小编给大家分享一下pytorch如何实现查看网络参数显存占用量等操作，希望大家阅读完这篇文章之后都有所收获，下面让我们一起去探讨吧！
1.使用torchstat
pip install torchstat from torchstat import statimport torchvision.models as modelsmodel = models.resnet152()stat(model, (3, 224, 224))关于stat函数的参数，第一个应该是模型，第二个则是输入尺寸，3为通道数。我没有调研该函数的详细参数，也不知道为什么使用的时候并不提示相应的参数。
2.使用torchsummary
pip install torchsummary from torchsummary import summarysummary(model.cuda(),input_size=(3,32,32),batch_size=-1)使用该函数直接对参数进行提示，可以发现直接有显式输入batch_size的地方，我自己的感觉好像该函数更好一些。但是！！！不知道为什么，该函数在我的机器上一直报错！！！
TypeError: can't convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first.
Update：经过论坛咨询，报错的原因找到了，只需要把
pip install torchsummary修改为
pip install torch-summary补充：Pytorch查看模型参数并计算模型参数量与可训练参数量
查看模型参数(以AlexNet为例）
import torchimport torch.nn as nnimport torchvisionclass AlexNet(nn.Module): def __init__(self,num_classes=1000): super(AlexNet,self).__init__() self.feature_extraction = nn.Sequential( nn.Conv2d(in_channels=3,out_channels=96,kernel_size=11,stride=4,padding=2,bias=False), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=3,stride=2,padding=0), nn.Conv2d(in_channels=96,out_channels=192,kernel_size=5,stride=1,padding=2,bias=False), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=3,stride=2,padding=0), nn.Conv2d(in_channels=192,out_channels=384,kernel_size=3,stride=1,padding=1,bias=False), nn.ReLU(inplace=True), nn.Conv2d(in_channels=384,out_channels=256,kernel_size=3,stride=1,padding=1,bias=False), nn.ReLU(inplace=True), nn.Conv2d(in_channels=256,out_channels=256,kernel_size=3,stride=1,padding=1,bias=False), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=3, stride=2, padding=0), ) self.classifier = nn.Sequential( nn.Dropout(p=0.5), nn.Linear(in_features=256*6*6,out_features=4096), nn.ReLU(inplace=True), nn.Dropout(p=0.5), nn.Linear(in_features=4096, out_features=4096), nn.ReLU(inplace=True), nn.Linear(in_features=4096, out_features=num_classes), ) def forward(self,x): x = self.feature_extraction(x) x = x.view(x.size(0),256*6*6) x = self.classifier(x) return xif __name__ =='__main__': # model = torchvision.models.AlexNet() model = AlexNet() # 打印模型参数 #for param in model.parameters(): #print(param) #打印模型名称与shape for name,parameters in model.named_parameters(): print(name,':',parameters.size())feature_extraction.0.weight : torch.Size([96, 3, 11, 11])feature_extraction.3.weight : torch.Size([192, 96, 5, 5])feature_extraction.6.weight : torch.Size([384, 192, 3, 3])feature_extraction.8.weight : torch.Size([256, 384, 3, 3])feature_extraction.10.weight : torch.Size([256, 256, 3, 3])classifier.1.weight : torch.Size([4096, 9216])classifier.1.bias : torch.Size([4096])classifier.4.weight : torch.Size([4096, 4096])classifier.4.bias : torch.Size([4096])classifier.6.weight : torch.Size([1000, 4096])classifier.6.bias : torch.Size([1000])计算参数量与可训练参数量
def get_parameter_number(model): total_num = sum(p.numel() for p in model.parameters()) trainable_num = sum(p.numel() for p in model.parameters() if p.requires_grad) return {'Total': total_num, 'Trainable': trainable_num}第三方工具
from torchstat import statimport torchvision.models as modelsmodel = models.alexnet()stat(model, (3, 224, 224))
from torchvision.models import alexnetimport torchfrom thop import profilemodel = alexnet()input = torch.randn(1, 3, 224, 224)flops, params = profile(model, inputs=(input, ))print(flops, params)
pytorch的优点
1.PyTorch是相当简洁且高效快速的框架；2.设计追求最少的封装；3.设计符合人类思维，它让用户尽可能地专注于实现自己的想法；4.与google的Tensorflow类似，FAIR的支持足以确保PyTorch获得持续的开发更新；5.PyTorch作者亲自维护的论坛 供用户交流和求教问题6.入门简单
看完了这篇文章，相信你对“pytorch如何实现查看网络参数显存占用量等操作”有了一定的了解，如果想了解更多相关知识，欢迎关注编程网行业资讯频道，感谢各位的阅读！
