = NLayerDiscriminator(input_nc, ndf, n_layers_D, norm_layer=norm_layer, use_sigmoid=use_sigmoid, gpu_ids=gpu_ids)
    elif which_model_netD == 'pixel':
        netD = PixelDiscriminator(input_nc, ndf, norm_layer=norm_layer, use_sigmoid=use_sigmoid, gpu_ids=gpu_ids)
    else:
        raise NotImplementedError('Discriminator model name [%s] is not recognized' %
                                  which_model_netD)
    if use_gpu:
        netD.cuda(gpu_ids[0])
    init_weights(netD, init_type=init_type)
    return netD 

def init_params(net):
    '''Init layer parameters.'''
    for m in net.modules():
        if isinstance(m, nn.Conv2d):
            init.kaiming_normal(m.weight, mode='fan_out')
            if m.bias:
                init.constant(m.bias, 0)
        elif isinstance(m, nn.BatchNorm2d):
            init.constant(m.weight, 1)
            init.constant(m.bias, 0)
        elif isinstance(m, nn.Linear):
            init.normal(m.weight, std=1e-3)
            if m.bias:
                init.constant(m.bias, 0)


#_, term_width = os.popen('stty size', 'r').read().split()
# term_width = int(term_width) 

def define_D(input_nc, ndf, which_model_netD,
             n_layers_D=3, norm='batch', use_sigmoid=False, init_type='normal', gpu_ids=[]):
    netD = None
    use_gpu = len(gpu_ids) > 0
    norm_layer = get_norm_layer(norm_type=norm)

    if use_gpu:
        assert(torch.cuda.is_available())
    if which_model_netD == 'basic':
        netD = NLayerDiscriminator(input_nc, ndf, n_layers=3, norm_layer=norm_layer, use_sigmoid=use_sigmoid, gpu_ids=gpu_ids)
    elif which_model_netD == 'n_layers':
        netD = NLayerDiscriminator(input_nc, ndf, n_layers_D, norm_layer=norm_layer, use_sigmoid=use_sigmoid, gpu_ids=gpu_ids)
    elif which_model_netD == 'pixel':
        netD = PixelDiscriminator(input_nc, ndf, norm_layer=norm_layer, use_sigmoid=use_sigmoid, gpu_ids=gpu_ids)
    else:
        raise NotImplementedError('Discriminator model name [%s] is not recognized' %
                                  which_model_netD)
    if use_gpu:
        netD.cuda(gpu_ids[0])
    init_weights(netD, init_type=init_type)
    return netD 

def reset_parameters(self,
                         init_shared=lambda x: normal(x, std=0.1),
                         init_importance=lambda x: normal(x, std=0.0005)):
        """Resets the trainable parameters."""
        def set_constant_row(parameters, iRow=0, value=0):
            """Return `parameters` with row `iRow` as s constant `value`."""
            data = parameters.data
            data[iRow, :] = value
            return torch.nn.Parameter(data, requires_grad=parameters.requires_grad)

        np.random.seed(self.seed)
        if self.seed is not None:
            torch.manual_seed(self.seed)

        self.shared_embeddings.weight = init_shared(self.shared_embeddings.weight)
        self.importance_weights.weight = init_importance(self.importance_weights.weight)

        if self.padding_idx is not None:
            # Unfortunately has to set weight to 0 even when paddingIdx = 0
            self.shared_embeddings.weight = set_constant_row(self.shared_embeddings.weight)
            self.importance_weights.weight = set_constant_row(self.importance_weights.weight)

        self.shared_embeddings.weight.requires_grad = self.train_sharedEmbed
        self.importance_weights.weight.requires_grad = self.train_weight 

def define_D(input_nc, ndf, which_model_netD,
             n_layers_D=3, norm='batch', use_sigmoid=False, init_type='normal', gpu_ids=[]):
    netD = None
    use_gpu = len(gpu_ids) > 0
    norm_layer = get_norm_layer(norm_type=norm)

