jiarui_li/DeepHealth

Go to file

Jiarui Li dd58ced9b9 fix(attn): convert boolean attention mask to additive float (-1e9) to avoid cudnn ptrDesc->finalize on some GPUs

2025-10-22 17:51:12 +08:00

.gitattributes

feat: Add training and validation data via Git LFS

2025-10-16 14:24:56 +08:00

.gitignore

feat: Add multi-GPU training and improve config/ignore

2025-10-17 14:09:34 +08:00

best_model_n_embd_120_n_layer_12_n_head_12.pt

feat: Add model checkpoints and configurations

2025-10-20 09:38:24 +08:00

best_model_n_embd_256_n_layer_16_n_head_16.pt

feat: Add model checkpoints and configurations

2025-10-20 09:38:24 +08:00

config_n_embd_120_n_layer_12_n_head_12.json

feat(model): add TimeAwareGPT2TemporalConv using TemporalConvEncoder; wire into train.py and utils.load_model; add model_name to configs; translate CN comments and add math import

2025-10-22 17:34:06 +08:00

config_n_embd_256_n_layer_16_n_head_16.json

feat(model): add TimeAwareGPT2TemporalConv using TemporalConvEncoder; wire into train.py and utils.load_model; add model_name to configs; translate CN comments and add math import

2025-10-22 17:34:06 +08:00

delphi_labels_chapters_colours_icd.csv

add evaluation scripts.

2025-10-18 13:26:56 +08:00

evaluate_auc.py

evaluate_auc: adapt to new utils.load_model signature (infer checkpoint from config)

2025-10-22 11:40:46 +08:00

evaluate_models.ipynb

evaluate_models.ipynb: update load_model usage to new signature (infer checkpoint from config)

2025-10-22 13:27:28 +08:00

GEMINI.md

feat: Implement time-aware GPT-2 for patient event prediction

2025-10-16 14:21:36 +08:00

LICENSE

Initial commit

2025-10-15 13:54:52 +08:00

models.py

fix(attn): convert boolean attention mask to additive float (-1e9) to avoid cudnn ptrDesc->finalize on some GPUs

2025-10-22 17:51:12 +08:00

plot_auc_boxplots_by_chapter.R

R: order ICD-10 chapters by chapter number (Roman numeral prefix) in boxplots; handle 'Death' and unknowns at end

2025-10-22 16:08:00 +08:00

plot_model_comparison_1year.R

R: add plot_model_comparison_no_gap.R mirroring 1-year script; generate per-plot and 2x2 cowplot grid from model_comparison_auc_no_gap.csv

2025-10-22 15:43:16 +08:00

plot_model_comparison_no_gap.R

R: add plot_model_comparison_no_gap.R mirroring 1-year script; generate per-plot and 2x2 cowplot grid from model_comparison_auc_no_gap.csv

2025-10-22 15:43:16 +08:00

prepare_data.py

feat: Implement time-aware GPT-2 for patient event prediction

2025-10-16 14:21:36 +08:00

README.md

Initial commit

2025-10-15 13:54:52 +08:00

requirements.txt

feat: Optimize AUC evaluation with parallel processing

2025-10-20 16:16:50 +08:00

train_ddp.py

Add train_ddp.py: DistributedDataParallel multi-GPU training with distributed samplers, rank-0 checkpointing, and aggregated metrics

2025-10-22 11:54:48 +08:00

train_iter.py

feat: Add load_model function and update training script

2025-10-18 11:07:59 +08:00

train.py

feat(model): add TimeAwareGPT2TemporalConv using TemporalConvEncoder; wire into train.py and utils.load_model; add model_name to configs; translate CN comments and add math import

2025-10-22 17:34:06 +08:00

ukb_real_train.bin

feat: Add training and validation data via Git LFS

2025-10-16 14:24:56 +08:00

ukb_real_val.bin

feat: Add training and validation data via Git LFS

2025-10-16 14:24:56 +08:00

utils.py

feat(model): add TimeAwareGPT2TemporalConv using TemporalConvEncoder; wire into train.py and utils.load_model; add model_name to configs; translate CN comments and add math import

2025-10-22 17:34:06 +08:00

README.md

DeepHealth