恒源云 (Gpushare)_ 今日炼丹小疑问：如何给数据加权重？

import numpy as npimport torchfrom torch.utils.data import WeightedRandomSamplerfrom torch.utils.data import DataLoaderfrom torch.utils.data import TensorDataset

# 假设是一个三分类的问题，每一类的样本数分别为 10，1000，3000class_counts = np.array([10, 1000, 3000])#  样本总数n_samples = class_counts.sum() # 4010# 标签labels = []for i in range(len(class_counts)):    labels.extend([i]*class_counts[i])
Y = torch.from_numpy(np.array(labels, dtype=np.int64))# 随机生成一些数据，不重要X = torch.randn(n_samples)

# 给每一类一个权重class_weights = [n_samples/class_counts[i] for i in range(len(class_counts))]# [401.0, 4.01, 1.3367]# 对每个样本生成权重weights = [class_weights[i] for i in labels]

train_dataset = TensorDataset(X, Y)sampler =  WeightedRandomSampler(weights, int(n_samples),replacement=True)

train_loader = DataLoader(train_dataset, batch_size=1024,sampler=sampler, drop_last=True)
for i, (x,y) in enumerate(train_loader):    print(f"batch index {i}, n_0: {(y==0).sum()}, n_1: {(y==1).sum()}, n_2: {(y==3).sum()}")# output:# 第一个batch，每类的数量分别为 349, 344, 331# 第二个batch，每类的数量分别为 344, 360, 320# 第三个batch，每类的数量分别为 339, 348, 337

sampler =  WeightedRandomSampler(weights, int(num_samples),replacement=False)
train_loader = DataLoader(train_dataset, batch_size=1024,sampler=sampler, drop_last=True)
for i, (x,y) in enumerate(train_loader):    print(f"batch index {i}, n_0: {(y==0).sum()}, n_1: {(y==1).sum()}, n_2: {(y==3).sum()}")# output:# 第一个batch，每类的数量分别为 10, 466, 548# 第二个batch，每类的数量分别为 0, 333, 691# 第三个batch，每类的数量分别为 0, 173, 851

train_loader = DataLoader(train_dataset, batch_size=20,shuffle=True, drop_last=True)
for i, (x,y) in enumerate(train_loader):    print(f"batch index {i}, n_0: {(y==0).sum()}, n_1: {(y==1).sum()}, n_2: {(y==3).sum()}")# output:# 第一个batch，每类的数量分别为 0, 227, 797# 第二个batch，每类的数量分别为 1, 271, 752# 第三个batch，每类的数量分别为 6, 257, 761