    if use_gpu:
        assert(torch.cuda.is_available())
    if which_model_netD == 'basic':
        netD = NLayerDiscriminator(input_nc, ndf, n_layers=3, norm_layer=norm_layer, use_sigmoid=use_sigmoid, gpu_ids=gpu_ids)
    elif which_model_netD == 'n_layers':
        netD = NLayerDiscriminator(input_nc, ndf, n_layers_D, norm_layer=norm_layer, use_sigmoid=use_sigmoid, gpu_ids=gpu_ids)
    else:
        raise NotImplementedError('Discriminator model name [%s] is not recognized' %
                                  which_model_netD)
    if use_gpu:
        netD.cuda(gpu_ids[0])
    init_weights(netD, init_type=init_type)
    return netD 

def __init__(self, dim, dropout=0.2, slope=0.0):
        super(SDAE, self).__init__()
        self.in_dim = dim[0]
        self.nlayers = len(dim)-1
        self.reluslope = slope
        self.enc, self.dec = [], []
        for i in range(self.nlayers):
            self.enc.append(nn.Linear(dim[i], dim[i+1]))
            setattr(self, 'enc_{}'.format(i), self.enc[-1])
            self.dec.append(nn.Linear(dim[i+1], dim[i]))
            setattr(self, 'dec_{}'.format(i), self.dec[-1])
        self.base = []
        for i in range(self.nlayers):
            self.base.append(nn.Sequential(*self.enc[:i]))
        self.dropmodule1 = nn.Dropout(p=dropout)
        self.dropmodule2 = nn.Dropout(p=dropout)
        self.loss = nn.MSELoss(size_average=True)

        # initialization
        for m in self.modules():
            if isinstance(m, nn.Linear):
                init.normal(m.weight, std=1e-2)
                if m.bias.data is not None:
                    init.constant(m.bias, 0) 

def __init__(self, dim, slope=0.0):
        super(extractSDAE, self).__init__()
        self.in_dim = dim[0]
        self.nlayers = len(dim)-1
        self.reluslope = slope
        self.enc, self.dec = [], []
        for i in range(self.nlayers):
            self.enc.append(nn.Linear(dim[i], dim[i+1]))
            setattr(self, 'enc_{}'.format(i), self.enc[-1])
            self.dec.append(nn.Linear(dim[i+1], dim[i]))
            setattr(self, 'dec_{}'.format(i), self.dec[-1])
        self.base = []
        for i in range(self.nlayers):
            self.base.append(nn.Sequential(*self.enc[:i]))

        # initialization
        for m in self.modules():
            if isinstance(m, nn.Linear):
                init.normal(m.weight, std=1e-2)
                if m.bias.data is not None:
                    init.constant(m.bias, 0) 

def define_G(input_nc, output_nc, ngf, which_model_netG, norm='batch', use_dropout=False, init_type='normal', gpu_ids=[]):
    netG = None
    use_gpu = len(gpu_ids) > 0
    norm_layer = get_norm_layer(norm_type=norm)

    if use_gpu:
        assert(torch.cuda.is_available())

    if which_model_netG == 'reflrmnetwork':
        netG = ReflRmNetwork(input_nc, output_nc, ngf, norm_layer=norm_layer, use_dropout=use_dropout, gpu_ids=gpu_ids)
    else:
        raise NotImplementedError('Generator model name [%s] is not recognized' % which_model_netG)
    if len(gpu_ids) > 0:
        netG.cuda(gpu_ids[0])
    init_weights(netG, init_type=init_type)
    return netG 

def reset_params(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                init.kaiming_normal(m.weight, mode='fan_out')
                if m.bias is not None:
                    init.constant(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                init.constant(m.weight, 1)
                init.constant(m.bias, 0)
            elif isinstance(m, nn.Linear):
                init.normal(m.weight, std=0.001)
                if m.bias is not None:
                    init.constant(m.bias, 0) 

def weights_init_kaiming(m):
    classname = m.__class__.__name__
    if classname.find('Conv') != -1:
        init.kaiming_normal(m.weight.data, a=0, mode='fan_in')
    elif classname.find('Linear') != -1:
        init.kaiming_normal(m.weight.data, a=0, mode='fan_in')
    elif classname.find('BatchNorm2d') != -1:
        init.normal(m.weight.data, 1.0, 0.02)
        init.constant(m.bias.data, 0.0) 

def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                init.kaiming_normal(m.weight, mode='fan_out')
                if m.bias is not None:
                    init.constant(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                init.constant(m.weight, 1)
                init.constant(m.bias, 0)
            elif isinstance(m, nn.Linear):
                init.normal(m.weight, std=0.001)
                if m.bias is not None:
                    init.constant(m.bias, 0) 

def weights_init_orthogonal(m):
    classname = m.__class__.__name__
    print(classname)
    if classname.find('Conv') != -1:
        init.orthogonal(m.weight.data, gain=1)
    elif classname.find('Linear') != -1:
        init.orthogonal(m.weight.data, gain=1)
    elif classname.find('BatchNorm2d') != -1:
        init.normal(m.weight.data, 1.0, 0.02)
        init.constant(m.bias.data, 0.0) 

def weights_init_kaiming(m):
    classname = m.__class__.__name__
    # print(classname)
    if classname.find('Conv') != -1:
        init.kaiming_normal(m.weight.data, a=0, mode='fan_in')
    elif classname.find('Linear') != -1:
        init.kaiming_normal(m.weight.data, a=0, mode='fan_in')
    elif classname.find('BatchNorm2d') != -1:
        init.normal(m.weight.data, 1.0, 0.02)
        init.constant(m.bias.data, 0.0) 

def weights_init_xavier(m):
    classname = m.__class__.__name__
    # print(classname)
    if classname.find('Conv') != -1:
        init.xavier_normal(m.weight.data, gain=0.02)
    elif classname.find('Linear') != -1:
        init.xavier_normal(m.weight.data, gain=0.02)
    elif classname.find('BatchNorm2d') != -1:
        init.normal(m.weight.data, 1.0, 0.02)
        init.constant(m.bias.data, 0.0) 

def _initialize_weights(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                init.kaiming_normal(m.weight, mode='fan_out')
                if m.bias is not None:
                    init.constant(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                init.constant(m.weight, 1)
                init.constant(m.bias, 0)
            elif isinstance(m, nn.Linear):
                init.normal(m.weight, std=0.001)
                if m.bias is not None:
                    init.constant(m.bias, 0) 

def reset_params(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                init.kaiming_normal(m.weight, mode='fan_out')
                if m.bias is not None:
                    init.constant(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                init.constant(m.weight, 1)
                init.constant(m.bias, 0)
            elif isinstance(m, nn.Linear):
                init.normal(m.weight, std=0.001)
                if m.bias is not None:
                    init.constant(m.bias, 0) 

def init_params(net):
    '''Init layer parameters.'''
    for m in net.modules():
        if isinstance(m, nn.Conv2d):
            init.kaiming_normal(m.weight, mode='fan_out')
            if m.bias:
                init.constant(m.bias, 0)
        elif isinstance(m, nn.BatchNorm2d):
            init.constant(m.weight, 1)
            init.constant(m.bias, 0)
        elif isinstance(m, nn.Linear):
            init.normal(m.weight, std=1e-3)
            if m.bias:
                init.constant(m.bias, 0) 

def init_params(net):
    '''Init layer parameters.'''
    for m in net.modules():
        if isinstance(m, nn.Conv2d):
            init.kaiming_normal(m.weight, mode='fan_out')
            if m.bias:
                init.constant(m.bias, 0)
        elif isinstance(m, nn.BatchNorm2d):
            init.constant(m.weight, 1)
            init.constant(m.bias, 0)
        elif isinstance(m, nn.Linear):
            init.normal(m.weight, std=1e-3)
            if m.bias:
                init.constant(m.bias, 0) 

def init_params(net):
    '''Init layer parameters.'''
    for m in net.modules():
        if isinstance(m, nn.Conv2d):
            init.kaiming_normal(m.weight, mode='fan_out')
            if m.bias:
                init.constant(m.bias, 0)
        elif isinstance(m, nn.BatchNorm2d):
            init.constant(m.weight, 1)
            init.constant(m.bias, 0)
        elif isinstance(m, nn.Linear):
            init.normal(m.weight, std=1e-3)
            if m.bias:
                init.constant(m.bias, 0) 

