赞
踩
import torch.nn as nn import torch class BasicBlock(nn.Module): expansion = 1 def __init__(self, in_channel, out_channel, stride=1, downsample=None, **kwargs): super(BasicBlock, self).__init__() self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel, kernel_size=3, stride=stride, padding=1, bias=False) self.bn1 = nn.BatchNorm2d(out_channel) self.relu = nn.ReLU() self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel, kernel_size=3, stride=1, padding=1, bias=False) self.bn2 = nn.BatchNorm2d(out_channel) self.downsample = downsample def forward(self, x): identity = x if self.downsample is not None: identity = self.downsample(x) out = self.conv1(x) out = self.bn1(out) out = self.relu(out) out = self.conv2(out) out = self.bn2(out) out += identity out = self.relu(out) return out class Bottleneck(nn.Module): """ 注意:原论文中,在虚线残差结构的主分支上,第一个1x1卷积层的步距是2,第二个3x3卷积层步距是1。 但在pytorch官方实现过程中是第一个1x1卷积层的步距是1,第二个3x3卷积层步距是2, 这么做的好处是能够在top1上提升大概0.5%的准确率。 可参考Resnet v1.5 https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch """ expansion = 4 def __init__(self, in_channel, out_channel, stride=1, downsample=None, groups=1, width_per_group=64): super(Bottleneck, self).__init__() width = int(out_channel * (width_per_group / 64.)) * groups self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=width, kernel_size=1, stride=1, bias=False) # squeeze channels self.bn1 = nn.BatchNorm2d(width) # ----------------------------------------- self.conv2 = nn.Conv2d(in_channels=width, out_channels=width, groups=groups, kernel_size=3, stride=stride, bias=False, padding=1) self.bn2 = nn.BatchNorm2d(width) # ----------------------------------------- self.conv3 = nn.Conv2d(in_channels=width, out_channels=out_channel*self.expansion, kernel_size=1, stride=1, bias=False) # unsqueeze channels self.bn3 = nn.BatchNorm2d(out_channel*self.expansion) self.relu = nn.ReLU(inplace=True) self.downsample = downsample def forward(self, x): identity = x if self.downsample is not None: identity = self.downsample(x) out = self.conv1(x) out = self.bn1(out) out = self.relu(out) out = self.conv2(out) out = self.bn2(out) out = self.relu(out) out = self.conv3(out) out = self.bn3(out) out += identity out = self.relu(out) return out class ResNet(nn.Module): def __init__(self, block, blocks_num, num_classes=1000, include_top=True, groups=1, width_per_group=64): super(ResNet, self).__init__() self.include_top = include_top self.in_channel = 64 self.groups = groups self.width_per_group = width_per_group self.conv1 = nn.Conv2d(3, self.in_channel, kernel_size=7, stride=2, padding=3, bias=False) self.bn1 = nn.BatchNorm2d(self.in_channel) self.relu = nn.ReLU(inplace=True) self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) self.layer1 = self._make_layer(block, 64, blocks_num[0]) self.layer2 = self._make_layer(block, 128, blocks_num[1], stride=2) self.layer3 = self._make_layer(block, 256, blocks_num[2], stride=2) self.layer4 = self._make_layer(block, 512, blocks_num[3], stride=2) if self.include_top: self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) # output size = (1, 1) self.fc = nn.Linear(512 * block.expansion, num_classes) for m in self.modules(): if isinstance(m, nn.Conv2d): nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') def _make_layer(self, block, channel, block_num, stride=1): downsample = None if stride != 1 or self.in_channel != channel * block.expansion: downsample = nn.Sequential( nn.Conv2d(self.in_channel, channel * block.expansion, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(channel * block.expansion)) layers = [] layers.append(block(self.in_channel, channel, downsample=downsample, stride=stride, groups=self.groups, width_per_group=self.width_per_group)) self.in_channel = channel * block.expansion for _ in range(1, block_num): layers.append(block(self.in_channel, channel, groups=self.groups, width_per_group=self.width_per_group)) return