Comments (12)
@deepseek I think @ws-lin is right. Could you please try to use CUDA_VISIBLE_DEVICES=0
in the command.
from db.
I set it to work on just one gpu
from db.
@liangkaihuan Thanks for the hint,
I found the solution, the issue was caused because I had CUDA Version 10.0.130
, while @MhLiao tutorial had cudatoolkit=10.1
.
In my case, the solution was to use cudatoolkit=10.0
Thanks all
from db.
the same error
from db.
I changed model.py(line:56) to
if self.training:
pred = self.model(data, training=self.training)
else:
pred = self.model(data)
and solved the problem.
from db.
@ws-lin What code values did you change to solve this?
@liangkaihuan Upload your modified model.py
here so i can test.
from db.
@MhLiao CUDA_VISIBLE_DEVICES=0
allows to continue the process, but the end is "Segmentation fault", and in results
folder nothing is recognized.
(db) home@home-desktop:~/p9/DB$ CUDA_VISIBLE_DEVICES=0 python eval.py experiments/seg_detector/totaltext_resnet18_deform_thre.yaml --resume ./modelz/totaltext_resnet18 --polygon --box_thresh 0.6
./datasets/total_text/
[INFO] [2019-12-05 20:11:06,534] Resuming from ./modelz/totaltext_resnet18
[INFO] [2019-12-05 20:11:06,563] Resumed from ./modelz/totaltext_resnet18
100%|██████████████████████████████████████████████████████████████████████████████████████| 300/300 [00:10<00:00, 27.78it/s]
[INFO] [2019-12-05 20:11:17,641] precision : 0.000000 (300)
[INFO] [2019-12-05 20:11:17,641] recall : 0.000000 (300)
[INFO] [2019-12-05 20:11:17,641] fmeasure : 0.000000 (1)
Segmentation fault
from db.
I tested CUDA_VISIBLE_DEVICES=0
without modifying code, and the forward() missing
error can also be solved. I think Segmentation fault
in your case may come from incorrect compilation of deformable convolution.
from db.
use CUDA_VISIBLE_DEVICES=0 can't always solve this problem when run the demo.
It still tells "TypeError: forward() missing 1 required positional argument: 'data'" .
Are there some other problems?
from db.
use CUDA_VISIBLE_DEVICES=0 can't always solve this problem when run the demo.
It still tells "TypeError: forward() missing 1 required positional argument: 'data'" .
Are there some other problems?
After hundreds of time trying, I find the issue is "CUDA_VISIBLE_DEVICES=0" doesn't take effect in my centos, while add one line of "os.environ["CUDA_VISIBLE_DEVICES"] = '3'" in demo.py finally saved me.
from db.
The problem is here: DataParallel doesn't properly handle kwargs
from db.
@deepseek it doesn't work. cuda version is equal cudatoolkit version.
from db.
Related Issues (20)
- 百度网盘地址失效了 HOT 2
- are there any resources for sorting the bounding boxes ?
- Spelling of prepare is wrong in README
- could you add a license file to your repo?
- ValueError: num_samples should be a positive integer value, but got num_samples=0
- 计算FPS时,--speed报错ZeroDivisionError: division by zero
- Error when converting checkpoint to ONNX HOT 3
- eval.py 报错:RuntimeError: Attempted to set the storage of a tensor on device "cuda:0" to a storage on different device "cpu". This is no longer allowed; the devices must match. HOT 5
- eval结果为0 HOT 8
- 想使用torch自带的dcn,代替代码中的DCN编译算子,请问大家如何下手?还是建议不修改 HOT 1
- The model trained by ASF config can't be used by demo.py
- Could not find a version that satisfies the requirement opencv-python==4.1.2.30 HOT 1
- CUDA error: device-side assert triggered HOT 1
- 运行python setup.py build_ext --inplace命令时出现错误 HOT 2
- Unknown CUDA
- .
- TypeError: metaclass conflict: the metaclass of a derived class must be a (non-strict) subclass of the metaclasses of all its bases
- Sizes of tensors must match except in dimension 0. Got 2 and 1 in dimension 1 HOT 1
- Calculation of Valiation loss
- How to print the output results of each layer of the model.Plz help
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 db.