Skip to content

Feat/add classification metrics#10

Open
Rmin-cmd wants to merge 22 commits intoMiracle-2001:mainfrom
Rmin-cmd:feat/add-classification-metrics
Open

Feat/add classification metrics#10
Rmin-cmd wants to merge 22 commits intoMiracle-2001:mainfrom
Rmin-cmd:feat/add-classification-metrics

Conversation

@Rmin-cmd
Copy link
Copy Markdown

No description provided.

Rmin-cmd and others added 22 commits June 8, 2025 15:44
…1, pytorch-lightning==1.7.5 from requirments.txt
…1, pytorch-lightning==1.7.5 from requirments.txt
…1, pytorch-lightning==1.7.5, scikit-learn==1.2.0 from requirments.txt
…1, pytorch-lightning==1.7.5, scikit-learn==1.2.0 from requirments.txt
…1, pytorch-lightning==1.7.5, scikit-learn==1.2.0, scipy==1.10.0 from requirments.txt
…1, pytorch-lightning==1.7.5, scikit-learn==1.2.0, scipy==1.10.0 from requirments.txt
…1, pytorch-lightning==1.7.5, scikit-learn==1.2.0, scipy==1.10.0 from requirments.txt
…1, pytorch-lightning==1.7.5, scikit-learn==1.2.0, scipy==1.10.0 from requirments.txt
…1, pytorch-lightning==1.7.5, scikit-learn==1.2.0, scipy==1.10.0 from requirments.txt
…1, pytorch-lightning==1.7.5, scikit-learn==1.2.0, scipy==1.10.0 from requirments.txt
…1, pytorch-lightning==1.7.5, scikit-learn==1.2.0, scipy==1.10.0 from requirments.txt
…1, pytorch-lightning==1.7.5, scikit-learn==1.2.0, scipy==1.10.0 from requirments.txt
…1, pytorch-lightning==1.7.5, scikit-learn==1.2.0, scipy==1.10.0 from requirments.txt
…1, pytorch-lightning==1.7.5, scikit-learn==1.2.0, scipy==1.10.0 from requirments.txt
This commit enhances the training process by calculating and displaying F1-score, recall, and precision in addition to accuracy and loss.

Changes include:
- Modified the `do_epoch` method in `ge/Models/trainer.py` to compute F1-score, recall, and precision. These metrics are calculated across the entire epoch's predictions and true labels for better accuracy, using `sklearn.metrics` with 'weighted' averaging and `zero_division=0`.
- Updated the `epoch_metrics` dictionary to include these new metrics.
- Modified the print statement within the `train_and_eval` method in `ge/Models/trainer.py` to log these new metrics for both training and validation phases when `train_log` is enabled.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant