Pytorch--Dropout笔记

dropout经常用于抑制过拟合，pytorch也提供了很方便的函数。可是常常不知道dropout的参数p是什么意思。在TensorFlow中p叫作keep_prob,就一直觉得pytorch中的p应该就是保留节点数的比例，可是实验结果发现反了，实际上表示的是不保留节点数的比例。看下面的例子：

a = torch.randn(10,1)
>>> tensor([[ 0.0684],
        [-0.2395],
        [ 0.0785],
        [-0.3815],
        [-0.6080],
        [-0.1690],
        [ 1.0285],
        [ 1.1213],
        [ 0.5261],
        [ 1.1664]])

• p=0.5

torch.nn.Dropout(0.5)(a)
>>> tensor([[ 0.0000],  
        [-0.0000],  
        [ 0.0000],  
        [-0.7631],  
        [-0.0000],  
        [-0.0000],  
        [ 0.0000],  
        [ 0.0000],  
        [ 1.0521],  
        [ 2.3328]])

• p=0

torch.nn.Dropout(0)(a)
>>> tensor([[ 0.0684],
        [-0.2395],
        [ 0.0785],
        [-0.3815],
        [-0.6080],
        [-0.1690],
        [ 1.0285],
        [ 1.1213],
        [ 0.5261],
        [ 1.1664]])

• p=1

torch.nn.Dropout(0)(a)
>>> tensor([[0.],  
        [-0.], 
        [0.],  
        [-0.], 
        [-0.], 
        [-0.], 
        [0.],  
        [0.],  
        [0.],  
        [0.]])

MARSGGBO♥原创




2019-3-25