正则化方法之DropBlock

参考：https://blog.csdn.net/qq_14845119/article/details/85103503

正则化方法之DropBlock

论文：

DropBlock: A regularization method for convolutional networks 

Github：

https://github.com/miguelvr/dropblock

Install directly from PyPI:

pip install dropblock

or the bleeding edge version from github:

pip install git+https://github.com/miguelvr/dropblock.git#egg=dropblock

NOTE: Implementation and tests were done in Python 3.6, if you have problems with other versions of python please open an issue.

Usage

For 2D inputs (DropBlock2D):

import torch
from dropblock import DropBlock2D

# (bsize, n_feats, height, width)
x = torch.rand(100, 10, 16, 16)

drop_block = DropBlock2D(block_size=3, drop_prob=0.3)
regularized_x = drop_b