什么是衡量训练性能的好学习率图

Question

我正在从头开始训练一个基于 SSD 的对象检测网络。我正在训练 250,000 张图像。数据集对某些类有偏差，但我对少数类也有很好的表示（2000 年左右）。

我看到模型训练得不好，150k 步，它只达到了 8% 的准确率和 25% 的召回率。学习率也不是平滑图。我应该期待什么样的学习率图表，以及我可以尝试哪些其他方法来改进我的训练？

  optimizer {
    rms_prop_optimizer {
      learning_rate {
        exponential_decay_learning_rate {
          initial_learning_rate: 0.004000000189989805
          decay_steps: 800720
          decay_factor: 0.949999988079071
        }
      }
      momentum_optimizer_value: 0.8999999761581421
      decay: 0.8999999761581421
      epsilon: 1.0
    }
  }

Answer 1

你的模型的学习率很差。你肯定是过拟合了。

一些变化是： 1.先做交叉验证 2.尝试删除一些功能。 3.确保您的标签编码正确

可能有很多事情可能是错误的。很难说。 作为参考，我可以给你架构。

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
from layers import *
from data import voc, coco
import os

class SSD(nn.Module):
"""Single Shot Multibox Architecture
The network is composed of a base VGG network followed by the
added multibox conv layers.  Each multibox layer branches into
    1) conv2d for class conf scores
    2) conv2d for localization predictions
    3) associated priorbox layer to produce default bounding
       boxes specific to the layer's feature map size.
See: https://arxiv.org/pdf/1512.02325.pdf for more details.
Args:
    phase: (string) Can be "test" or "train"
    size: input image size
    base: VGG16 layers for input, size of either 300 or 500
    extras: extra layers that feed to multibox loc and conf layers
    head: "multibox head" consists of loc and conf conv layers
"""

def __init__(self, phase, size, base, extras, head, num_classes):
    super(SSD, self).__init__()
    self.phase = phase
    self.num_classes = num_classes
    self.cfg = (coco, voc)[num_classes == 21]
    self.priorbox = PriorBox(self.cfg)
    self.priors = Variable(self.priorbox.forward(), volatile=True)
    self.size = size

    # SSD network
    self.vgg = nn.ModuleList(base)
    # Layer learns to scale the l2 normalized features from conv4_3
    self.L2Norm = L2Norm(512, 20)
    self.extras = nn.ModuleList(extras)

    self.loc = nn.ModuleList(head[0])
    self.conf = nn.ModuleList(head[1])

    if phase == 'test':
        self.softmax = nn.Softmax(dim=-1)
        self.detect = Detect(num_classes, 0, 200, 0.01, 0.45)

def forward(self, x):
    """Applies network layers and ops on input image(s) x.
    Args:
        x: input image or batch of images. Shape: [batch,3,300,300].
    Return:
        Depending on phase:
        test:
            Variable(tensor) of output class label predictions,
            confidence score, and corresponding location predictions for
            each object detected. Shape: [batch,topk,7]
        train:
            list of concat outputs from:
                1: confidence layers, Shape: [batch*num_priors,num_classes]
                2: localization layers, Shape: [batch,num_priors*4]
                3: priorbox layers, Shape: [2,num_priors*4]
    """
    sources = list()
    loc = list()
    conf = list()

    # apply vgg up to conv4_3 relu
    for k in range(23):
        x = self.vgg[k](x)

    s = self.L2Norm(x)
    sources.append(s)

    # apply vgg up to fc7
    for k in range(23, len(self.vgg)):
        x = self.vgg[k](x)
    sources.append(x)

    # apply extra layers and cache source layer outputs
    for k, v in enumerate(self.extras):
        x = F.relu(v(x), inplace=True)
        if k % 2 == 1:
            sources.append(x)

    # apply multibox head to source layers
    for (x, l, c) in zip(sources, self.loc, self.conf):
        loc.append(l(x).permute(0, 2, 3, 1).contiguous())
        conf.append(c(x).permute(0, 2, 3, 1).contiguous())

    loc = torch.cat([o.view(o.size(0), -1) for o in loc], 1)
    conf = torch.cat([o.view(o.size(0), -1) for o in conf], 1)
    if self.phase == "test":
        output = self.detect(
            loc.view(loc.size(0), -1, 4),                   # loc preds
            self.softmax(conf.view(conf.size(0), -1,
                         self.num_classes)),                # conf preds
            self.priors.type(type(x.data))                  # default boxes
        )
    else:
        output = (
            loc.view(loc.size(0), -1, 4),
            conf.view(conf.size(0), -1, self.num_classes),
            self.priors
        )
    return output

def load_weights(self, base_file):
    other, ext = os.path.splitext(base_file)
    if ext == '.pkl' or '.pth':
        print('Loading weights into state dict...')
        self.load_state_dict(torch.load(base_file,
                             map_location=lambda storage, loc: storage))
        print('Finished!')
    else:
        print('Sorry only .pth and .pkl files supported.')



def vgg(cfg, i, batch_norm=False):
    layers = []
    in_channels = i
    for v in cfg:
        if v == 'M':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
        elif v == 'C':
            layers += [nn.MaxPool2d(kernel_size=2, stride=2, ceil_mode=True)]
        else:
            conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
            if batch_norm:
                layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
            else:
                layers += [conv2d, nn.ReLU(inplace=True)]
            in_channels = v
    pool5 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
    conv6 = nn.Conv2d(512, 1024, kernel_size=3, padding=6, dilation=6)
    conv7 = nn.Conv2d(1024, 1024, kernel_size=1)
    layers += [pool5, conv6,
               nn.ReLU(inplace=True), conv7, nn.ReLU(inplace=True)]
    return layers


def add_extras(cfg, i, batch_norm=False):
    # Extra layers added to VGG for feature scaling
    layers = []
    in_channels = i
    flag = False
    for k, v in enumerate(cfg):
        if in_channels != 'S':
            if v == 'S':
                layers += [nn.Conv2d(in_channels, cfg[k + 1],
                           kernel_size=(1, 3)[flag], stride=2, padding=1)]
            else:
                layers += [nn.Conv2d(in_channels, v, kernel_size=(1, 3)[flag])]
            flag = not flag
        in_channels = v
    return layers


def multibox(vgg, extra_layers, cfg, num_classes):
    loc_layers = []
    conf_layers = []
    vgg_source = [21, -2]
    for k, v in enumerate(vgg_source):
        loc_layers += [nn.Conv2d(vgg[v].out_channels,
                                 cfg[k] * 4, kernel_size=3, padding=1)]
        conf_layers += [nn.Conv2d(vgg[v].out_channels,
                        cfg[k] * num_classes, kernel_size=3, padding=1)]
    for k, v in enumerate(extra_layers[1::2], 2):
        loc_layers += [nn.Conv2d(v.out_channels, cfg[k]
                                 * 4, kernel_size=3, padding=1)]
        conf_layers += [nn.Conv2d(v.out_channels, cfg[k]
                                  * num_classes, kernel_size=3, padding=1)]
    return vgg, extra_layers, (loc_layers, conf_layers)


base = {
    '300': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'C', 512, 512, 512, 'M',
            512, 512, 512],
    '512': [],
}
extras = {
    '300': [256, 'S', 512, 128, 'S', 256, 128, 256, 128, 256],
    '512': [],
}
mbox = {
    '300': [4, 6, 6, 6, 4, 4],  # number of boxes per feature map location
    '512': [],
}


def build_ssd(phase, size=300, num_classes=21):
    if phase != "test" and phase != "train":
        print("ERROR: Phase: " + phase + " not recognized")
        return
    if size != 300:
        print("ERROR: You specified size " + repr(size) + ". However, " +
              "currently only SSD300 (size=300) is supported!")
        return
    base_, extras_, head_ = multibox(vgg(base[str(size)], 3),
                                     add_extras(extras[str(size)], 1024),
                                     mbox[str(size)], num_classes)
    return SSD(phase, size, base_, extras_, head_, num_classes)

Answer 2

这是一个超参数调整问题。
首先，刚开始时，您需要坚持使用基本的普通随机梯度下降法。这既是为了让事情变得简单，也是为了让您了解您的数据集和模型。此外，这将减少您可以调整的超参数数量。
然后，您应该训练少量的 epoch（取决于训练时间），并以对数方式改变学习率。

学习率：
0.0001
0.001
0.01
0.1
1.0
10
100

这样，您将大致了解您的网络将在何处进行良好的训练。只有在找到一个像样的球场之后，您才应该开始添加指数衰减和动量。

尝试阅读hyperparameter tuning 上的一些资源。此外，Andrew Ng 在 coursera 上的 courses 非常适合教授构建和调整 DNN 的方法。

---

回答你的问题：我认为你的学习率太低了。我希望学习率图的形状会有所不同。但是随着动量对抗指数衰减，如果不明确绘制它就很难知道。您的准确率和召回率图实际上表明网络正在学习一些东西。但是，由于您的学习率下降，看起来它的峰值非常低，然后变平。很可能，此时您的学习率实际上为零。