Comments (7)
Hi, I just solved that several days ago. The error caused by the fixed max number of steps in adjusting learning rate. You can have a check if it's work.
Cheers,
zx
from ccm.
嗨,我几天前刚刚解决了这个问题。调整学习率时固定的最大步数引起的错误。您可以检查它是否有效。干杯,zx
I also encountered this problem recently, can you elaborate on how to solve it? Thank you very much
Hi there,
Sorry for the late reply. The issue is coming from the incorrect max step during optimizating. Here is my version:
def adjust_learning_rate(optimizer, i_iter, len_loader, args):
lr = lr_poly(args.learning_rate, i_iter, args.epochs*len_loader, args.power)
optimizer.param_groups[0]['lr'] = lr
if len(optimizer.param_groups) > 1:
optimizer.param_groups[1]['lr'] = lr * 10
return lr
Hope this could help.
Zx
from ccm.
Hello,
Thanks for your interest on our work!
I tried to locate the problem you post but failed. But I postulate that the error is caused by the new version of pytorch, so I think using pytorch=1.7.0 may helps.
Hope it helps.
from ccm.
Hello,
Thanks for your interest on our work! I tried to locate the problem you post but failed. But I postulate that the error is caused by the new version of pytorch, so I think using pytorch=1.7.0 may helps.
Hope it helps.
Hi, thanks for your advise. I have tried the version of pytorch==1.7.0, the before error was disappeared but another error is appaer:
Traceback (most recent call last):
File "so_run.py", line 51, in
main()
File "so_run.py", line 43, in main
trainer.train()
File "/home/CCM/trainer/source_only_trainer.py", line 58, in train
self.optim.step()
File "/home/anaconda3/envs/torch1.7/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 26, in decorate_context
return func(*args, **kwargs)
File "/home/anaconda3/envs/torch1.7/lib/python3.8/site-packages/torch/optim/sgd.py", line 112, in step
p.add_(d_p, alpha=-group['lr'])
RuntimeError: value cannot be converted to type float without overflow: (2.10957e-06,-6.85442e-07)
I have no idea at all
from ccm.
Hello
As far as I can postulate, it maybe because the training steps exceeds the max steps of the optimizer.
You can check it..
from ccm.
Same error here, and I've tried to increase num_steps in so_config.yaml but it didn't work. Could you provide the parameter that you use to train source-only model?
Thank you!
from ccm.
嗨,我几天前刚刚解决了这个问题。调整学习率时固定的最大步数引起的错误。您可以检查它是否有效。干杯,zx
I also encountered this problem recently, can you elaborate on how to solve it? Thank you very much
from ccm.
Related Issues (14)
- Could you provide the pre-trained model "SYNTHIA-Source-only"
- A little question about piece of code in the ccm_config.yml HOT 2
- Questions about the two models HOT 2
- about the label of target domain HOT 1
- Source only model HOT 4
- About SYNTHIA pretrained models
- Baseline_model HOT 1
- config, writer = init_config("config/final_config.yml", sys.argv) HOT 1
- neptune.exceptions.MissingApiToken: Missing API token. HOT 2
- thres in gene_thres HOT 1
- Source Only Train HOT 1
- self.cnts don't need to be updated? HOT 1
- The random selection of 'pool_prop' before matching and selection HOT 1
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 ccm.