Remove extra info token pathway
This commit is contained in:
@@ -320,13 +320,6 @@ def build_model_from_dataset(args: argparse.Namespace, cfg: Dict[str, Any], data
|
||||
n_embd=int(cfg_get(args, cfg, "n_embd", 120)),
|
||||
n_head=int(cfg_get(args, cfg, "n_head", 10)),
|
||||
n_hist_layer=int(cfg_get(args, cfg, "n_hist_layer", 12)),
|
||||
n_tab_layer=int(cfg_get(args, cfg, "n_tab_layer", 4)),
|
||||
n_types=dataset.n_types,
|
||||
n_cont_types=dataset.n_cont_types,
|
||||
n_categories=dataset.n_categories,
|
||||
cont_type_ids=dataset.cont_type_ids,
|
||||
n_bins=int(cfg_get(args, cfg, "n_bins", 16)),
|
||||
extra_pool_reduce=str(cfg_get(args, cfg, "extra_pool_reduce", "mean")),
|
||||
target_mode=model_target_mode,
|
||||
time_mode=str(cfg_get(args, cfg, "time_mode", "relative")),
|
||||
dist_mode=str(cfg_get(args, cfg, "dist_mode", "exponential")),
|
||||
@@ -424,11 +417,6 @@ def validate_dataset_metadata(dataset: HealthDataset, cfg: Dict[str, Any]) -> No
|
||||
|
||||
actual: Dict[str, Any] = {
|
||||
"vocab_size": int(dataset.vocab_size),
|
||||
"n_types": int(dataset.n_types),
|
||||
"n_cont_types": int(dataset.n_cont_types),
|
||||
"n_categories": int(dataset.n_categories),
|
||||
"cont_type_ids": [int(x) for x in dataset.cont_type_ids],
|
||||
"extra_info_types": [int(x) for x in dataset.extra_info_types],
|
||||
}
|
||||
mismatches = [
|
||||
f"{key}: train_config={meta.get(key)!r}, current_dataset={value!r}"
|
||||
@@ -438,7 +426,7 @@ def validate_dataset_metadata(dataset: HealthDataset, cfg: Dict[str, Any]) -> No
|
||||
if mismatches:
|
||||
raise RuntimeError(
|
||||
"Current dataset metadata does not match train_config.json. "
|
||||
"Use the same prepared data and extra_info_types as training. "
|
||||
"Use the same prepared data as training. "
|
||||
+ "; ".join(mismatches)
|
||||
)
|
||||
|
||||
@@ -536,10 +524,6 @@ def infer_readout_hidden(
|
||||
sex=batch_dev["sex"][active],
|
||||
padding_mask=padding_mask[active],
|
||||
t_query=time_seq[active, pos],
|
||||
other_type=batch_dev["other_type"][active],
|
||||
other_value=batch_dev["other_value"][active],
|
||||
other_value_kind=batch_dev["other_value_kind"][active],
|
||||
other_time=batch_dev["other_time"][active],
|
||||
target_mode="all_future",
|
||||
)
|
||||
hidden[active, pos, :] = hidden_pos.float()
|
||||
@@ -550,10 +534,6 @@ def infer_readout_hidden(
|
||||
time_seq=time_seq,
|
||||
sex=batch_dev["sex"],
|
||||
padding_mask=padding_mask,
|
||||
other_type=batch_dev["other_type"],
|
||||
other_value=batch_dev["other_value"],
|
||||
other_value_kind=batch_dev["other_value_kind"],
|
||||
other_time=batch_dev["other_time"],
|
||||
target_mode="next_token",
|
||||
)
|
||||
ro = readout(
|
||||
@@ -1337,7 +1317,6 @@ def main() -> None:
|
||||
include_no_event_in_uts_target=include_no_event,
|
||||
min_history_events=int(cfg.get("all_future_min_history_events", 1)),
|
||||
min_future_events=int(cfg.get("all_future_min_future_events", 1)),
|
||||
extra_info_types=parse_int_list(cfg.get("extra_info_types", None)),
|
||||
)
|
||||
validate_dataset_metadata(dataset, cfg)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user