Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/JiJingYu/tensorflow-exercise
https://github.com/JiJingYu/tensorflow-exercise
Last synced: 6 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/JiJingYu/tensorflow-exercise
- Owner: JiJingYu
- License: apache-2.0
- Created: 2017-03-12T10:03:06.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2017-04-02T07:34:29.000Z (over 7 years ago)
- Last Synced: 2024-08-01T16:41:43.149Z (3 months ago)
- Language: Python
- Size: 16.6 KB
- Stars: 14
- Watchers: 3
- Forks: 14
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# tensorflow-exercise
# 1. mnist_test.py
程序列举了常用分类评价指标的计算方法
1. 混淆矩阵(Confusion Matrix,CM)
2. 每类分类精度
3. 平均分类精度(Average Accuracy,OA)
4. 总体分类精度(Overall Accuracy,OA)# 2. svm_grid_search.py
程序使用SVM算法针对iris数据集做分类实验,使用GridSearchCV模块自动搜索超参数
1. 自动搜索超参数的GridSearchCV模块的基本用法
2. 获取不同超参数组合对应的模型性能,使用pandas.DataFrame模块快速保存至CSV文件。# 3. evaluate.py
程序列举了高光谱图像重构评价指标及其Python实现
1. SAM(光谱角相似度)
2. 从PSNR到MPSNR
3. 从SSIM到MSSIM