Comments (1)
我把训练命令中的run
改为launch
发现多卡可以跑了,但这又是为什么呢?为什么run
不行?
然后我又有个新的疑问。
因为训练自己数据集的类别只有 5 类,所以对载入的预训练权重做了改动,没有改网络结构,全连接层依然是 1000 个节点,我的改动如下:载入预训练权重后对几个全连接层单独进行改写,然后载入cuda避免这部分网络在cpu中(感觉就是这部分引发了后面的错误):
但是这种方式在多卡训练时会报错,报错如下:
按照报错信息做了如下修改:
重新运行后,训练了 1 个epoch后有报了下面的错误:
然后换了一种加载预训练权重的方式,如下:修改网络结构里的类别为5,并在载入ckpt后,将全连接层的参数删除:
这种方法好像可行,目前没报错。
请问能解答一下吗?非常感谢!
from repvgg.
Related Issues (20)
- why get different result after reparam HOT 3
- Paper Question - Why less favored than MobileNets for low-powered devices? HOT 1
- how to prune repvgg
- 请问如果我用RepVGG作为backbone,并且在neck中有其他的操作,比如5*5卷积,这样训练出来的模型还能做结构重参数化吗? HOT 1
- subprocess.CalledProcessError: Command '['/usr/bin/python3', '-u', 'main.py', '--local_rank=0']' returned non-zero exit status 1.
- Question about multi-branch and single-branch network HOT 1
- Training script inquiry
- The bug of QAT
- jit.trace error
- a mistake in code HOT 1
- 为什么RepVgg的单个block拿出来测试,重参数化前后输出的结果是不一样的
- Question about RepVGG usage for downstream task
- 多分支存在非线性的合并 HOT 1
- 关于量化的问题,一般是对重参数化后的模型,再进一步进行量化的吗
- 为什么SEBlock中使用Conv2D而不是Linear层? HOT 1
- Question about training and inference models
- The diff is large when BN use other initialization method in verify script
- Running example_pspnet.py generates an error: raise NotImplementedError HOT 1
- Why would you use 3x3+1x1+identity instead of 3x3+3x3+identity?
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 repvgg.