Comments (13)
你有把我文件中的mmcv软连接删除么?https://github.com/ggjy/DeFeat.pytorch/blob/main/mmcv/_ext.cpython-36m-x86_64-linux-gnu.so
我是从mmcv的源文件.tar.gz
编译然后再把编译好的mmcv包mv
过去的。编译好和mmdet2.0适配的mmcv,能跑起来mmdetection即可。
from defeat.pytorch.
您好,我是直接下载您的源文件后解压后python setup.py install 安装了mmdet2.0, 然后pip安装的mmcv0.5.6, 您的意思是不用再手动安装mmcv吗?
from defeat.pytorch.
那应该不用了,你直接把我文件夹下的mmcv删除就行了。
from defeat.pytorch.
您好,我删除您文件夹下的mmcv提示还是这个问题?请问大概是哪里安装版本适配有问题吗?
from defeat.pytorch.
这个错还是mmcv的问题,我建议你可以试试以下两种方法:
-1- clone我的文件后,删除mmcv,先进行mmcv的安装,再cd DeFeat.pytorch
和 pip install -v -e .
-2- 我是去下载mmcv源码https://pypi.org/project/mmcv/0.5.6/
然后install from source,最后cd DeFeat.pytorch
和 pip install -v -e .
from defeat.pytorch.
您好,感谢您的留言,根据您的意见采用方法1解决了上述问题,但
在跑您源代码时/DeFeat.pytorch/mmdet/apis/train.py中 from mmcv.runner import Runner_kd, 出现ImportError: cannot import name 'Runner_kd',这个是什么问题呢?我试了下mmcv中好像没有没有Runner_kd这个函数?
from defeat.pytorch.
当时跑实验的时候为了方便我直接改了mmcv里面的部分函数(https://github.com/ggjy/DeFeat.pytorch/blob/main/mmcv/runner/runner_kd.py#L303
)来实现蒸馏的效果,如果你想直接用我代码里面的蒸馏代码最快捷的方法是从source编译mmcv,这样可以直接像我一样改mmcv的代码,或者你可以稍微重构一下我的代码而不去更改mmcv里面的函数。
from defeat.pytorch.
明白了,谢谢您
from defeat.pytorch.
求问具体改了哪些函数 咋改回去呀?
from defeat.pytorch.
可以具体说一下怎样“稍微重构”您的代码吗T T
from defeat.pytorch.
明白了,谢谢您
请问下从source编译mmcv是怎么个编译法?我也遇到了ImportError: cannot import name 'Runner_kd',请问您是怎么解决的?万分感谢!
from defeat.pytorch.
当时跑实验的时候为了方便我直接改了mmcv里面的部分函数(
https://github.com/ggjy/DeFeat.pytorch/blob/main/mmcv/runner/runner_kd.py#L303
)来实现蒸馏的效果,如果你想直接用我代码里面的蒸馏代码最快捷的方法是从source编译mmcv,这样可以直接像我一样改mmcv的代码,或者你可以稍微重构一下我的代码而不去更改mmcv里面的函数。
请问下从source编译mmcv是怎么个编译法?我也遇到了ImportError: cannot import name 'Runner_kd',请问具体是怎么解决?万分感谢!
from defeat.pytorch.
当时跑实验的时候为了方便我直接改了mmcv里面的部分函数(
https://github.com/ggjy/DeFeat.pytorch/blob/main/mmcv/runner/runner_kd.py#L303
)来实现蒸馏的效果,如果你想直接用我代码里面的蒸馏代码最快捷的方法是从source编译mmcv,这样可以直接像我一样改mmcv的代码,或者你可以稍微重构一下我的代码而不去更改mmcv里面的函数。请问下从source编译mmcv是怎么个编译法?我也遇到了ImportError: cannot import name 'Runner_kd',请问具体是怎么解决?万分感谢!
抱歉,我还有相同的问题,可以为我解答吗?
from defeat.pytorch.
Related Issues (20)
- Question about ‘head-cls’ type HOT 2
- ImportError: cannot import name 'Runner_kd' from 'mmcv.runner' HOT 24
- 小白求指教,怎么样开始训练 ,是先要下好数据集和下好主干网络的权值吗 HOT 1
- Successfully load teacher network checkpoint. Traceback (most recent call last): File "tools/train_kd.py", line 204, in <module> main() File "tools/train_kd.py", line 200, in main meta=meta) File "/home/Disk-2T/DeFeat.pytorch-main/mmdet/apis/train.py", line 532, in train_detector_kd meta=meta) TypeError: 'module' object is not callable 为什么会报这种错误呀 我使用的命令:python tools/train_kd.py --validate --work-dir /home/Disk-2T/DeFeat.pytorch-main --config configs/kd_faster_rcnn/voc_stu_faster_rcnn_r50_decouple_neck.py --config-t /home/Disk-2T/DeFeat.pytorch-main/configs/kd_faster_rcnn/voc_tea_faster_rcnn_r101.py 大家帮我看看
- 请教作者,请问论文中中间层特征的蒸馏损失,在代码的哪些部分? HOT 1
- About the train log of on coco dataset HOT 2
- 请问在one-stage上是怎么实现的? HOT 1
- Question about the code HOT 3
- KeyError: 'metric mAP is not supported'
- 请问在自制coco数据集上训练时需要怎样增加class HOT 2
- 请问你是怎么安好的啊 我现在已经github下载了mmcv0.5.6版本的,然后runner_kd那个文件也复制过去了,之后怎么做呀?> >
- >我把runner_kd文件复制到runner文件夹之后,用github上的mmcv把作者项目中的mmcv替换了,然后运行了python setup.py develop安装好了mmdet2.0但是pip list之后还是没有mmcv这个环境,并且运行项目也说我缺少mmcv
- About VOC pretrained weight
- 有关于项目代码编译的问题
- python setup.py报错 HOT 2
- 安装报错
- KeyError: 'proposal_list'
- 如何进行多卡训练
- About GT-mask?
- How to calculate ground-truth mask?
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 defeat.pytorch.