Skip to content
Projects
Groups
Snippets
Help
This project
Loading...
Sign in / Register
Toggle navigation
点
点头人工智能课程-v6.0-影像
Overview
Overview
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
shuo zhang
点头人工智能课程-v6.0-影像
Commits
c7fd01f3
Commit
c7fd01f3
authored
Jul 28, 2025
by
前钰
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Add new file
parent
139ee718
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
49 additions
and
0 deletions
+49
-0
readme.md
3-算法讲解/3.9-作业/readme.md
+49
-0
No files found.
3-算法讲解/3.9-作业/readme.md
0 → 100644
View file @
c7fd01f3
# 花朵五分类任务:算法对比实验作业
# 花朵五分类任务:算法对比实验作业
本作业基于“花朵分类”数据集,完成不同深度学习模型在该任务上的对比实验,旨在通过经典与新型架构的对比分析,掌握模型性能评估与可视化展示的基本方法
## 作业文件获取
作业所需数据已通过百度网盘分享(代码见图像分类章节):
-
链接:
[
点击前往百度网盘下载
](
https://pan.baidu.com/s/12xlvASQ9zYAkIWtKISa3vw?pwd=8888
)
-
提取码:
`8888`
---
## 实验内容
在指定数据集上,使用起码以下模型进行分类实验并进行对比分析:
-
VGG 系列(如 VGG16)
-
ResNet 系列(如 ResNet18 / ResNet50)
-
Vision Transformer(ViT)
### 实验目标
-
比较不同模型在花朵五分类任务上的准确率(Accuracy)
-
输出基础对比表格与可视化结果(此处可使用matplotlib绘制acc、loss曲线)
-
探索模型结构差异对结果的影响
---
## 实验结果示例
下表为模型在测试集上的准确率对比(仅作格式示例):
| 模型名称 | Top-1 Accuracy |
|------------|----------------|
| VGG16 | 85.2% |
| ResNet50 | 90.1% |
| ViT-B/16 | 91.3% |
> 实际结果需通过运行模型在数据集上得出
---
## 注意事项
-
请确保每个模型的训练轮数、优化器设置等尽量一致,以保证公平比较
-
可以适当使用预训练模型进行 finetune
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment