We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent f43b225 commit b28d2f6Copy full SHA for b28d2f6
docs/ch07/ch07.md
@@ -1760,3 +1760,5 @@ plt.show()
1760
## 引用资料
1761
1762
- [MIT 6.5940 TinyML and Efficient Deep Learning Computing](https://hanlab.mit.edu/courses/2023-fall-65940)
1763
+- [machine-learning-notes](https://luweikxy.gitbook.io/machine-learning-notes)
1764
+- [matrix-decomposition-series](https://rendazhang.medium.com/matrix-decomposition-series-table-of-contents-841b77a035db)
docs/ch08/ch08.md
@@ -1,6 +1,7 @@
1
# 第8章 项目实践
2
3
  在前面的章节里,我们分别学习了剪枝、量化、神经网络架构搜索、知识蒸馏与低秩分解等模型压缩技术,那么你能融合两种以上的技术对模型进行压缩吗?
4
+
5
> 任务:基于前面已学知识,选择一种实际应用场景,不限框架和方法,使用两种及以上技术对模型进行压缩并对比前后效果~
6
7
## 总结
0 commit comments