nn.Sequential(*layers) def forward(self, x): x = self.conv1(x) x = self.bn1(x) x = self.relu(x) x = self.maxpool(x) x = self.layer1(x) x = self.layer2(x) x = self.layer3(x) x = self.layer4(x) if self.include_top: x = self.avgpool(x) x = torch.flatten(x, 1) x = self.fc(x) return x # # resnet34 pre-train parameters https://download.pytorch.org/models/resnet34-333f7ec4.pth # def resnet_samll(num_classes=1000, include_top=True): # return ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top) # # resnet50 pre-train parameters https://download.pytorch.org/models/resnet50-19c8e357.pth # def resnet(num_classes=1000, include_top=True): # return ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top) # # resnet101 pre-train parameters https://download.pytorch.org/models/resnet101-5d3b4d8f.pth # def resnet_big(num_classes=1000, include_top=True): # return ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, include_top=include_top) # # resneXt pre-train parameters https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth # def resnext(num_classes=1000, include_top=True): # groups = 32 # width_per_group = 4 # return ResNet(Bottleneck, [3, 4, 6, 3], # num_classes=num_classes, # include_top=include_top, # groups=groups, # width_per_group=width_per_group) # # resneXt_big pre-train parameters https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth # def resnext_big(num_classes=1000, include_top=True): # groups = 32 # width_per_group = 8 # return ResNet(Bottleneck, [3, 4, 23, 3], # num_classes=num_classes, # include_top=include_top, # groups=groups, # width_per_group=width_per_group) def resnet34(num_classes=1000, include_top=True): # https://download.pytorch.org/models/resnet34-333f7ec4.pth return ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top) def resnet50(num_classes=1000, include_top=True): # https://download.pytorch.org/models/resnet50-19c8e357.pth return ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top) def resnet101(num_classes=1000, include_top=True): # https://download.pytorch.org/models/resnet101-5d3b4d8f.pth return ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, include_top=include_top) def resnext50_32x4d(num_classes=1000, include_top=True): # https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth groups = 32 width_per_group = 4 return ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top, groups=groups, width_per_group=width_per_group) def resnext101_32x8d(num_classes=1000, include_top=True): # https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth groups = 32 width_per_group = 8 return ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, include_top=include_top, groups=groups, width_per_group=width_per_group)
import torch.nn as nn import torch import torch import matplotlib.pyplot as plt import numpy as np from PIL import Image from torchvision import transforms class AlexNet(nn.Module): def __init__(self, num_classes=5, init_weights=False): super().__init__() self.features = nn.Sequential( nn.Conv2d(3, 96, kernel_size=11, stride=4, padding=2), # input[3, 224, 224] output[96, 55, 55] nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=3, stride=2), # output[96, 27, 27] nn.Conv2d(96, 256, kernel_size=5, padding=2), # output[256, 27, 27] nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=3, stride=2), # output[256, 13, 13] nn.Conv2d(256, 384, kernel_size=3, padding=1), # output[384, 13, 13] nn.ReLU(inplace=True), nn.Conv2d(384, 384, kernel_size=3, padding=1), # output[384, 13, 13] nn.ReLU(inplace=True), nn.Conv2d(384, 256, kernel_size=3, padding=1), # output[256, 13, 13] nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=3, stride=2), # output[256, 6, 6] ) self.classifier = nn.Sequential( nn.Dropout(p=0.5), nn.Linear(256 * 6 * 6, 