SppNet 多尺度訓練

?

原理網(wǎng)上非常多了，這里不再贅述。

感覺我看了很多博客，對我?guī)椭^大的兩個是：

https://blog.csdn.net/qq_42052229/article/details/90446073

https://zhuanlan.zhihu.com/p/42732128

?

使用過程中的重點總結(jié)：

?

1、網(wǎng)絡(luò)目的確實是解決input的圖像size大小不同的問題，

但是：

訓練的時候，我們需要一個batch一個batch的訓練，這每一個batch的維度是相同的，意味著，這一個batch內(nèi)的圖像input size是相同的，才能訓練。除非我們一張一張的訓練，這樣就會帶來其他的很多問題。

所以在訓練的時候，往往采用幾種不同尺度的size的input，對同一個網(wǎng)絡(luò)分別進行訓練。

而測試時候，因為一般是一張一張的，所以可以任意size的圖像input。

?

2、使用自適應卷積一樣可以。

?

3、代碼拆解，不一定要按照網(wǎng)上人家的來，最后全連接數(shù)量自己可以任意調(diào)整。

?

4、例子pytorch：

多尺度訓練：不同尺度size分別跑一個epoch

if __name__ == '__main__':train_loader_350, test_loader_350 = load(350)train_loader_400, test_loader_400 = load(400)train_loader_450, test_loader_450 = load(450)train_loader_500, test_loader_500 = load(500)train_loaders = [train_loader_350, train_loader_400, train_loader_450, train_loader_500]test_loaders = [test_loader_350, test_loader_400, test_loader_450, test_loader_500]model = SPPNet().to(device)optimizer = optim.Adam(model.parameters(), lr=0.0001, betas=(0.9, 0.99))criterion = nn.CrossEntropyLoss()for epoch in range(1, EPOCH + 1):for train_loader, test_loader in zip(train_loaders, test_loaders):train(model, device, train_loader, criterion, optimizer, epoch)test(model, device, test_loader, criterion, epoch)torch.save(model, save_path)

resnet+sppnet，或者 自適應卷積

import torch from torch import nn from torchvision import models import torch.nn.functional as F import os, math from torch.nn.modules.pooling import AdaptiveAvgPool2d, AdaptiveMaxPool2dclass ResNet(nn.Module):def __init__(self, layers=18, num_class=2, pretrained=True):super(ResNet, self).__init__()if layers == 18:self.resnet = models.resnet18(pretrained=pretrained)elif layers == 34:self.resnet = models.resnet34(pretrained=pretrained)elif layers == 50:self.resnet = models.resnet50(pretrained=pretrained)elif layers == 101:self.resnet = models.resnet101(pretrained=pretrained)elif layers == 152:self.resnet = models.resnet152(pretrained=pretrained)else:raise ValueError('layers should be 18, 34, 50, 101.')self.num_class = num_classif layers in [18, 34]:self.fc = nn.Linear(512, num_class)if layers in [50, 101, 152]:self.fc = nn.Linear(512 * 4, num_class)def conv_base(self, x):x = self.resnet.conv1(x)x = self.resnet.bn1(x)x = self.resnet.relu(x)x = self.resnet.maxpool(x)layer1 = self.resnet.layer1(x)layer2 = self.resnet.layer2(layer1)layer3 = self.resnet.layer3(layer2)layer4 = self.resnet.layer4(layer3)return layer1, layer2, layer3, layer4def forward(self, x):layer1, layer2, layer3, layer4 = self.conv_base(x)x = self.resnet.avgpool(layer4)x = x.view(x.size(0), -1)x = self.fc(x)return xclass SPPNet(nn.Module):def __init__(self, backbone=101, num_class=2, pool_size=(1, 2, 6), pretrained=True):# Only resnet is supported in this versionsuper(SPPNet, self).__init__()if backbone in [18, 34, 50, 101, 152]:self.resnet = ResNet(backbone, num_class, pretrained)else:raise ValueError('Resnet{} is not supported yet.'.format(backbone))if backbone in [18, 34]:self.c = 512if backbone in [50, 101, 152]:self.c = 2048self.spp = SpatialPyramidPool2D(out_side=pool_size)num_features = self.c * (pool_size[0] ** 2 + pool_size[1] ** 2 + pool_size[2] ** 2)self.classifier = nn.Linear(num_features, num_class)def forward(self, x):_, _, _, x = self.resnet.conv_base(x)x = self.spp(x)x = self.classifier(x)return xclass SpatialPyramidPool2D(nn.Module):"""Args:out_side (tuple): Length of side in the pooling results of each pyramid layer.Inputs:- `input`: the input Tensor to invert ([batch, channel, width, height])"""def __init__(self, out_side):super(SpatialPyramidPool2D, self).__init__()self.out_side = out_sidedef forward(self, x):# batch_size, c, h, w = x.size()out = Nonefor n in self.out_side: # w_r, h_r = map(lambda s: math.ceil(s / n), x.size()[2:]) # Receptive Field Size # s_w, s_h = map(lambda s: math.floor(s / n), x.size()[2:]) # Stride # max_pool = nn.MaxPool2d(kernel_size=(w_r, h_r), stride=(s_w, s_h))max_pool = AdaptiveMaxPool2d(output_size=(n, n))y = max_pool(x)if out is None:out = y.view(y.size()[0], -1)else:out = torch.cat((out, y.view(y.size()[0], -1)), 1)return out

code源地址：

https://github.com/mmmmmmiracle/SPPNet/blob/master/multi.py

https://github.com/stanleykao72/Deepfake-Detector/blob/934749da71ae31f6e689f2ca2e015cd3e2d5c50a/py_utils/DL/sppnet/models/classifier.py

?

總結(jié)

以上是生活随笔為你收集整理的SppNet 多尺度训练的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。