关于pytorch中,self.training的理解

最近在看源码的过程中看到了有些模型的forward函数中self.training判断训练还是推理的状态。 这个是如何做到呢?下面我通过源码分析一下:

 if self.training:
       return x, x_dist
  else:
       # during inference, return the average of both classifier predictions
       return (x + x_dist) / 2

这段代码来自deit的代码,在训练的时候,你会发现self.training为True,在推理的时候self.training为False,如果直接搜索training这个字段,你发现只有一个结果,没有看到在哪里赋值,只有这一处在使用,我们继续寻找父类VisionTransformer,发现VisionTransformer里面也没有,只能继续寻找父类nn.Module,在这个类里面找到了。

class Module:
    r"""Base class for all neural network modules.

    Your models should also subclass this class.

    Modules can also contain other Modules, allowing to nest them in
    a tree structure. You can assign the submodules as regular attributes::

        import torch.nn as nn
        import torch.nn.functional as F

        class Model(nn.Module):
            def __init__(self):
                super().__init__()
                self.conv1 = nn.Conv2d(1, 20, 5)
                self.conv2 = nn.Conv2d(20, 20, 5)

            def forward(self, x):
                x = F.relu(self.conv1(x))
                return F.relu(self.conv2(x))

    Submodules assigned in this way will be registered, and will have their
    parameters converted too when you call :meth:`to`, etc.

    .. note::
        As per the example above, an ``__init__()`` call to the parent class
        must be made before assignment on the child.

    :ivar training: Boolean represents whether this module is in training or
                    evaluation mode.
    :vartype training: bool
    """

    dump_patches: bool = False

    _version: int = 1
    r"""This allows better BC support for :meth:`load_state_dict`. In
    :meth:`state_dict`, the version number will be saved as in the attribute
    `_metadata` of the returned state dict, and thus pickled. `_metadata` is a
    dictionary with keys that follow the naming convention of state dict. See
    ``_load_from_state_dict`` on how to use this information in loading.

    If new parameters/buffers are added/removed from a module, this number shall
    be bumped, and the module's `_load_from_state_dict` method can compare the
    version number and do appropriate changes if the state dict is from before
    the change."""

    training: bool
    _parameters: Dict[str, Optional[Parameter]]
    _buffers: Dict[str, Optional[Tensor]]
    _non_persistent_buffers_set: Set[str]
    _backward_hooks: Dict[int, Callable]
    _is_full_backward_hook: Optional[bool]
    _forward_hooks: Dict[int, Callable]
    _forward_pre_hooks: Dict[int, Callable]
    _state_dict_hooks: Dict[int, Callable]
    _load_state_dict_pre_hooks: Dict[int, Callable]
    _load_state_dict_post_hooks: Dict[int, Callable]
    _modules: Dict[str, Optional['Module']]

我们继续在源码里寻找,直到看到train()和eval函数才明白:

    def train(self: T, mode: bool = True) -> T:
        r"""Sets the module in training mode.

        This has any effect only on certain modules. See documentations of
        particular modules for details of their behaviors in training/evaluation
        mode, if they are affected, e.g. :class:`Dropout`, :class:`BatchNorm`,
        etc.

        Args:
            mode (bool): whether to set training mode (``True``) or evaluation
                         mode (``False``). Default: ``True``.

        Returns:
            Module: self
        """
        if not isinstance(mode, bool):
            raise ValueError("training mode is expected to be boolean")
        self.training = mode
        for module in self.children():
            module.train(mode)
        return self

    def eval(self: T) -> T:
        r"""Sets the module in evaluation mode.

        This has any effect only on certain modules. See documentations of
        particular modules for details of their behaviors in training/evaluation
        mode, if they are affected, e.g. :class:`Dropout`, :class:`BatchNorm`,
        etc.

        This is equivalent with :meth:`self.train(False) <torch.nn.Module.train>`.

        See :ref:`locally-disable-grad-doc` for a comparison between
        `.eval()` and several similar mechanisms that may be confused with it.

        Returns:
            Module: self
        """
        return self.train(False)

在我们训练的时候会执行model.train(),这时候将training设置为True,在执行eval()的时候,将training设置为false。

智能网联汽车的安全员高级考试涉及多个方面的专业知识,包括但不限于自动驾驶技术原理、车辆传感器融合、网络安全防护以及法律法规等内容。以下是针对该主题的一些核心知识点解析: ### 关于智能网联车安全员高级考试的核心内容 #### 1. 自动驾驶分级标准 国际自动机工程师学会(SAE International)定义了六个级别的自动驾驶等级,从L0到L5[^1]。其中,L3及以上级别需要安全员具备更高的应急处理能力。 #### 2. 车辆感知系统的组成与功能 智能网联车通常配备多种传感器,如激光雷达、毫米波雷达、摄像头和超声波传感器等。这些设备协同工作以实现环境感知、障碍物检测等功能[^2]。 #### 3. 数据通信与网络安全 智能网联车依赖V2X(Vehicle-to-Everything)技术进行数据交换,在此过程中需防范潜在的网络攻击风险,例如中间人攻击或恶意软件入侵[^3]。 #### 4. 法律法规要求 不同国家和地区对于无人驾驶测试及运营有着严格的规定,考生应熟悉当地交通法典中有关自动化驾驶部分的具体条款[^4]。 ```python # 示例代码:模拟简单决策逻辑 def decide_action(sensor_data): if sensor_data['obstacle'] and not sensor_data['emergency']: return 'slow_down' elif sensor_data['pedestrian_crossing']: return 'stop_and_yield' else: return 'continue_driving' example_input = {'obstacle': True, 'emergency': False, 'pedestrian_crossing': False} action = decide_action(example_input) print(f"Action to take: {action}") ``` 需要注意的是,“橙点同学”作为特定平台上的学习资源名称,并不提供官方认证的标准答案集;建议通过正规渠道获取教材并参加培训课程来准备此类资格认证考试。
评论 3
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

打赏作者

AI浩

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

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