def init_params(net):
    '''Init layer parameters.'''
    for m in net.modules():
        if isinstance(m, nn.Conv2d):
            init.kaiming_normal(m.weight, mode='fan_out')
            if m.bias:
                init.constant(m.bias, 0)
        elif isinstance(m, nn.BatchNorm2d):
            init.constant(m.weight, 1)
            init.constant(m.bias, 0)
        elif isinstance(m, nn.Linear):
            init.normal(m.weight, std=1e-3)
            if m.bias:
                init.constant(m.bias, 0) 

def init_params(net):
    '''Init layer parameters.'''
    for m in net.modules():
        if isinstance(m, nn.Conv2d):
            init.kaiming_normal(m.weight, mode='fan_out')
            if m.bias:
                init.constant(m.bias, 0)
        elif isinstance(m, nn.BatchNorm2d):
            init.constant(m.weight, 1)
            init.constant(m.bias, 0)
        elif isinstance(m, nn.Linear):
            init.normal(m.weight, std=1e-3)
            if m.bias:
                init.constant(m.bias, 0) 

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) 

def init_params(net):
    '''Init layer parameters.'''
    for m in net.modules():
        if isinstance(m, nn.Conv2d):
            init.kaiming_normal(m.weight, mode='fan_out')
            if m.bias:
                init.constant(m.bias, 0)
        elif isinstance(m, nn.BatchNorm2d):
            init.constant(m.weight, 1)
            init.constant(m.bias, 0)
        elif isinstance(m, nn.Linear):
            init.normal(m.weight, std=1e-3)
            if m.bias:
                init.constant(m.bias, 0) 

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) 

def weights_normal_init(model, dev=0.01):
    if isinstance(model, list):
        for m in model:
            weights_normal_init(m, dev)
    else:
        for m in model.modules():
            if isinstance(m, nn.Conv2d):
                m.weight.data.normal_(0.0, dev)
                if m.bias is not None:
                    m.bias.data.fill_(0.0)

            elif isinstance(m, nn.LSTM):
                for weight_set in m._all_weights:
                    for param in weight_set:
                        if 'weight' in param:
                            m.__getattr__(param).data.normal_(0.0, dev)
                        if 'bias' in param:
                            m.__getattr__(param).data.fill_(0.0)

            elif isinstance(m, _Conv2d_dilated):
                m.weight.data.copy_(m.weight.data.normal_(0.0, dev))
                if m.bias is not None:
                    m.bias.data.fill_(0.0)

            elif isinstance(m, nn.Linear):
                m.weight.data.normal_(0.0, dev)
            elif isinstance(m, nn.BatchNorm2d):
                init.normal(m.weight.data, 1.0, 0.02)
                init.constant(m.bias.data, 0.0) 

def init_params(net):
    '''Init layer parameters.'''
    for m in net.modules():
        if isinstance(m, nn.Conv2d):
            init.kaiming_normal(m.weight, mode='fan_out')
            if m.bias:
                init.constant(m.bias, 0)
        elif isinstance(m, nn.BatchNorm2d):
            init.constant(m.weight, 1)
            init.constant(m.bias, 0)
        elif isinstance(m, nn.Linear):
            init.normal(m.weight, std=1e-3)
            if m.bias:
                init.constant(m.bias, 0) 

def initialize_weights(method='kaiming', *models):
    for model in models:
        for module in model.modules():

            if isinstance(module, nn.Conv2d) or isinstance(module, nn.ConvTranspose2d) or isinstance(module, nn.Linear):
                if method == 'kaiming':
                    init.kaiming_normal(module.weight.data, np.sqrt(2.0))
                elif method == 'xavier':
                    init.xavier_normal(module.weight.data, np.sqrt(2.0))
                elif method == 'orthogonal':
                    init.orthogonal(module.weight.data, np.sqrt(2.0))
                elif method == 'normal':
                    init.normal(module.weight.data,mean=0, std=0.02)
                if module.bias is not None:
                    init.constant(module.bias.data,0)