深度学习入门(3) - CNN

CNN

Convolutional Layer

We use a filter to slide over the image spatially (computing dot products)

Interspersed with activation function as well

What it learns?

First-layer conv filters: local image templates (Often learns oriented edges, opposing colors)

Problems:
  1. For large images, we need many layers to get information about the whole image

​ Solution: Downsample inside the network

  1. Feature map shrinks with each layer

    Solution: Padding : adding zeros around the input

Pooling layer

-> downsampling

Without parameters that needs to be learnt.

ex:

max pooling

Aver pooling

...

FC layer(Fully Connected)

The last layer should always be a FC layer.

Batch normalization

we need to force inputs to be nicely scaled at each layer so that we can do the optimization more easily.

Usually inserted after FC layer / Convolutional layer, before non-linearity

Pros:

make the network easier to train

robust to initialization

Cons:

behaves differently during training and testing

Architechtures (History of ImageNet Challenge)

AlexNet

Input 3 * 277 * 277

Layer filters 64 kernel 11 stride 4 pad 2

We need to pay attention to the Memory, pramas, flop size

ZFNet

larger AlexNet

VGG

Rules:

  1. All conv 3*3 stride 1 pad 1
  2. max pool 2*2 stride 2
  3. after pool double channels

Stages:

conv-conv-pool

conv-conv-pool

conv-conv-pool

conv-conv-conv-pool

conv-conv-conv-pool

GoogLeNet

Stem network: aggressively downsamples input

Inception module:

Use such local unit with different kernal size

Use 1*1 Bottleneck to reduce channel dimensions

At the end, rather than flatting to destroy the spatial information with giant parameters

GoogLeNet use average pooling: 7 * 7 * 1024 -> 1024

There is only on FClayer at the last.

找到瓶颈位置,尽可能降低需要学习的参数数量/内存占用

Auxiliary Classifiers:

To help the deep network converge (batch normalization was not invented then): Auxiliary classification outputs to inject additional gradient at lower layers

Residual Networks

We find out that, somtimes we make the net deeper but it turns out to be underfitted.

Deeper network should strictly have the capability to do whatever a shallow one can, but it's hard to learn the parameters.

So we need the residual network!

This can help learning Identity, with all the parameters to be 0.

The still imitate VGG with its sat b

ResNeXt

Adding grops improves preforamance with same computational complexity.

MobileNets

reduce cost to make it affordable on mobile devices

Transfer learning

We can pretrain the model on a dataset.

When applying it to a new dataset, just finetune/Use linear classifier on the top layers.

Froze the main body of the net.

有一定争议,不需要预训练也能在2-3x的时间达到近似的效果

相关推荐
对你无可奈何6 小时前
给 ComfyUI 做了一个手机助手
人工智能
feasibility.7 小时前
英伟达把物理AI的3D模型“应用商店”开放了:2575个SimReady仿真资产,总计约472GB,可让agent装配机器人训练场景
人工智能·3d·机器人·仿真·建模·具身智能·英伟达
智联视频超融合平台8 小时前
消防宣传月过半,“AI+消防“给视频平台换了张考卷
人工智能·边缘计算·视频监控·安防·视频联网
冬奇Lab8 小时前
一天一个开源项目(第262篇):AG-UI —— 把 AI Agent 接进前端的开放协议,和 MCP、A2A 并列的第三块拼图
人工智能·开源
罗西的思考9 小时前
【轻量化复现大模型 / KIMI K3】MTP / EAGLE‑3 模块交互式演示
人工智能·深度学习·算法
RobinDevNotes10 小时前
Claude Code 剪视频,不上传、不要 API Key
人工智能·python·音视频·开发工具·ipython
stormzhangV10 小时前
Coding Agent,通往 AGI 的重要一环
人工智能·agent·ai编程
Bowen_J11 小时前
Apple Foundation Models:Apple AI核心框架
人工智能·ai编程·apple
IT_陈寒11 小时前
Redis那个过期删除策略,差点让我线上崩了
前端·人工智能·后端
阿里云大数据AI技术12 小时前
AI 原生大数据服务 ADA 快速入门:完成首次对话式数据分析
大数据·人工智能