51Halcon机器视觉

 找回密码
 会员注册

QQ登录

只需一步,快速开始

扫一扫,微信登录

查看: 202|回复: 4

[资料] 深度学习的术语(terms)

[复制链接]
  • TA的每日心情
    窃喜
    2019-12-2 10:35
  • 签到天数: 51 天

    连续签到: 1 天

    [LV.5]常住居民I

    136

    主题

    417

    帖子

    1684

    积分

    Rank: 7Rank: 7Rank: 7

    积分
    1684

    优秀版主

    发表于 2020-5-25 10:06:13 | 显示全部楼层 |阅读模式

    51Halcon诚邀您的加入,专注于机器视觉开发与应用技术,我们一直都在努力!

    您需要 登录 才可以下载或查看,没有帐号?会员注册

    x
    本帖最后由 wenluderen 于 2020-5-25 10:09 编辑

    In the following, we describe the most important terms used in the context of deep learning:

    anchor
    Anchors are fixed bounding boxes. They serve as reference boxes, with the aid of which the network
    proposes bounding boxes for the objects to be localized.


    annotation
    An annotation is the ground truth information, what a given instance in the data represents, in a way
    recognizable for the network. This is e.g., the bounding box and the corresponding label for an instance in
    object detection.


    anomaly
    An anomaly means something deviating from the norm, something unknown.


    backbone
    A backbone is a part of a pretrained classification network. Its task is to generate various feature maps,
    for what reason the classifying layer has been removed.

    batch size - hyperparameter
    ’batch_size’ The dataset is divided into smaller subsets of data, which are called
    batches. The batch size determines the number of images taken into a batch and thus processed simultaneously.


    bounding box
    Bounding boxes are rectangular boxes used to define a part within an image and to specify the
    localization of an object within an image.

    class agnostic
    Class agnostic means without the knowledge of the different classes.In HALCON, we use it for reduction of overlapping predicted bounding boxes. This means, for a class
    agnostic bounding box suppression the suppression of overlapping instances is done ignoring the knowledge
    of classes, thus strongly overlapping instances get suppressed independently of their class.





    1.发帖求助前要善用论坛搜索功能,那里可能会有你要找的答案;

    2.提问请组织好自己的逻辑,标题注明大概是什么问题,问题内容写详细,需提供问题症状、错误代码、截图、位置等等信息,不要让别人去猜你想问啥;

    3.如果你在论坛求助问题,并且已经从坛友或者管理的回复中解决了问题,请把帖子分类或者标题前面加上【已解决】

    4.回报帮助你解决问题的坛友,右下角【免费评分】赠与对方视觉币和热心值,伸手党遭人唾弃,做一个热心并受欢迎的人!

  • TA的每日心情
    窃喜
    2019-12-2 10:35
  • 签到天数: 51 天

    连续签到: 1 天

    [LV.5]常住居民I

    136

    主题

    417

    帖子

    1684

    积分

    Rank: 7Rank: 7Rank: 7

    积分
    1684

    优秀版主

     楼主| 发表于 2020-5-25 10:14:18 | 显示全部楼层
    change strategy A change strategy denotes the strategy, when and how hyperparameters are changed during the
    training of a DL model.
    class
    Classes are discrete categories (e.g., ’apple’, ’peach’, ’pear’) that the network distinguishes. In HALCON,
    the class of an instance is given by its appropriate annotation.

    classifier
    In the context of deep learning we refer to the term classifier as follows. The classifier takes an image
    as input and returns the inferred confidence values, expressing how likely the image belongs to every distinguished
    class. E.g., the three classes ’apple’, ’peach’, and ’pear’ are distinguished. Now we give an image
    of an apple to the classifier. As a result, the confidences ’apple’: 0.92, ’peach’: 0.07, and ’pear’: 0.01 could
    be returned.

    COCO

    COCO is an abbreviation for "common objects in context", a large-scale object detection, segmentation,
    and captioning dataset. There is a common file format for each of the different annotation types.

    confidence
    Confidence is a number expressing the affinity of an instance to a class. In HALCON the confidence
    is the probability, given in the range of [0,1]. Alternative name: score


    confusion matrix

    A confusion matrix is a table which compares the classes predicted by the network (top-1) with
    the ground truth class affiliations. It is often used to visualize the performance of the network on a validation
    or test set.


    ××××××××××
    Convolutional Neural Networks (CNNs)
    Convolutional Neural Networks are neural networks used in deep
    learning, characterized by the presence of at least one convolutional layer in the network. They are particularly
    successful for image classification.

    data
    We use the term data in the context of deep learning for instances to be recognized (e.g., images) and their
    appropriate information concerning the predictable characteristics (e.g., the labels in case of classification).



    data augmentation
    Data augmentation is the generation of altered copies of samples within a dataset. This is
    done in order to augment the richness of the dataset, e.g., through flipping or rotating.

    dataset: training, validation, and test set
    With dataset we refer to the complete set of data used for a training.
    The dataset is split into three, if possible disjoint, subsets:
    • The training set contains the data on which the algorithm optimizes the network directly.
    • The validation set contains the data to evaluate the network performance during training.
    • The test set is used to test possible inferences (predictions), thus to test the performance on data without
    any influence on the network optimization.



    ×××××

    deep learning
    The term "deep learning" was originally used to describe the training of neural networks with
    multiple hidden layers. Today it is rather used as a generic term for several different concepts in machine
    learning. In HALCON, we use the term deep learning for methods using a neural network with multiple
    hidden layers.

    epoch
    In the context of deep learning, an epoch is a single training iteration over the entire training data, i.e., over
    all batches. Iterations over epochs should not be confused with the iterations over single batches (e.g., within
    an epoch).

    errors
    In the context of deep learning, we refer to error when the inferred class of an instance does not match the
    real class (e.g., the ground truth label in case of classification). Within HALCON, we use the term error in
    deep learning when we refer to the top-1 error.

    feature map
    A feature map is the output of a given layer

    feature pyramid
    A feature pyramid is simply a group of feature maps, whereby every feature map origins from
    another level, i.e., it is smaller than its preceding levels.


    head
    Heads are subnetworks. For certain architectures they attach on selected pyramid levels. These subnetworks
    proceed information from previous parts of the total network in order to generate spatially resolved output,
    e.g., for the class predictions. Thereof they generate the output of the total network and therewith constitute
    the input of the losses.


    1.发帖求助前要善用论坛搜索功能,那里可能会有你要找的答案;

    2.提问请组织好自己的逻辑,标题注明大概是什么问题,问题内容写详细,需提供问题症状、错误代码、截图、位置等等信息,不要让别人去猜你想问啥;

    3.如果你在论坛求助问题,并且已经从坛友或者管理的回复中解决了问题,请把帖子分类或者标题前面加上【已解决】

    4.回报帮助你解决问题的坛友,右下角【免费评分】赠与对方视觉币和热心值,伸手党遭人唾弃,做一个热心并受欢迎的人!

  • TA的每日心情
    窃喜
    2019-12-2 10:35
  • 签到天数: 51 天

    连续签到: 1 天

    [LV.5]常住居民I

    136

    主题

    417

    帖子

    1684

    积分

    Rank: 7Rank: 7Rank: 7

    积分
    1684

    优秀版主

     楼主| 发表于 2020-5-25 10:21:49 | 显示全部楼层
    hyperparameter
    Like every machine learning model, CNNs contain many formulas with many parameters. During
    training the model learns from the data in the sense of optimizing the parameters. However, such models
    can have other, additional parameters, which are not directly learned during the regular training. These
    parameters have values set before starting the training. We refer to this last type of parameters as hyperparameters
    in order to distinguish them from the network parameters that are optimized during training. Or
    from another point of view, hyperparameters are solver-specific parameters.
    Prominent examples are the initial learning rate or the batch size.

    inference phase
    The inference phase is the stage when a trained network is applied to predict (infer) instances
    (which can be the total input image or just a part of it) and eventually their localization. Unlike during the
    training phase, the network is not changed anymore in the inference phase.

