pytorch处理类别不平衡问题

访问本站观看效果更佳
当训练样本不均匀时，我们可以采用过采样、欠采样、数据增强等手段来避免过拟合。今天遇到一个3d点云数据集合，样本分布极不均匀，正例与负例相差4-5个数量级。数据增强效果就不会太好了，另外过采样也不太合适，因为是空间数据，新增的点有可能会对真实分布产生未知影响。所以采用欠采样来缓解类别不平衡的问题。
下面的代码展示了如何使用WeightedRandomSampler来完成抽样。

numDataPoints = 1000
data_dim = 5
bs = 100

# Create dummy data with class imbalance 9 to 1
data = torch.FloatTensor(numDataPoints, data_dim)
target = np.hstack((np.zeros(int(numDataPoints * 0.9), dtype=np.int32),
                    np.ones(int(numDataPoints * 0.1), dtype=np.int32)))

print 'target train 0/1: {}/{}'.format(
    len(np.where(target == 0)[0]), len(np.where(target == 1)[0]))

class_sample_count = np.array(
    [len(np.where(target == t)[0]) for t in np.unique(target)])
weight = 1. / class_sample_count
samples_weight = np.array([weight[t] for t in target])

samples_weight = torch.from_numpy(samples_weight)
samples_weight = samples_weight.double()
sampler = WeightedRandomSampler(samples_weight, len(samples_weight))

target = torch.from_numpy(target).long()
train_dataset = torch.utils.data.TensorDataset(data, target)

train_loader = DataLoader(
    train_dataset, batch_size=bs, num_workers=1, sampler=sampler)

for i, (data, target) in enumerate(train_loader):
    print "batch index {}, 0/1: {}/{}".format(
        i,
        len(np.where(target.numpy() == 0)[0]),
        len(np.where(target.numpy() == 1)[0]))

核心部分为实际使用时替换下变量把sampler传递给DataLoader即可，注意使用了sampler就不能使用shuffle，另外需要指定采样点个数：

class_sample_count = np.array(
    [len(np.where(target == t)[0]) for t in np.unique(target)])
weight = 1. / class_sample_count
samples_weight = np.array([weight[t] for t in target])

samples_weight = torch.from_numpy(samples_weight)
samples_weight = samples_weight.double()
sampler = WeightedRandomSampler(samples_weight, len(samples_weight))

参考