深度学习 DataLoader与enumerate()

1.enumerate()使用

import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt


x_train = [[1, 2, 3], [3, 4, 5], [5, 6, 7]]
y_train = [1, 2, 3]
mm = zip(x_train, y_train)
print(list(mm))
db = zip(x_train, y_train)

for step, (x_train, y_train) in enumerate(db):
    print(step, x_train, y_train, sep='\t')  

2.dataloader实列

批训练

import torch
import torch.utils.data as Data
torch.manual_seed(1)    # reproducible
 
BATCH_SIZE = 5      # 批训练的数据个数
 
x = torch.linspace(1, 10, 10)       # x data (torch tensor)
y = torch.linspace(10, 1, 10)       # y data (torch tensor)
 
# 先转换成 torch 能识别的 Dataset
torch_dataset = Data.TensorDataset(data_tensor=x, target_tensor=y)
 
# 把 dataset 放入 DataLoader
loader = Data.DataLoader(
    dataset=torch_dataset,      # torch TensorDataset format
    batch_size=BATCH_SIZE,      # mini batch size
    shuffle=True,               # 要不要打乱数据 (打乱比较好)
    num_workers=2,              # 多线程来读数据
)
 
for epoch in range(3):   # 训练所有!整套!数据 3 次
    for step, (batch_x, batch_y) in enumerate(loader):  # 每一步 loader 释放一小批数据用来学习
        # 假设这里就是你训练的地方...
 
        # 打出来一些数据
        print('Epoch: ', epoch, '| Step: ', step, '| batch x: ',
              batch_x.numpy(), '| batch y: ', batch_y.numpy())