    intersection over union
    The intersection over union (IoU) is a measure to quantify the overlap of two areas. We
    can determine the parts common in both areas, the intersection, as well as the united areas, the union. The
    IoU is the ratio between the two areas intersection and union.
    The application of this concept may differ between the methods.

    label
    Labels are arbitrary strings used to define the class of an image. In HALCON these labels are given by the
    image name (eventually followed by a combination of underscore and digits) or by the folder name, e.g.,
    ’apple_01.png’, ’pear.png’, ’peach/01.png’.

    layer and hidden layer
    A layer is a building block in a neural network, thus performing specific tasks (e.g., convolution,
    pooling, etc., for further details we refer to the “Solution Guide on Classification”).
    It can be seen as a container, which receives weighted input, transforms it, and returns the output to the next
    layer. Input and output layers are connected to the dataset, i.e., the images or the labels, respectively. All
    layers in between are called hidden layers.

    learning rate - hyperparameter
    ’learning_rate’ The learning rate is the weighting, with which the gradient (see
    the entry for the stochastic gradient descent SGD) is considered when updating the arguments of the loss
    function. In simple words, when we want to optimize a function, the gradient tells us the direction in which
    we shall optimize and the learning rate determines how far along this direction we step.
    Alternative names: , step size

    level
    The term level is used to denote within a feature pyramid network the whole group of layers, whose feature
    maps have the same width and height. Thereby the input image represents level 0.

    loss
    A loss function compares the prediction from the network with the given information, what it should find in
    the image (and, if applicable, also where), and penalizes deviations. This loss function is the function we
    optimize during the training process to adapt the network to a specific task.
    Alternative names: objective function, cost function, utility function

    momentum - hyperparameter ’momentum’ The momentum  2 [0; 1) is used for the optimization of the loss
    function arguments. When the loss function arguments are updated (after having calculated the gradient), a
    fraction  of the previous update vector (of the past iteration step) is added. This has the effect of damping
    oscillations. We refer to the hyperparameter  as momentum. When  is set to 0, the momentum method has
    no influence. In simple words, when we update the loss function arguments, we still remember the step we
    did for the last update. Now we go a step in direction of the gradient with a length according to the learning
    rate and additionally we repeat the step we did last time, but this time only  times as long.


    non-maximum suppression
    In object detection, non-maximum suppression is used to suppress overlapping predicted
    bounding boxes. When different instances overlap more than a given threshold value, only the one
    with the highest confidence value is kept while the other instances, not having the maximum confidence
    value, are suppressed.

    overfitting
    Overfitting happens when the network starts to ’memorize’ training data instead of learning how to
    find general rules for the classification. This becomes visible when the model continues to minimize error on
    the training set but the error on the validation set increases. Since most neural networks have a huge amount
    of weights, these networks are particularly prone to overfitting.

    1.发帖求助前要善用论坛搜索功能,那里可能会有你要找的答案;

    2.提问请组织好自己的逻辑,标题注明大概是什么问题,问题内容写详细,需提供问题症状、错误代码、截图、位置等等信息,不要让别人去猜你想问啥;

    3.如果你在论坛求助问题,并且已经从坛友或者管理的回复中解决了问题,请把帖子分类或者标题前面加上【已解决】

    4.回报帮助你解决问题的坛友,右下角【免费评分】赠与对方视觉币和热心值,伸手党遭人唾弃,做一个热心并受欢迎的人!

  • TA的每日心情
    窃喜
    2019-12-2 10:35
  • 签到天数: 51 天

    连续签到: 1 天

    [LV.5]常住居民I

    136

    主题

    417

    帖子

    1684

    积分

    Rank: 7Rank: 7Rank: 7

    积分
    1684

    优秀版主

     楼主| 发表于 2020-5-25 10:24:08 | 显示全部楼层
    regularization - hyperparameter ’weight_prior’ Regularization is a technique to prevent neural networks from
    overfitting by adding an extra term to the loss function. It works by penalizing large weights, i.e., pushing
    the weights towards zero. Simply put, regularization favors simpler models that are less likely to fit to
    noise in the training data and generalize better. In HALCON, regularization is controlled via the parameter
    ’weight_prior’.
    Alternative names: regularization parameter, weight decay parameter,  (note that in HALCON we use 
    for the learning rate and within formulas the symbol for the regularization parameter).


