首页model = models.resnet18(pretrained=False) model.fc = torch.nn.Linear(512, ???)

model = models.resnet18(pretrained=False) model.fc = torch.nn.Linear(512, ???)

时间: 2023-06-24 08:07:35 浏览: 195

关于PyTorch源码解读之torchvision.models

5星 · 资源好评率100%

PyTorch框架中有一个非常重要且好用的包：torchvision，该包主要由3个子包组成，分别是：torchvision.datasets、torchvision.models、torchvision.transforms。这3个子包的具体介绍可以参考官网： http://pytorch.org/docs/master/torchvision/index.html。具体代码可以参考github： https://github.com/pytorch/vision/tree/master/torchvision。这篇博客介绍torchvision.models。torchvision.

The number of output units in the `torch.nn.Linear` layer depends on the number of classes in your classification task. For example, if you have 10 classes, you would set the number of output units to 10: ``` model.fc = torch.nn.Linear(512, 10) ``` If you have a binary classification task, you would set the number of output units to 1: ``` model.fc = torch.nn.Linear(512, 1) ``` If you're doing regression instead of classification, you would set the number of output units to 1 (assuming you're predicting a single continuous value): ``` model.fc = torch.nn.Linear(512, 1) ```

阅读全文