Skip to content
GitLab
Projects
Groups
Snippets
Help
Loading...
Help
What's new
10
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Open sidebar
CrowdHMT
ros_resource_perception
Commits
c5385916
Commit
c5385916
authored
2 years ago
by
Marco_Legend
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Upload New File
parent
61aeba71
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
32 additions
and
0 deletions
+32
-0
README.md
README.md
+32
-0
No files found.
README.md
0 → 100644
View file @
c5385916
# Tf-Torch Converter and Quantization
**简介:**
随着深度神经网络在性能上的不断突破,模型本身的深度和宽度也逐渐扩展,运行时的时间复杂度和空间复杂度等指标也呈现出了爆炸式的增长。因而,深度神经网络的运行对计算平台的处理、存储能力提出了更高要求,加大了模型在资源受限的移动或嵌入式设备上的部署难度,特别以资源约束极端有限的微控制器为代表。这样的背景下,剪枝、量化等模型压缩和加速技术及轻量化的神经网络架构设计为上述挑战带来了可能的解决方案。本代码提供了一种由Pytorch模型生成TensorFlow模型的转换框架,并且提供了商用设备可应用的8-bit训练后量化,将TensorFlow模型进一步转换为TensorFlow Lite模型。
**主要功能:**
本代码在tensorflow0.8及以上版本进行开发。算法输入为可转换Pytorch模型,输出TensorFlow模型和8-bit量化后的TensorFlow Lite模型。
**模型框架示意图:**
|
<div
style=
"width: 100pt"
>
算法名称 | Tf-Torch Converter and Quantization |
| :--------------------------------- | :----------------------------------------------------------- |
| 算法接口 | python test.py |
| 输入 | 可转换Pytorch模型 |
| 输出 | TensorFlow模型和8-bit量化后的TensorFlow Lite模型 |
| 支持数据集 |
\
|
| 依赖平台 | Raspberry Pi 4B、Jetson Nano、PC等 |
| 依赖库 | Python 3.6+、tensorflow0.8+ |
| 参考资源 |
\
|
**联系方式:**
组长邮箱:2544552413@qq.com
### Change Log:
#### V1——20220726:实现pytorch模型向tensorflow模型的转换,并且进一步可将tensorflow模型转换为tensorflow lite模型
#### To-do list:
1.
实现tensorflow模型向pytorch模型的转换。
\ No newline at end of file
This diff is collapsed.
Click to expand it.
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