Pytorch教程內置模型源碼實現
翻譯自
https://pytorch.org/docs/stable/torchvision/models.html
主要講解瞭torchvision.models的使用
torchvision.models
torchvision.models中包含瞭如下模型
- AlexNet
- VGG
- ResNet
- SqueezeNet
- DenseNet
- Inception v3
隨機初始化模型
import torchvision.models as models resnet18 = models.resnet18() alexnet = models.alexnet() vgg16 = models.vgg16() squeezenet = models.squeezenet1_0() desnet = models.densenet161() inception =models.inception_v3()
使用預訓練好的參數
pytorch提供瞭預訓練的模型,使用torch.utils.model_zoo ,通過讓參數pretrained =True來構建訓練好的模型
方法如下
resnet18 = models.resnet18(pretrained=True) alexnet = models.alexnet(pretrained=True) squeezenet = models.squeezenet1_0(pretrained=True) vgg16 = models.vgg16(pretrained=True) densenet = models.densenet161(pretrained=True) inception = models.inception_v3(pretrained=True)
實例化一個預訓練好的模型會自動下載權重到緩存目錄,這個權重存儲路徑可以通過環境變量TORCH_MODEL_ZOO來指定,詳細的參考torch.utils.model_zoo.load_url() 這個函數
有的模型試驗瞭不同的訓練和評估,例如batch normalization。使用model.train()和model.eval()來轉換,查看train() or eval() 來瞭解更多細節
所有的預訓練網絡希望使用相同的方式進行歸一化,例如圖片是mini-batch形式的3通道RGB圖片(3HW),H和W最少是244,。 圖像必須加載到[0,1]范圍內,然後使用均值=[0.485,0.456,0.406]和std =[0.229, 0.224, 0.225]進行歸一化。
您可以使用以下轉換來normalzie:
normalize = trainform.Normalize9mean = [0.485,0.456,0.406],std = [0.229,0.224,0.225])
在這裡我們可以找到一個在Imagenet上的這樣的例子
https://github.com/pytorch/examples/blob/42e5b996718797e45c46a25c55b031e6768f8440/imagenet/main.py#L89-L101
目前這些模型的效果如下
下面是模型源碼的具體實現,具體實現大傢可以閱讀源碼
###ALEXNET torchvision.models.alexnet(pretrained=False, **kwargs)[SOURCE] AlexNet model architecture from the “One weird trick…” paper. Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet ###VGG torchvision.models.vgg11(pretrained=False, **kwargs)[SOURCE] VGG 11-layer model (configuration “A”) Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet torchvision.models.vgg11_bn(pretrained=False, **kwargs)[SOURCE] VGG 11-layer model (configuration “A”) with batch normalization Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet torchvision.models.vgg13(pretrained=False, **kwargs)[SOURCE] VGG 13-layer model (configuration “B”) Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet torchvision.models.vgg13_bn(pretrained=False, **kwargs)[SOURCE] VGG 13-layer model (configuration “B”) with batch normalization Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet torchvision.models.vgg16(pretrained=False, **kwargs)[SOURCE] VGG 16-layer model (configuration “D”) Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet torchvision.models.vgg16_bn(pretrained=False, **kwargs)[SOURCE] VGG 16-layer model (configuration “D”) with batch normalization Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet torchvision.models.vgg19(pretrained=False, **kwargs)[SOURCE] VGG 19-layer model (configuration “E”) Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet torchvision.models.vgg19_bn(pretrained=False, **kwargs)[SOURCE] VGG 19-layer model (configuration ‘E') with batch normalization Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet RESNET torchvision.models.resnet18(pretrained=False, **kwargs)[SOURCE] Constructs a ResNet-18 model. Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet torchvision.models.resnet34(pretrained=False, **kwargs)[SOURCE] Constructs a ResNet-34 model. Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet torchvision.models.resnet50(pretrained=False, **kwargs)[SOURCE] Constructs a ResNet-50 model. Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet torchvision.models.resnet101(pretrained=False, **kwargs)[SOURCE] Constructs a ResNet-101 model. Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet torchvision.models.resnet152(pretrained=False, **kwargs)[SOURCE] Constructs a ResNet-152 model. Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet SQUEEZENET torchvision.models.squeezenet1_0(pretrained=False, **kwargs)[SOURCE] SqueezeNet model architecture from the “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size” paper. Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet torchvision.models.squeezenet1_1(pretrained=False, **kwargs)[SOURCE] SqueezeNet 1.1 model from the official SqueezeNet repo. SqueezeNet 1.1 has 2.4x less computation and slightly fewer parameters than SqueezeNet 1.0, without sacrificing accuracy. Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet DENSENET torchvision.models.densenet121(pretrained=False, **kwargs)[SOURCE] Densenet-121 model from “Densely Connected Convolutional Networks” Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet torchvision.models.densenet169(pretrained=False, **kwargs)[SOURCE] Densenet-169 model from “Densely Connected Convolutional Networks” Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet torchvision.models.densenet161(pretrained=False, **kwargs)[SOURCE] Densenet-161 model from “Densely Connected Convolutional Networks” Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet torchvision.models.densenet201(pretrained=False, **kwargs)[SOURCE] Densenet-201 model from “Densely Connected Convolutional Networks” Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet INCEPTION V3 torchvision.models.inception_v3(pretrained=False, **kwargs)[SOURCE] Inception v3 model architecture from “Rethinking the Inception Architecture for Computer Vision”. Parameters: pretrained (bool) – If True, returns a model pre-trained on ImageNet
以上就是Pytorch教程內置模型源碼實現的詳細內容,更多關於Pytorch內置模型的資料請關註WalkonNet其它相關文章!
推薦閱讀:
- pytorch 預訓練模型讀取修改相關參數的填坑問題
- Pytorch模型遷移和遷移學習,導入部分模型參數的操作
- pytorch加載預訓練模型與自己模型不匹配的解決方案
- pytorch 實現凍結部分參數訓練另一部分
- pytorch 一行代碼查看網絡參數總量的實現