    retraining
    We define retraining as updating the weights of an already pretrained network, i.e., during retraining
    the network learns the specific task.
    Alternative names: fine-tuning.


    solver
    The solver optimizes the network by updating the weights in a way to optimize (i.e., minimize) the loss

    stochastic gradient descent (SGD)
    SGD is an iterative optimization algorithm for differentiable functions. In
    deep learning we use this algorithm to calculate the gradient to optimize (i.e., minimize) the loss function.
    A key feature of the SGD is to calculate the gradient only based on a single batch containing stochastically
    sampled data and not all data.

    top-k error
    The classifier infers for a given image class confidences of how likely the image belongs to every
    distinguished class. Thus, for an image we can sort the predicted classes according to the confidence value
    the classifier assigned. The top-k error tells the ratio of predictions where the ground truth class is not
    within the k predicted classes with highest probability. In the case of top-1 error, we check if the target label
    matches the prediction with the highest probability. In the case of top-3 error, we check if the target label
    matches one of the top 3 predictions (the 3 labels getting the highest probability for this image).
    Alternative names: top-k score


    transfer learning
    Transfer learning refers to the technique where a network is built upon the knowledge of an
    already existing network. In concrete terms this means taking an already (pre)trained network with its
    weights and adapt the output layer to the respective application to get your network. In HALCON, we also
    see the following retraining step as a part of transfer learning.

    underfitting
    Underfitting occurs when the model over-generalizes. In other words it is not able to describe the
    complexity of the task. This is directly reflected in the error on the training set, which does not decrease
    significantly.


    weights
    In general weights are the free parameters of the network, which are altered during the training due to the
    optimization of the loss. A layer with weights multiplies or adds them with its input values. In contrast to
    hyperparameters, weights are optimized and thus changed during the training.

    1.发帖求助前要善用论坛搜索功能,那里可能会有你要找的答案;

    2.提问请组织好自己的逻辑,标题注明大概是什么问题,问题内容写详细,需提供问题症状、错误代码、截图、位置等等信息,不要让别人去猜你想问啥;

    3.如果你在论坛求助问题,并且已经从坛友或者管理的回复中解决了问题,请把帖子分类或者标题前面加上【已解决】

    4.回报帮助你解决问题的坛友,右下角【免费评分】赠与对方视觉币和热心值,伸手党遭人唾弃,做一个热心并受欢迎的人!

  • TA的每日心情
    开心
    半小时前
  • 签到天数: 189 天

    连续签到: 1 天

    [LV.7]常住居民III

    0

    主题

    61

    帖子

    328

    积分

    Rank: 2Rank: 2

    积分
    328

    切换助手验证会员

    发表于 2020-5-25 19:06:05 | 显示全部楼层
    有中文的介绍就完美了

    1.发帖求助前要善用论坛搜索功能,那里可能会有你要找的答案;

    2.提问请组织好自己的逻辑,标题注明大概是什么问题,问题内容写详细,需提供问题症状、错误代码、截图、位置等等信息,不要让别人去猜你想问啥;

    3.如果你在论坛求助问题,并且已经从坛友或者管理的回复中解决了问题,请把帖子分类或者标题前面加上【已解决】

    4.回报帮助你解决问题的坛友,右下角【免费评分】赠与对方视觉币和热心值,伸手党遭人唾弃,做一个热心并受欢迎的人!

    您需要登录后才可以回帖 会员登录 | 会员注册

    本版积分规则

    建议您使用Chrome、Firefox、Edge、IE10及以上版本和360等主流浏览器浏览本网站

    51Halcon会员技术交流会员技术交流 | 51Halcon官方客服咨询官方客服咨询 | Halcon切换助手使用反馈切换助手使用

    有问题需要咨询站长?| 申请友链| 小黑屋| 手机版| Archiver|  

    粤ICP备15095995号-2 粤公网安备44030602000670号

    CopyRight © 2015-2020 51Halcon机器视觉. Tencent Cloud X3.4.

    快速回复 返回顶部 返回列表