Comments (5)
@xafarranxera
It looks like the path problem, did you modify anything?
from atss.
Now I fixed it, but a major error is still present:
(ATSS) vortiz@vortiz-pc:~/ATSS$ python demo/atss_demo.py THCudaCheck FAIL file=/opt/conda/conda-bld/pytorch_1556653215914/work/aten/src/THC/THCGeneral.cpp line=51 error=30 : unknown error Traceback (most recent call last): File "demo/atss_demo.py", line 114, in <module> main() File "demo/atss_demo.py", line 98, in main min_image_size=args.min_image_size File "/home/vortiz/ATSS/demo/predictor.py", line 112, in __init__ self.model.to(self.device) File "/home/vortiz/anaconda3/envs/ATSS/lib/python3.7/site-packages/torch/nn/modules/module.py", line 386, in to return self._apply(convert) File "/home/vortiz/anaconda3/envs/ATSS/lib/python3.7/site-packages/torch/nn/modules/module.py", line 193, in _apply module._apply(fn) File "/home/vortiz/anaconda3/envs/ATSS/lib/python3.7/site-packages/torch/nn/modules/module.py", line 193, in _apply module._apply(fn) File "/home/vortiz/anaconda3/envs/ATSS/lib/python3.7/site-packages/torch/nn/modules/module.py", line 193, in _apply module._apply(fn) [Previous line repeated 1 more time] File "/home/vortiz/anaconda3/envs/ATSS/lib/python3.7/site-packages/torch/nn/modules/module.py", line 199, in _apply param.data = fn(param.data) File "/home/vortiz/anaconda3/envs/ATSS/lib/python3.7/site-packages/torch/nn/modules/module.py", line 384, in convert return t.to(device, dtype if t.is_floating_point() else None, non_blocking) File "/home/vortiz/anaconda3/envs/ATSS/lib/python3.7/site-packages/torch/cuda/__init__.py", line 163, in _lazy_init torch._C._cuda_init() RuntimeError: cuda runtime error (30) : unknown error at /opt/conda/conda-bld/pytorch_1556653215914/work/aten/src/THC/THCGeneral.cpp:51
So, do we COMPULSORILY need a CUDA GPU to run the demo?
Thanks in advance.
from atss.
@xafarranxera
During inference, ml_nms is used, which does not support CPU. You can try to use nms.
from atss.
Excuse me, but I'm not able to tell how the error presented above relates with nms...
from atss.
@xafarranxera
From your error message, I do not know the reason behind it, you better debug to find the reason. The previous response is to your question that "do we COMPULSORILY need a CUDA GPU to run the demo?".
from atss.
Related Issues (20)
- No module named 'atss_core' HOT 1
- C1083: 无法打开包括文件: “cpu/vision.h”: No such file or directory HOT 1
- 大batch_size和多目标检测的双层for循环导致ATSS算法执行时间长,GPU利用率低,如何提升性能与效率? HOT 3
- cannot import name '_C' from 'atss_core'
- file HOT 1
- How to get the model's test-dev result? Is that right if I change or edit some coding lines in test_net.py? HOT 2
- How can I do batch processing in demo?
- where is the ATSS? HOT 5
- resnet50 is not official version? HOT 1
- how do I run the setup.py file HOT 1
- About sigmoid focal loss cpu.
- A small bug.
- Can you provide the result of multi-scale training with Resnet50 backbone in 2x or 3x?
- total stride size
- The full version of ATSS applied to FCOS HOT 3
- training issues
- Train on own dataset
- YOLOv3
- Install Issue, children need your help!
- where is the code of lite version for FCOS
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 atss.