斯坦福cs231n课程记录——assignment2 Dropout

最新推荐文章于 2020-08-24 14:16:36 发布

原创

最新推荐文章于 2020-08-24 14:16:36 发布 · 1.1k 阅读

6 ·

CC 4.0 BY-SA版权

文章标签：

#Dropout

一、Dropout原理

作用：regularize neural networks by randomly setting some features to zero during the forward pass.

二、Dropout实现

1.dropout_forward

def dropout_forward(x, dropout_param):
    p, mode = dropout_param['p'], dropout_param['mode']
    if 'seed' in dropout_param:
        np.random.seed(dropout_param['seed'])
    mask = None
    out = None
    if mode == 'train':
        mask = (np.random.rand(*x.shape) < p) / p
        out = x * mask
    elif mode == 'test':
        out = x
    cache = (dropout_param, mask)
    out = out.astype(x.dtype, copy=False)

    return out, cache

2.dropout_backward