Comments (7)
hello,i meet a problem as follow:
when i want to debug train.py and test.py,there is a error:
from ._reorg_layers import lib as _lib, ffi as _ffi
ModuleNotFoundError: No module named 'layers.reorg._ext.reorg_layer._reorg_layers'
Have you encountered such a problem, can you tell me how to solve it?
from dpatch.
hello,i meet a problem as follow:
when i want to debug train.py and test.py,there is a error:
from ._reorg_layers import lib as _lib, ffi as _ffi
ModuleNotFoundError: No module named 'layers.reorg._ext.reorg_layer._reorg_layers'
Have you encountered such a problem, can you tell me how to solve it?
hello,me too. i just run demo.py ,and the Error is same with u
did u solve it ?
from dpatch.
from dpatch.
i think you should install the cuda-9.0 and torch-0.4.0.However,i should tell that this work is extremely painful
…
------------------ 原始邮件 ------------------ 发件人: "tangchuanming1995"<[email protected]>; 发送时间: 2020年8月20日(星期四) 晚上7:23 收件人: "veralauee/DPatch"<[email protected]>; 抄送: "『☆初陽卍綻放』"<[email protected]>; "Comment"<[email protected]>; 主题: Re: [veralauee/DPatch] RuntimeError: CUDNN_STATUS_EXECUTION_FAILED (#6) hello,i meet a problem as follow: when i want to debug train.py and test.py,there is a error: from ._reorg_layers import lib as _lib, ffi as _ffi ModuleNotFoundError: No module named 'layers.reorg._ext.reorg_layer._reorg_layers' Have you encountered such a problem, can you tell me how to solve it? hello,me too. i just run demo.py ,and the Error is same with u did u solve it ? — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.
thanks, and torch & cuda is right.but it still not work. painful~
from dpatch.
hello,i meet a problem as follow:
when i want to debug train.py and test.py,there is a error:
from ._reorg_layers import lib as _lib, ffi as _ffi
ModuleNotFoundError: No module named 'layers.reorg._ext.reorg_layer._reorg_layers'
Have you encountered such a problem, can you tell me how to solve it?hello,me too. i just run demo.py ,and the Error is same with u
did u solve it ?
hello,you can do the step following the make.sh, then the problem will go
from dpatch.
The cause of this problem may be a mismatch between the CUDA version and pytorch
from dpatch.
Hello,
To avoid this problem I downloaded cuda9.1 using this link Cuda 9.1 on Ubuntu 18.04.
Then don't forget to install all recommended packages + conda install pytorch=0.4.1 cuda91 -c pytorch
.
Hope my comment will help others.
from dpatch.
Related Issues (15)
- How to convert your trainer DPatch from numpy array to image?
- Code for training seems incomplete? HOT 13
- mAP has hardly decreased HOT 9
- The mAP is few decreased
- ModuleNotFoundError: No module named 'layers.reorg._ext.reorg_layer._reorg_layer' HOT 1
- the mAP are too high HOT 3
- Dose the code implement the targetd attack? HOT 7
- inf and -inf in the trained patch
- Trained DPatch not available HOT 5
- The link is invalid HOT 2
- ModuleNotFoundError: No module named 'layers.reorg._ext.reorg_layer._reorg_layer' HOT 1
- How to untarget attack
- Not limite the allowable range of (0,1)?So Dpatch get inf or -inf value ?just looks good。
- Train loss do not change
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 dpatch.