nn.Linear(输入数据的形状,输出数据的形状,bias默认是True)
torch.randn(*sizes, out=None) → Tensor
是从标准正态分布中随机选取的size大小的噪声, 噪声的形状=size. 例如:
torch.randn(2, 3)
0.5419 0.1594 -0.0413
-2.7937 0.9534 0.4561
[torch.FloatTensor of size 2x3]
全连接层如何使用
import torch as t
from torch import nn
# in_features由输入张量的形状决定,out_features则决定了输出张量的形状
connected_layer = nn.Linear(in_features = 64*64*3, out_features = 1) # [12288,1]
print(connected_layer)
# Linear(in_features=12288, out_features=1, bias=True)
print(dir(connected_layer)) # dir(a)用来查看a都有哪些属性和方法
# ['__call__', '__class__', '__constants__', '__delattr__', '__dict