pytorch SubsetRandomSampler 用法和说明

官网：https://pytorch.org/docs/stable/data.html?highlight=subsetrandomsampler#torch.utils.data.SubsetRandomSampler

推荐参考：https://www.sohu.com/a/291959747_197042

https://www.jianshu.com/p/a32ae0294223

https://www.cnblogs.com/marsggbo/p/10496696.html

理解一下：

DataLoader其实就是先根据sampler方法先采样，再切分出batch（比如样本有10个，SubsetRandomSampler返回一个下标，比如0到7，那么取出这8个数据，然后按照batch_size切分出一个个的batch）

实际应用：

from torch.utils.data import DataLoader
from torch.utils.data import sampler

train_data = CriteoDataset('./data', train=True) #自己定义

split_num = int(len(train_data) * 0.8)
index_list = list(range(len(train_data)))
train_idx, valid_idx = index_list[:split_num], index_list[split_num:]

tr_sampler = sampler.SubsetRandomSampler(train_idx)
val_sampler = sampler.SubsetRandomSampler(valid_idx)

loader_train = DataLoader(train_data, batch_size=100,
                          sampler=tr_sampler)

loader_val = DataLoader(val_data, batch_size=100,
                        sampler=val_sampler)