tf.identity()与tf.group()

本文介绍了TensorFlow中tf.identity()和tf.group()的作用及用法。通过具体代码示例展示了如何利用这两个函数将简单的赋值操作转换为依赖操作,这对于控制依赖关系和构建计算图至关重要。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

                                tf.identity()与tf.group()

1. tf.identity():

import tensorflow as tf
x = tf.Variable(0.0)
x_plus = tf.assign_add(x, 1)
with tf.control_dependencies([x_plus]):#只有当内部为操作时以来才会生效
    y = tf.identity(x)#将该语句变为操作
init = tf.global_variables_initializer()
with tf.Session() as session:
    init.run()
    for i in range(5):
        print(y.eval())
    print(x.eval())#5

2.tf.group():

import tensorflow as tf
x = tf.Variable(0.0)
x_plus = tf.assign_add(x, 1)
with tf.control_dependencies([x_plus]):#只有当内部为操作时以来才会生效
    #y = tf.identity(x)#将该语句变为操作
    y = x
    update = tf.group(y)#将该语句变为操作
init = tf.global_variables_initializer()
with tf.Session() as session:
    init.run()
    for i in range(5):
        session.run(update)
        print(y.eval())
    print(x.eval())#5
总结:tf.identity()和tf.group()均可将语句变为操作




class Conv(nn.Module): """Standard convolution with args(ch_in, ch_out, kernel, stride, padding, groups, dilation, activation).""" default_act = nn.SiLU() # default activation def __init__(self, c1, c2, k=1, s=1, p=None, g=1, d=1, act=True): """Initialize Conv layer with given arguments including activation.""" super().__init__() self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p, d), groups=g, dilation=d, bias=False) self.bn = nn.BatchNorm2d(c2) self.act = self.default_act if act is True else act if isinstance(act, nn.Module) else nn.Identity() def forward(self, x): """Apply convolution, batch normalization and activation to input tensor.""" return self.act(self.bn(self.conv(x))) def forward_fuse(self, x): """Perform transposed convolution of 2D data.""" return self.act(self.conv(x)) def gcd(a, b): while b: a, b = b, a % b return a # Other types of layers can go here (e.g., nn.Linear, etc.) def _init_weights(module, name, scheme=''): if isinstance(module, nn.Conv2d) or isinstance(module, nn.Conv3d): if scheme == 'normal': nn.init.normal_(module.weight, std=.02) if module.bias is not None: nn.init.zeros_(module.bias) elif scheme == 'trunc_normal': trunc_normal_tf_(module.weight, std=.02) if module.bias is not None: nn.init.zeros_(module.bias) elif scheme == 'xavier_normal': nn.init.xavier_normal_(module.weight) if module.bias is not None: nn.init.zeros_(module.bias) elif scheme == 'kaiming_normal': nn.init.kaiming_normal_(module.weight, mode='fan_out', nonlinearity='relu') if module.bias is not None: nn.init.zeros_(module.bias) else: # efficientnet like fan_out = module.kernel_size[0] * module.kernel_size[1] * module.out_channels fan_out //= module.groups nn.init.normal_(module.weight, 0, math.sqrt(2.0 / fan_out)) if module.bias is not None: nn.init.zeros_(module.bias) elif isinstance(module, nn.BatchNorm2d) or isinstance(module, nn.BatchNorm3d): nn.init.constant_(module.weight, 1) nn.init.constant_(module.bias, 0) elif isinstance(module, nn.LayerNorm): nn.init.constant_(module.weight, 1) nn.init.constant_(module.bias, 0) def act_layer(act, inplace=False, neg_slope=0.2, n_prelu=1): # activation layer act = act.lower() if act == 'relu': layer = nn.ReLU(inplace) elif act == 'relu6': layer = nn.ReLU6(inplace) elif act == 'leakyrelu': layer = nn.LeakyReLU(neg_slope, inplace) elif act == 'prelu': layer = nn.PReLU(num_parameters=n_prelu, init=neg_slope) elif act == 'gelu': layer = nn.GELU() elif act == 'hswish': layer = nn.Hardswish(inplace) else: raise NotImplementedError('activation layer [%s] is not found' % act) return layer def channel_shuffle(x, groups): batchsize, num_channels, height, width = x.data.size() channels_per_group = num_channels // groups # reshape x = x.view(batchsize, groups, channels_per_group, height, width) x = torch.transpose(x, 1, 2).contiguous() # flatten x = x.view(batchsize, -1, height, width) return x # Multi-scale depth-wise convolution (MSDC) class MSDC(nn.Module): def __init__(self, in_channels, kernel_sizes, stride, activation='relu6', dw_parallel=True): super(MSDC, self).__init__() self.in_channels = in_channels self.kernel_sizes = kernel_sizes self.activation = activation self.dw_parallel = dw_parallel self.dwconvs = nn.ModuleList([ nn.Sequential( nn.Conv2d(self.in_channels, self.in_channels, kernel_size, stride, kernel_size // 2, groups=self.in_channels, bias=False), nn.BatchNorm2d(self.in_channels), act_layer(self.activation, inplace=True) ) for kernel_size in self.kernel_sizes ]) self.init_weights('normal') def init_weights(self, scheme=''): named_apply(partial(_init_weights, scheme=scheme), self) def forward(self, x): # Apply the convolution layers in a loop outputs = [] for dwconv in self.dwconvs: dw_out = dwconv(x) outputs.append(dw_out) if self.dw_parallel == False: x = x+dw_out # You can return outputs based on what you intend to do with them return outputs 如何使用MSDC对Conv进行改进
最新发布
07-16
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值