用pytorch加載.pth格式的訓(xùn)練模型

在pytorch/vision/models網(wǎng)頁(yè)上有很多現(xiàn)成的經(jīng)典網(wǎng)絡(luò)模型可以調(diào)用，其中包括alexnet、vgg、googlenet、resnet、inception、densenet、mobilenet等。把模型下載下來(lái)之后，打開(kāi)模型查看網(wǎng)絡(luò)模型里面的具體內(nèi)容內(nèi)容是什么。
以resnet101為例，查看它里面定義了網(wǎng)絡(luò)的哪些參數(shù)。

import torch import torchvision.models as models# squeezenet1_1是一種輕量級(jí)卷積神經(jīng)網(wǎng)絡(luò)模型 net = models.squeezenet1_1(pretrained = False) # 'r'是讀取指令，后面加上訓(xùn)練模型的存放路徑名 checkpoint = r'/home/resnet/resnet101.pth' net.load_state_dict(torch.load(checkpoint)) print('Parameters of resnet101:', net)

有時(shí)候用以上代碼打開(kāi)訓(xùn)練模型的時(shí)候可能會(huì)提示Runtime Error，修改加載模型部分的代碼為

net.load_state_dict(torch.load(checkpoint), False)

可以看到resnet101.pth的定義的模型結(jié)構(gòu)和參數(shù)如下，包括卷積層的卷積核大小、層數(shù)、滑動(dòng)步長(zhǎng)、激活函數(shù)、池化函數(shù)、隨機(jī)失活（dropout）的概率等信息。

Parameters of resnet101: SqueezeNet((features): Sequential((0): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2))(1): ReLU(inplace=True)(2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)(3): Fire((squeeze): Conv2d(64, 16, kernel_size=(1, 1), stride=(1, 1))(squeeze_activation): ReLU(inplace=True)(expand1x1): Conv2d(16, 64, kernel_size=(1, 1), stride=(1, 1))(expand1x1_activation): ReLU(inplace=True)(expand3x3): Conv2d(16, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(expand3x3_activation): ReLU(inplace=True))(4): Fire((squeeze): Conv2d(128, 16, kernel_size=(1, 1), stride=(1, 1))(squeeze_activation): ReLU(inplace=True)(expand1x1): Conv2d(16, 64, kernel_size=(1, 1), stride=(1, 1))(expand1x1_activation): ReLU(inplace=True)(expand3x3): Conv2d(16, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(expand3x3_activation): ReLU(inplace=True))(5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)(6): Fire((squeeze): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1))(squeeze_activation): ReLU(inplace=True)(expand1x1): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1))(expand1x1_activation): ReLU(inplace=True)(expand3x3): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(expand3x3_activation): ReLU(inplace=True))(7): Fire((squeeze): Conv2d(256, 32, kernel_size=(1, 1), stride=(1, 1))(squeeze_activation): ReLU(inplace=True)(expand1x1): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1))(expand1x1_activation): ReLU(inplace=True)(expand3x3): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(expand3x3_activation): ReLU(inplace=True))(8): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=True)(9): Fire((squeeze): Conv2d(256, 48, kernel_size=(1, 1), stride=(1, 1))(squeeze_activation): ReLU(inplace=True)(expand1x1): Conv2d(48, 192, kernel_size=(1, 1), stride=(1, 1))(expand1x1_activation): ReLU(inplace=True)(expand3x3): Conv2d(48, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(expand3x3_activation): ReLU(inplace=True))(10): Fire((squeeze): Conv2d(384, 48, kernel_size=(1, 1), stride=(1, 1))(squeeze_activation): ReLU(inplace=True)(expand1x1): Conv2d(48, 192, kernel_size=(1, 1), stride=(1, 1))(expand1x1_activation): ReLU(inplace=True)(expand3x3): Conv2d(48, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(expand3x3_activation): ReLU(inplace=True))(11): Fire((squeeze): Conv2d(384, 64, kernel_size=(1, 1), stride=(1, 1))(squeeze_activation): ReLU(inplace=True)(expand1x1): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1))(expand1x1_activation): ReLU(inplace=True)(expand3x3): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(expand3x3_activation): ReLU(inplace=True))(12): Fire((squeeze): Conv2d(512, 64, kernel_size=(1, 1), stride=(1, 1))(squeeze_activation): ReLU(inplace=True)(expand1x1): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1))(expand1x1_activation): ReLU(inplace=True)(expand3x3): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(expand3x3_activation): ReLU(inplace=True)))(classifier): Sequential((0): Dropout(p=0.5, inplace=False)(1): Conv2d(512, 1000, kernel_size=(1, 1), stride=(1, 1))(2): ReLU(inplace=True)(3): AdaptiveAvgPool2d(output_size=(1, 1))) )

總結(jié)

以上是生活随笔為你收集整理的用pytorch加载训练模型的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

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