Comments (4)
midasklr
commented on August 23, 2024
请问这是什么原因呢？谢谢版主~
prune ratio太高, 可以根据log中推荐的ratio, 一个基本的准则是每层bn至少保留一个channel,你的model17.cv1.bn层全被剪掉了.
from yolov5prune.
yanggui19891007
commented on August 23, 2024
好的，谢谢版主，剪纸完了后又出现这个错误是什么原因啊？麻烦版主帮我看看谢谢
IndexError: too many indices for tensor of dimension 3
from yolov5prune.
yanggui19891007
commented on August 23, 2024
这个地方报错是不是写错了bug，要把pruned_layer.weight.data = w[:,formerin, :, :].clone()改成pruned_layer.weight.data = w.clone()呢？请版主回复一下谢谢~
from yolov5prune.
midasklr
commented on August 23, 2024
这个地方报错是不是写错了bug，要把pruned_layer.weight.data = w[:,formerin, :, :].clone()改成pruned_layer.weight.data = w.clone()呢？请版主回复一下谢谢~
对的，因为你这里有一层bn只剩下一个channel，导致w索引后张量w变成了3维，已经修复：02729d3#diff-ef54babcc6303af9a9ef15daccc24d8a03b5185088c609df96cedbfb41ea3755R476
git pull一下最新代码
from yolov5prune.
Related Issues (20)
- 剪枝问题 HOT 2
- 你好，我想对yolov5s上训练的模型进行稀疏训练，提示缺少DetectionModel HOT 2
- 想问一个关于剪枝参数设置问题
- ModuleNotFoundError No module named 'tensorboard' HOT 1
- TensorRT 显存没有减少 HOT 1
- conv剪枝 percent超过10%就报错 HOT 1
- 对yolov5x训练出来的模型使用conv+bn剪枝报错
- 第一种方法剪枝后精度下降为0，微调后上升的问题 HOT 1
- 一堆问题，都没法运行，有没有一个完整的版本 HOT 1
- bn_weight/hist未出现 HOT 1
- 稀疏训练掉点严重
- 正常训练显示时显示TypeError: on_fit_epoch_end() missing 1 required positional argument: 'fi' HOT 2
- step后权值没有更新 HOT 1
- 在进行稀疏化的时候遇到报错 HOT 2
- TypeError: on_fit_epoch_end() missing 1 required positional argument: 'fi'
- 6.0版本稀疏训练train_sparity.py 报错TypeError: on_fit_epoch_end() takes 5 positional arguments but 6 were given HOT 2
- 我想请教下稀疏训练的稀疏效果一直不好是怎么回事，我甚至把sr开到了10 HOT 2
- prune.py脚本运行报错 too many indices for tensor demension 3 HOT 1
- 计算量 HOT 1
- RuntimeError: mat1 and mat2 shapes cannot be multiplied HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from yolov5prune.