Comments (3)
One way to solve your problem and conform to the template philosophy is to integrate loss
into valid_metrics
. To do so, you have to customize the MetricTracker
class under util.py
. When it is done, you can access val_loss
by val_log.val_loss
in train_epoch()
.
from pytorch-template.
Hello @YiweiJiang2015, Thanks for your support. Will work on it and try to make a pull request.
from pytorch-template.
Hello @YiweiJiang2015, while working on this I found out that in _train_epoch()
log
is a dictionary that already contains the resulting {'loss', 'accuracy', 'top_k_acc', 'val_loss', 'val_accuracy', 'val_top_k_acc'}
can I use these values to step the scheduler?
from pytorch-template.
Related Issues (20)
- Loss function HOT 1
- Any plans to support Wandb Hyperparameter Searching?
- Strange bugs occur when the number of Gpus trained and tested is inconsistent
- usage of shuffle=True when using SubsetRandomSampler HOT 1
- TODO: also configure logging for sub-processes(not master) HOT 4
- DataLoader example
- python train.py --resume path/to/checkpoint HOT 1
- Reading config: reading for save_dir
- Model is moved to GPU after the optimizer is instatiated, resulting in a performance hit. HOT 4
- Setting 'early_stop: 0' does not disable it HOT 2
- Passing an iterable from config.json HOT 2
- Add custom flag & override from CLI HOT 1
- Some features I have implemented.
- Only `data_loader.data_loaders` is plural HOT 5
- Any support for multiple loss functions? HOT 5
- Latest checkpoint HOT 8
- Some thing wrong with add_histogram function HOT 2
- Adding mesh to Tensorboard not working via TensorboardWriter HOT 2
- Any plans to support DistributedDataParallel? HOT 2
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 pytorch-template.