pytorch實現focal loss的兩種方式

import torch

import torch.nn.functional as f
import numpy as np
from torch.autograd import variable
'''pytorch實現focal loss的兩種方式(現在討論的是基於分割任務)
在計算損失函式的過程中考慮到類別不平衡的問題，假設加上背景類別共有6個類別
'''def compute_class_weights(histogram):
classweights = np.ones(6, dtype=np.float32)
normhist = histogram / np.sum(histogram)
for i in range(6):
classweights[i] = 1 / (np.log(1.10 + normhist[i]))
return classweights
def focal_loss_my(input,target):
''':param input: shape [batch_size,num_classes,h,w] 僅僅經過卷積操作後的輸出，並沒有經過任何啟用函式的作用
:param target: shape [batch_size,h,w]
:return:
'''n, c, h, w = input.size()
target = target.long()
input = input.transpose(1, 2).transpose(2, 3).contiguous().view(-1, c)
target = target.contiguous().view(-1)
number_0 = torch.sum(target == 0).item()
number_1 = torch.sum(target == 1).item()
number_2 = torch.sum(target == 2).item()
number_3 = torch.sum(target == 3).item()
number_4 = torch.sum(target == 4).item()
number_5 = torch.sum(target == 5).item()
frequency = torch.tensor((number_0, number_1, number_2, number_3, number_4, number_5), dtype=torch.float32)
frequency = frequency.numpy()
classweights = compute_class_weights(frequency)
'''根據當前給出的ground truth label計算出每個類別所佔據的權重
'''# weights=torch.from_numpy(classweights).float().cuda()
weights = torch.from_numpy(classweights).float()
focal_frequency = f.nll_loss(f.softmax(input, dim=1), target, reduction='none')
'''上面一篇博文講過
f.nll_loss(torch.log(f.softmax(inputs, dim=1)，target)的函式功能與f.cross_entropy相同
可見f.nll_loss中實現了對於target的one-hot encoding編碼功能，將其編碼成與input shape相同的tensor
然後與前面那一項（即f.nll_loss輸入的第一項）進行 element-wise production
相當於取出了 log(p_gt)即當前樣本點被分類為正確類別的概率
現在去掉取log的操作，相當於 focal_frequency shape [num_samples]
即取出ground truth類別的概率數值，並取了負號
'''focal_frequency += 1.0#shape [num_samples] 1-p（gt_classes）
focal_frequency = torch.pow(focal_frequency, 2) # torch.size([75])
focal_frequency = focal_frequency.repeat(c, 1)
'''進行repeat操作後，focal_frequency shape [num_classes,num_samples]
'''focal_frequency = focal_frequency.transpose(1, 0)
loss = f.nll_loss(focal_frequency * (torch.log(f.softmax(input, dim=1))), target, weight=none,
reduction='elementwise_mean')
return loss
def focal_loss_zhihu(input, target):
''':param input: 使用知乎上面大神給出的方案 
:param target:
:return:
'''n, c, h, w = input.size()
target = target.long()
inputs = input.transpose(1, 2).transpose(2, 3).contiguous().view(-1, c)
target = target.contiguous().view(-1)
n = inputs.size(0)
c = inputs.size(1)
number_0 = torch.sum(target == 0).item()
number_1 = torch.sum(target == 1).item()
number_2 = torch.sum(target == 2).item()
number_3 = torch.sum(target == 3).item()
number_4 = torch.sum(target == 4).item()
number_5 = torch.sum(target == 5).item()
frequency = torch.tensor((number_0, number_1, number_2, number_3, number_4, number_5), dtype=torch.float32)
frequency = frequency.numpy()
classweights = compute_class_weights(frequency)
weights = torch.from_numpy(classweights).float()
weights=weights[target.view(-1)]#這行**非常重要
gamma = 2
p = f.softmax(inputs, dim=1)#shape [num_samples,num_classes]
class_mask = inputs.data.new(n, c).fill_(0)
class_mask = variable(class_mask)
ids = target.view(-1, 1)
class_mask.scatter_(1, ids.data, 1.)#shape [num_samples,num_classes] one-hot encoding
probs = (p * class_mask).sum(1).view(-1, 1)#shape [num_samples,]
log_p = probs.log()
print('in calculating batch_loss',weights.shape,probs.shape,log_p.shape)
# batch_loss = -weights * (torch.pow((1 - probs), gamma)) * log_p
batch_loss = -(torch.pow((1 - probs), gamma)) * log_p
print(batch_loss.shape)
loss = batch_loss.mean()
return loss
if __name__=='__main__':
pred=torch.rand((2,6,5,5))
y=torch.from_numpy(np.random.randint(0,6,(2,5,5)))
loss1=focal_loss_my(pred,y)
loss2=focal_loss_zhihu(pred,y)
print('loss1',loss1)
print('loss2', loss2)
'''in calculating batch_loss torch.size([50]) torch.size([50, 1]) torch.size([50, 1])
torch.size([50, 1])
loss1 tensor(1.3166)
loss2 tensor(1.3166)
'''

Pytorch 通過pytorch實現線性回歸

linear regression 線性回歸是分析乙個變數與另外乙個 多個 變數之間關係的方法 因變數 y 自變數 x 關係 線性 y wx b 分析 求解w，b 求解步驟 1.確定模型 2.選擇損失函式 3.求解梯度並更新w，b 此題 1.model y wx b 下為 實現 import tor...

pytorch實現分類

完整 實現分類 import torch import torch.nn.functional as f from torch.autograd import variable import matplotlib.pyplot as plt import torch.optim as optim 生...

pytorch 實現多層網路

import torch import torch.nn as nn import torch.nn.init as init import torch.nn.functional as f import math 讀取資料集 pima indians diabetes資料集 import pand...