Comments (6)
by the way ,The first time i encountered this error when training to step=1400.
how can i solve it ? thanks !
from fcos.
@studyharderer Please try to set DATALOADER.NUM_WORKERS
as 0.
from fcos.
@tianzhi0549 Thank you very much for your reply ! After setting DATALOADER.NUM_WORKERS=0 , it runs to iters=3340 and reports the following error:
Fatal Python error: GC object already tracked
Thread 0x00007f52917fe700 (most recent call first):
Thread 0x00007f52a6cbe700 (most recent call first):
Thread 0x00007f52a813e700 (most recent call first):
Thread 0x00007f5291fff700 (most recent call first):
Current thread 0x00007f5388734740 (most recent call first):
File "/home/zzy/anaconda3/envs/FCOS/lib/python3.7/site-packages/torchvision/datasets/coco.py", line 115 in getitem
File "/home/zzy/fcos/FCOS/maskrcnn_benchmark/data/datasets/coco.py", line 67 in getitem
File "/home/zzy/anaconda3/envs/FCOS/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 529 in
File "/home/zzy/anaconda3/envs/FCOS/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 529 in next
File "/home/zzy/fcos/FCOS/maskrcnn_benchmark/engine/trainer.py", line 56 in do_train
File "/home/zzy/fcos/FCOS/tools/train_net.py", line 73 in train
File "/home/zzy/fcos/FCOS/tools/train_net.py", line 167 in main
File "/home/zzy/fcos/FCOS/tools/train_net.py", line 174 in
What does this error mean ? how can i solve it ?
from fcos.
@studyharderer I am not sure why this error happens on your machine. Did you change any of the code? Can you try to use a larger batch size such as 4?
from fcos.
@tianzhi0549 I think I might have found the problem. When I started training, the CPU usage of the server reached more than 400% ...... And I used one 1080ti to take up 60%. How do I reduce the usage of cpu and convert into gpu?
I found that the model in your code uses model.to(device) to use gpu. Is the training data in gpu or cpu? I didn't understand your code about dataloader.
from fcos.
@studyharderer In my opinion, I don't think the error has to do with the CPU or GPU usages. Do your server has limited host memory?
from fcos.
Related Issues (20)
- Can I use it on CPU?
- Can we use this FCOS algorithm for counting the objects in images??
- May I ask you for a train log file?
- Which is the accuracy index in the paper?
- Error pip install git+https://github.com/tianzhi0549/FCOS.git HOT 1
- use my dataset to train FCOS net,why the loss is nan? HOT 2
- Can’t calculate the Params and FLOPs of Backbone
- Testing with test dataset while training
- ValueError: Unknown CUDA arch (8.6) or GPU not supported HOT 2
- weird time consuming of FCOS head when changing the backbone
- Problem with the last line of Testing-only installation HOT 1
- Deepcopy returns TypeError: 'int' object is not callable HOT 1
- assert len(proposal_losses) == 1 and proposal_losses["zero"] == 0 # loss_dict should be empty dict
- tools/train_net.py FAILED HOT 1
- Convert onnx
- Segmentation fault (core dumped)
- gempy to load csv data
- ImportError: cannot import name '_C'
- Why regression head wasn't normalized ?
- ValueError: num_samples should be a positive integer value, but got num_samples=0
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 fcos.