蜡笔小金QAQ的个人主页

封面：电影《Top Gun》(《壮志凌云》1986) 男主 "MAVERICK"(“独行侠”，汤姆克鲁斯 饰)，那时候的阿汤哥真年轻......

封面：Bing每日壁纸：The Needles sea stacks

封面：史蒂文·斯皮尔伯格，好莱坞导演。 代表作：《拯救大兵瑞恩》，《夺宝奇兵》，《侏罗纪公园》，《辛德勒的名单》等

NIN网络结构 代码实现1234567891011import torchfrom torch import nnfrom d2l import torch as d2ldef nin_block(in_channels, out_channels, kernel_size, strides, padding): return nn.Sequential( nn.Conv2d(in_channels, out_channels, kernel_size, strides, padding), nn.ReLU(), nn.Conv2d(out_channels, out_channels, kernel_size=1), nn.ReLU(), nn.Conv2d(out_channels, out_channels, kernel_size=1), nn.ReLU()) 1234567891011121314net = nn.Sequential( nin_block(1, 96, kernel_size=11, s ...

ResNet概念吴恩达老师讲的ResNet理论，通俗易懂(吴恩达老师yyds)传送门 代码1234567891011121314151617181920212223242526272829303132import torchfrom torch import nnfrom torch.nn import functional as Ffrom d2l import torch as d2lclass Residual(nn.Module): # @save def __init__(self, input_channels, num_channels, use_1x1conv=False, strides=1): super().__init__() # 定义两层卷积 self.conv1 = nn.Conv2d(input_channels, num_channels, kernel_size=3, padding=1, stride=stri ...

批量归一化概念加速收敛，加快训练速度，一般不改变精度(不与dropout混用) pytorch框架实现1234567891011121314import torchfrom torch import nnfrom d2l import torch as d2l# BatchNorm即批量归一化net = nn.Sequential( nn.Conv2d(1, 6, kernel_size=5), nn.BatchNorm2d(6), nn.Sigmoid(), nn.AvgPool2d(kernel_size=2, stride=2), nn.Conv2d(6, 16, kernel_size=5), nn.BatchNorm2d(16), nn.Sigmoid(), nn.AvgPool2d(kernel_size=2, stride=2), nn.Flatten(), nn.Linear(256, 120), nn.BatchNorm1d(120), nn.Sigmoid(), nn.Linear(120, 84), nn.BatchNorm1d ...

CNN网络实践引入包12345678import torch.nn as nnimport torch.nn.functional as Fimport numpy as npimport torchfrom torch.utils.data import Datasetimport pandas as pd%matplotlib inline 读入数据集onehot编码 iloc()函数 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748targetDict = { 109: torch.Tensor([1, 0, 0, 0, 0, 0, 0, 0, 0, 0]), 122: torch.Tensor([0, 1, 0, 0, 0, 0, 0, 0, 0, 0]), 135: torch.Tensor([0, 0, 1, 0, 0, 0, 0, 0, 0, 0]), 174: torch.Tensor([0, 0, 0, 1 ...

VGG网络模型结构图 代码实现1234567import torchfrom torch import nnfrom d2l import torch as d2lfrom torch.utils import datafrom torchvision import transformsimport torchvision%matplotlib inline 123456789101112def vgg_block(num_convs, in_channels, out_channels): layers = [] for _ in range(num_convs): layers.append(nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1)) layers.append(nn.ReLU()) in_channels = out_channels layers.append(nn.Ma ...

AlexNet模型概述 代码实现123456789101112131415161718192021222324import torchfrom torch import nnfrom d2l import torch as d2lfrom torch.utils import datafrom torchvision import transformsimport torchvision%matplotlib inlined2l.use_svg_display()net = nn.Sequential( nn.Conv2d(1, 96, kernel_size=11, stride=4, padding=1), nn.ReLU(), nn.MaxPool2d(kernel_size=3, stride=2), nn.Conv2d(96, 256, kernel_size=5, padding=2), nn.ReLU(), nn.MaxPool2d(kernel_size=3, stride=2), nn.Conv2d(256, 384, kernel_si ...

LeNet模型原理框架图 代码实现首先定义我们的LeNet模型 1234567891011121314151617181920212223import torchfrom torch import nnfrom d2l import torch as d2lclass Reshape(torch.nn.Module): def forward(self, x): return x.view(-1, 1, 28, 28)# 构建网络net = torch.nn.Sequential( Reshape(), # 对应 阶段1 nn.Conv2d(1, 6, kernel_size=5, padding=2), nn.Sigmoid(), # 对应 阶段2 nn.AvgPool2d(kernel_size=2, stride=2), # 对应 阶段3 nn.Conv2d(6, 16, kernel_size=5), nn.Sigmoid(), # 对应 阶段4 nn.AvgPool2d(kernel_size=2, stride=2) ...