sat類似資料增強
對抗樣本的定義：以影象樣本為例,在原樣本上加入一些輕微的擾動，使得在人眼分辨不出差別的情況下，誘導模型進行錯誤分類。
如圖所示，input（panda影象）+ 噪音點 = output（誤判為gibbon影象）
github：
根據**結果可知，在coco資料集上可以將準確率提高1.6%
# **實現
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 *****
`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:
"""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.:
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)
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 *****
`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:
"""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.:
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)
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)
Yolov4煙火檢測
作者開源的資料集 以上資料集包含煙霧影象，但是標註只有1類 開源模型只有fire類，如果要同時檢測煙霧，需要自己在影象上標註煙霧類別。採用yolov5煙霧 火災2類檢測模型，為自己的資料預標註，然後修正即可！煙火檢測資料集包含的場景型別 大火 小火，建築 草原 森林 車輛 汽車 卡車 電單車 電動車...
YOLOv4閱讀筆記
中英對照翻譯參考 中首先總結了目標檢測的一般性結構 通常，傳統的目標檢測器是離線訓練的。因此，研究人員總是喜歡利用這一優勢，開發更好的訓練方法，使目標檢測器在不增加推理成本的情況下獲得更好的精度。我們將這些方法稱為 bag of freebies 這些方法僅改變訓練策略或僅增加訓練成本。資料擴充 資...
YOLOv4學習資源
redmon寫完yolov3，退出計算機視覺領域之後，又有其他大佬推動著這一目標檢測神器的發展。yolov4我沒有看原 而是找了一些部落格資源進行學習，現在把我找到的部落格資源分享在此。看完這些部落格之後，yolov4其實並沒有引入特別創新的idea，作者的目標就是為了設計乙個用於實際工作環境的快速...