Comments (5)
Thanks for your attention.
You can find them in the training log files.
Specifically, all training logs will be saved in checkpoints/MODEL_EPOCH/MD5_of_config_file
.
For example, checkpoints/D2STGNN_100/85f8fd856810f2a2ce63b897f141864f
.
Here is the training log of D2STGNN on the METR-LA dataset:
2022-09-02 15:01:54,809 - easytorch-training - INFO - Result <train>: [train_time: 162.60 (s), lr: 1.56e-05, train_MAE: 2.5934, train_RMSE: 5.1506, train_MAPE: 0.0671]
2022-09-02 15:01:54,811 - easytorch-training - INFO - Start validation.
2022-09-02 15:02:03,768 - easytorch-training - INFO - Result <val>: [val_time: 8.96 (s), val_MAE: 2.6475, val_RMSE: 5.1250, val_MAPE: 0.0718]
2022-09-02 15:02:03,836 - easytorch-training - INFO - Checkpoint checkpoints/D2STGNN_100/85f8fd856810f2a2ce63b897f141864f/D2STGNN_best_val_MAE.pt saved
2022-09-02 15:02:21,336 - easytorch-training - INFO - Evaluate best model on test data for horizon 1, Test MAE: 2.0811, Test RMSE: 3.6146, Test MAPE: 0.0490
2022-09-02 15:02:21,339 - easytorch-training - INFO - Evaluate best model on test data for horizon 2, Test MAE: 2.3710, Test RMSE: 4.3777, Test MAPE: 0.0582
2022-09-02 15:02:21,341 - easytorch-training - INFO - Evaluate best model on test data for horizon 3, Test MAE: 2.5543, Test RMSE: 4.8949, Test MAPE: 0.0650
2022-09-02 15:02:21,343 - easytorch-training - INFO - Evaluate best model on test data for horizon 4, Test MAE: 2.6967, Test RMSE: 5.3210, Test MAPE: 0.0705
2022-09-02 15:02:21,345 - easytorch-training - INFO - Evaluate best model on test data for horizon 5, Test MAE: 2.8047, Test RMSE: 5.6422, Test MAPE: 0.0748
2022-09-02 15:02:21,348 - easytorch-training - INFO - Evaluate best model on test data for horizon 6, Test MAE: 2.9020, Test RMSE: 5.9155, Test MAPE: 0.0790
2022-09-02 15:02:21,349 - easytorch-training - INFO - Evaluate best model on test data for horizon 7, Test MAE: 2.9928, Test RMSE: 6.1642, Test MAPE: 0.0827
2022-09-02 15:02:21,351 - easytorch-training - INFO - Evaluate best model on test data for horizon 8, Test MAE: 3.0662, Test RMSE: 6.3694, Test MAPE: 0.0856
2022-09-02 15:02:21,352 - easytorch-training - INFO - Evaluate best model on test data for horizon 9, Test MAE: 3.1361, Test RMSE: 6.5526, Test MAPE: 0.0885
2022-09-02 15:02:21,354 - easytorch-training - INFO - Evaluate best model on test data for horizon 10, Test MAE: 3.2093, Test RMSE: 6.7209, Test MAPE: 0.0913
2022-09-02 15:02:21,355 - easytorch-training - INFO - Evaluate best model on test data for horizon 11, Test MAE: 3.2741, Test RMSE: 6.8814, Test MAPE: 0.0939
2022-09-02 15:02:21,357 - easytorch-training - INFO - Evaluate best model on test data for horizon 12, Test MAE: 3.3431, Test RMSE: 7.0353, Test MAPE: 0.0965
2022-09-02 15:02:21,368 - easytorch-training - INFO - Result <test>: [test_time: -17.53 (s), test_MAE: 2.8693, test_RMSE: 5.8797, test_MAPE: 0.0779]
2022-09-02 15:02:21,410 - easytorch-training - INFO - Checkpoint checkpoints/D2STGNN_100/85f8fd856810f2a2ce63b897f141864f/D2STGNN_078.pt saved
2022-09-02 15:02:21,410 - easytorch-training - INFO - The estimated training finish time is 2022-09-02 16:11:23
from basicts.
Maybe I didn't clarify the question clearly. I wonder how to save the predicted value of all sample points so I can visualize the results. I just found out that I should modify runners.base_tsf_runner.py
to achieve this function, right?
from basicts.
Yes, you are right!
You can save the prediction values of the test set by modifying test
function in runners.base_tsf_runner.py
.
However, saving the results of the training set might be a bit complicated. You need to modify the train
function of easytorch.
from basicts.
This is great!
Thank you for your quick reply @zezhishao
from basicts.
You're welcome!
If you have any questions, please feel free to open a new issue.
from basicts.
Related Issues (20)
- Add contributors. HOT 16
- 请问如何修改学习率衰减器 HOT 1
- 修改数据归一化方式。 HOT 1
- MS (multivariate -> univariate)? HOT 2
- 关于数据输入和输出特征个数的问题? HOT 2
- dataloader的droplast问题 HOT 2
- STGCN 模型不能跑第二次 HOT 1
- implementation of spatial indistinguishability HOT 1
- 能否支持early stop? HOT 1
- 您好,请教一下模型训练好后如何获取预测值与真实值的数据 HOT 5
- 怎么快速的修改输入输出长度,完成不同实验? HOT 1
- 关于训练速度 HOT 3
- 如何多卡训练 HOT 2
- 关于给模型增加额外输入的问题 HOT 1
- 关于TrainingMAE与ValidationMAE的大小 HOT 5
- 预测结果可视化时,results为空
- 关于预测结果可视化的问题 HOT 8
- 如何调参
- masked_wape在处理缺失值为nan时的问题 HOT 4
- 一些问题和优化建议 HOT 26
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 basicts.