1. 查看PyTorch版本
import torch
print(torch.__version__)
2. 模型参数量
model = FPN()
num_params = sum(p.numel() for p in model.parameters())
print("num of params: {:.2f}k".format(num_params/1000.0))
# torch.numel()返回tensor的元素数目，即number of elements
3. 打印模型
model = FPN()
num_params = sum(p.numel() for p in model.parameters())
print("num of params: {:.2f}k".format(num_params/1000.0))
print("===========================")
#for p in model.parameters():
# print(p.name)
print(model)
4. with torch.no_grad()
5. 激活函数torch.nn.ReLU(inplace=False)
- 官方文档：https://pytorch.org/docs/stable/nn.html#relu
- inplace的作用：https://www.cnblogs.com/wanghui-garcia/p/10642665.html
6. torch.nn.Sequential
7. 模型保存&&加载
https://zhuanlan.zhihu.com/p/76604532
8. 调整学习率 How to adjust learning rate
9. nn.ModuleList
10. detach() 分离，用于切断反向传播
https://www.cnblogs.com/wanghui-garcia/p/10677071.html
11. 二维卷积torch.nn.Conv2d
torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0,
dilation=1, groups=1, bias=True, padding_mode='zeros')
12. torch.nn.Unfold()
13. 打印网络架构
14. 固定模型的部分参数
15. torch.unbind
Removes a tensor dimension
返回一个tuple
16. torch.clamp
- torch.clamp(input, min, max)
- torch.clamp(input, min=MIN)
- torch.clamp(input, max=MAX)