Spaces:
Sleeping
Sleeping
File size: 4,472 Bytes
749745d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 |
import torch
import torch.nn.functional as F
from torch import nn
class DropBlock2D(nn.Module):
r"""Randomly zeroes 2D spatial blocks of the input tensor.
As described in the paper
`DropBlock: A regularization method for convolutional networks`_ ,
dropping whole blocks of feature map allows to remove semantic
information as compared to regular dropout.
Args:
drop_prob (float): probability of an element to be dropped.
block_size (int): size of the block to drop
Shape:
- Input: `(N, C, H, W)`
- Output: `(N, C, H, W)`
.. _DropBlock: A regularization method for convolutional networks:
https://arxiv.org/abs/1810.12890
"""
def __init__(self, drop_prob, block_size):
super(DropBlock2D, self).__init__()
self.drop_prob = drop_prob
self.block_size = block_size
def forward(self, x):
# shape: (bsize, channels, height, width)
assert x.dim() == 4, "Expected input with 4 dimensions (bsize, channels, height, width)"
if not self.training or self.drop_prob == 0.0:
return x
else:
# get gamma value
gamma = self._compute_gamma(x)
# sample mask
mask = (torch.rand(x.shape[0], *x.shape[2:]) < gamma).float()
# place mask on input device
mask = mask.to(x.device)
# compute block mask
block_mask = self._compute_block_mask(mask)
# apply block mask
out = x * block_mask[:, None, :, :]
# scale output
out = out * block_mask.numel() / block_mask.sum()
return out
def _compute_block_mask(self, mask):
block_mask = F.max_pool2d(
input=mask[:, None, :, :],
kernel_size=(self.block_size, self.block_size),
stride=(1, 1),
padding=self.block_size // 2,
)
if self.block_size % 2 == 0:
block_mask = block_mask[:, :, :-1, :-1]
block_mask = 1 - block_mask.squeeze(1)
return block_mask
def _compute_gamma(self, x):
return self.drop_prob / (self.block_size**2)
class DropBlock3D(DropBlock2D):
r"""Randomly zeroes 3D spatial blocks of the input tensor.
An extension to the concept described in the paper
`DropBlock: A regularization method for convolutional networks`_ ,
dropping whole blocks of feature map allows to remove semantic
information as compared to regular dropout.
Args:
drop_prob (float): probability of an element to be dropped.
block_size (int): size of the block to drop
Shape:
- Input: `(N, C, D, H, W)`
- Output: `(N, C, D, H, W)`
.. _DropBlock: A regularization method for convolutional networks:
https://arxiv.org/abs/1810.12890
"""
def __init__(self, drop_prob, block_size):
super(DropBlock3D, self).__init__(drop_prob, block_size)
def forward(self, x):
# shape: (bsize, channels, depth, height, width)
assert x.dim() == 5, "Expected input with 5 dimensions (bsize, channels, depth, height, width)"
if not self.training or self.drop_prob == 0.0:
return x
else:
# get gamma value
gamma = self._compute_gamma(x)
# sample mask
mask = (torch.rand(x.shape[0], *x.shape[2:]) < gamma).float()
# place mask on input device
mask = mask.to(x.device)
# compute block mask
block_mask = self._compute_block_mask(mask)
# apply block mask
out = x * block_mask[:, None, :, :, :]
# scale output
out = out * block_mask.numel() / block_mask.sum()
return out
def _compute_block_mask(self, mask):
block_mask = F.max_pool3d(
input=mask[:, None, :, :, :],
kernel_size=(self.block_size, self.block_size, self.block_size),
stride=(1, 1, 1),
padding=self.block_size // 2,
)
if self.block_size % 2 == 0:
block_mask = block_mask[:, :, :-1, :-1, :-1]
block_mask = 1 - block_mask.squeeze(1)
return block_mask
def _compute_gamma(self, x):
return self.drop_prob / (self.block_size**3)
|