DecafTea的博客

enumerate(sequence, [start=0])参数：sequence – 一个序列、迭代器或其他支持迭代对象。start – 下标起始位置。返回值：列出数据和数据下标，一般用在 for 循环当中。for i, data in enumerate(train_loader): inputs, labels = data print(inputs,shape) print(labels.shape) break# print output: # torch.Size([.

# view() 转换维度# reshape() 转换维度# permute() 坐标系变换# squeeze()/unsqueeze() 降维/升维# expand() 扩张张量# narraw() 缩小张量# resize_() 重设尺寸# repeat(), unfold() 重复张量# cat(), stack() 拼接张量文章链接：https://blog.csdn.net/x_yan033/article/details/104965077有详细总结

import numpy as npimport matplotlib.pyplot as pltfrom torch import nn, optimfrom torch.autograd import Variableimport torchx_data = np.random.rand(100)noise = np.random.normal(0, 0.01, x_data.shape)y_data = x_data * 0.1 + 0.2 + noiseplt.scatter(x

1. 简介torch.nn.Module类pytorch里面一切自定义操作基本上都是继承nn.Module类来实现的，本文仅仅先讨论使用Module来实现自定义模块，自定义层先不做讨论。class Module(object): def __init__(self): def forward(self, *input): def add_module(self, name, module): def cuda(self, device=None): def c