4096), nn.ReLU(inplace=True), nn.Dropout(p=0.5), nn.Linear(4096, 4096), nn.ReLU(inplace=True), nn.Linear(4096, num_classes), ) if init_weights: self._initialize_weights() def forward(self, x): outputs = [] for name, module in self.features.named_children(): x = module(x) if name in ["0"]: outputs.append(x) return outputs def _initialize_weights(self): for m in self.modules(): if isinstance(m, nn.Conv2d): nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu') if m.bias is not None: nn.init.constant_(m.bias, 0) elif isinstance(m, nn.Linear): nn.init.normal_(m.weight, 0, 0.01) nn.init.constant_(m.bias, 0) data_transform = transforms.Compose( [transforms.Resize((224, 224)), transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]) # create model model = AlexNet(num_classes=5) # load model weights model_weight_path = "/Users/jiangxiyu/根目录/深度学习/Deep-Learning-Image-Classification-Models-Based-CNN-or-Attention/results/weights/alexnet/AlexNet.pth" model.load_state_dict(torch.load(model_weight_path)) print(model) # load image img = Image.open("/Users/jiangxiyu/根目录/深度学习/flower/train/daisy/5547758_eea9edfd54_n.jpg") # [N, C, H, W] img = data_transform(img) # expand batch dimension img = torch.unsqueeze(img, dim=0) # forward out_put = model(img) for feature_map in out_put: # [N, C, H, W] -> [C, H, W] im = np.squeeze(feature_map.detach().numpy()) # [C, H, W] -> [H, W, C] im = np.transpose(im, [1, 2, 0]) # show top 12 feature maps plt.figure() for i in range(12): ax = plt.subplot(3, 4, i+1) # [H, W, C] plt.imshow(im[:, :, i], cmap='gray') plt.show() plt.savefig("./AelxNet_vis.jpg")
* 在刚开始训练的时候先使用一个较小的学习率,训练一些epoches或iterations,等模型稳定时再修改为预先设置的学习率进行训练。 提 1 个点
* 在分类问题中,我们的最后一层一般是全连接层,然后对应标签的one-hot编码,即把对应类别的值编码为1,其他为0。这种编码方式和通过降低交叉熵损失来调整参数的方式结合起来,会有一些问题。这种方式会鼓励模型对不同类别的输出分数差异非常大,或者说,模型过分相信它的判断。但是,对于一个由多人标注的数据集,不同人标注的准则可能不同,每个人的标注也可能会有一些错误。模型对标签的过分相信会导致过拟合。标签平滑(Label-smoothing regularization,LSR)是应对该问题的有效方法之一,它的具体思想是降低我们对于标签的信任,例如我们可以将损失的目标值从1稍微降到0.9,或者将从0稍微升到0.1。标签平滑最早在inception-v2[4]中被提出。
* (RICAP)方法随剪四个图片的中部分,然后把它们拼接为一个图片,同时混合这四个
* 知识蒸馏(Knowledge Distilling)是模型压缩的一种方法,是指利用已经训练完成的一个较复杂的Teacher模型,指导一个较轻量的Student模型训练,从而在减小模型大小和参数量的同时,尽量保持Teacher模型的准确率。模型复杂度如下图所示,很明显左边的老师模型的参数量远大于右边的学生模型,那么在部署上线时,只需要部署学生模型则可,这样就需要更少的显存,同时计算更快,一举两得。
* 给定输入,假定 p 是真正的概率分布,z 和 r 分别是学生模型和教师模型最后一个全连接层的输出。之前我们会用交叉熵损失l(p.softmax(z))来度量p和z之间的差异,这里的蒸馏损失同样用交叉熵。所以,使用知识蒸馏方法总的损失函数是
* T越高,softmax的output probability distribution越趋于平滑,其分布的熵越大,负标签携带的信息会被相对地放大,模型训练将更加关注负标签。
l
(
p
,
softmax
(
z
)
)
+
T
2
⋅
l
(
softmax
(
r
/
T
)
,
softmax
(
z
/
T
)
)
l(p, \text{softmax}(z)) + T^2 \cdot l(\text{softmax}(r/T),\text{softmax}(z/T))
l(p,softmax(z))+T2⋅l(softmax(r/T),softmax(z/T))
* Cutout是一种新的正则化方法。原理是在训练时随机把图片的一部分减掉,这样能提高模型的鲁棒性。它的来源是计算机视觉任务中经常遇到的物体遮挡问题。通过cutout生成一些类似被遮挡的物体,不仅可以让模型在遇到遮挡问题时表现更好,还能让模型在做决定时更多地考虑环境(context)。
* Random erasing其实和cutout非常类似,也是一种模拟物体遮挡情况的数据增强方法。区别在于,cutout是把图片中随机抽中的矩形区域的像素值置为0,相当于裁剪掉,random erasing是用随机数或者数据集中像素的平均值替换原来的像素值。而且,cutout每次裁剪掉的区域大小是固定的,Random erasing替换掉的区域大小是随机的。
* 在warmup之后的训练过程中,学习率不断衰减是一个提高精度的好方法。其中有step decay和cosine decay等,前者是随着epoch增大学习率不断减去一个小的数,后者是让学习率随着训练过程曲线下降。
* Mixup是一种新的数据增强的方法。Mixup training,就是每次取出2张图片,然后将它们线性组合,得到新的图片,以此来作为新的训练样本,进行网络的训练,如下公式,其中x代表图像数据,y代表标签,则得到的新的xhat,yhat。
x
=
λ
⋅
x
i
+
(
1
−
λ
)
⋅
x
j
x= \lambda \cdot x_{\text{i}} + (1 - \lambda) \cdot x_j
x=λ⋅xi+(1−λ)⋅xj
y
=
λ
⋅
y
i
+
(
1
−
λ
)
⋅
y
j
y= \lambda \cdot y_{\text{i}} + (1 - \lambda) \cdot y_j
y=λ⋅yi+(1−λ)⋅yj
* Mixup方法主要增强了训练样本之间的线性表达,增强网络的泛化能力,不过mixup方法需要较长的时间才能收敛得比较好。
* 数据增强在图像分类问题上有很重要的作用,但是增强的方法有很多,并非一股脑地用上所有的方法就是最好的。那么,如何选择最佳的数据增强方法呢?AutoAugment就是一种搜索适合当前问题的数据增强方法的方法。该方法创建一个数据增强策略的搜索空间,利用搜索算法选取适合特定数据集的数据增强策略。此外,从一个数据集中学到的策略能够很好地迁移到其它相似的数据集上。
* Dropout
* L1/L2正则
* Batch Normalization
* Early stopping
* Random cropping
* Mirroring
* Rotation
* Color shifting
* Xavier init
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。