updates to evaluation script and callbacks

Merge branch 'main' of https://github.com/griffin-goodwin/FOXES

cleaning up the code base significantly

Add in ViT ML Workflow illustration

Update README.md

Update README.md

Merge branch 'main' of https://github.com/griffin-goodwin/FOXES

Merge branch 'main' of https://github.com/griffin-goodwin/FOXES

Update AIA_GOESDataset to load 7 wavelengths, modify model configuration in localpatch.yaml, and enhance region detection in patch_analysis.py with parallel processing and contour movie generation.

Update plotting.py

Update inference_on_patch.py

Update inference.py

Update evaluation.py

Update evaluation.py

Update batch_evaluation.py

Update auto_evaluate.py

Update sxr_normalization.py

Update SDOAIA_dataloader.py

Update callback.py

Update train.py

Add in FOXES project description and instructions markdown.

Add in FOXES project description and instructions markdown.

Add in FOXES project description and instructions markdown doc.

Fix README.md by resolving merge conflict

Merge remote-tracking branch 'origin/main' into dev-patch

Initial commit

config changes

more changes

cleaning patch model

Various bug fixes and changes to all codes

Added some retry capability to sdo downloader so it doesnt just quit when connection is refused

enhance data splitting functionality.

made evaluation easier by adding auto eval... makes configs on its own...

made data pipeline for data processing in process_data_pipeline.py

Created a cnn model and local attention based model to get more physically significant predictions...

Enhance FlareDownloadProcessor to support time span mode for 1-minute cadence downloads, adding new arguments and methods for data existence checks. Update command-line arguments for improved usability. Refactor evaluation configurations and model training settings, including adjustments to checkpoint paths and model parameters for better performance.

Merge branch 'flaring' of https://github.com/FrontierDevelopmentLab/2025-HL-Flaring-MEGS-AI into flaring

configs

Enhance evaluation configuration and model evaluation process. Updated `create_evaluation_config` to include weight path, integrated timestamp generation for movie frames, and modified `run_evaluation` to utilize timestamps. Improved error handling for weight path and refined plot aesthetics in `SolarFlareEvaluator` with consistent font styling and background adjustments.

fixed plot colors

created batch evaluation

Merge branch 'flaring' of https://github.com/FrontierDevelopmentLab/2025-HL-Flaring-MEGS-AI into flaring

Refactor ViT model configuration and base weights; update learning rate in training configs; standardize Huber loss delta notation for consistency.

Merge branch 'flaring' of https://github.com/FrontierDevelopmentLab/2025-HL-Flaring-MEGS-AI into flaring

improved eval

Refactor SXRRegressionDynamicLoss weights and performance multipliers; adjust model configuration for ViTPatch with reduced patch size and increased number of heads; implement GPU memory isolation and monitoring in training script; enhance AttentionMapCallback to accept dynamic patch size.

add 2d positional embedding to try and improve forcasting

Update inference configuration and refactor FluxContributionAnalyzer to support YAML configuration; added time period filtering for analysis and enhanced simultaneous flare detection functionality.

patch

vit changes