def predict_all(data_name, X, use_cache=False):
"""予測。"""
gen = tk.generator.SimpleGenerator()
model = tk.dl.models.Model.load(MODELS_DIR / f'model.fold0.h5',
gen,
batch_size=BATCH_SIZE,
multi_gpu=True)
pred = _evaluation.predict_tta(model, X)
return pred
def predict_all(data_name, X, use_cache=False):
"""予測。"""
cache_path = CACHE_DIR / data_name / f'{MODEL_NAME}.pkl'
if use_cache and cache_path.is_file():
return joblib.load(cache_path)
if data_name == 'val':
X_list, vi_list = [], []
split_seed = int((MODELS_DIR / 'split_seed.txt').read_text())
for cv_index in range(CV_COUNT):
_, vi = tk.ml.cv_indices(X,
None,
cv_count=CV_COUNT,
cv_index=cv_index,
split_seed=split_seed,
stratify=False)
X_list.append(X[vi])
vi_list.append(vi)
else:
X = _data.load_test_data()
X_list = [X] * CV_COUNT
gen = tk.generator.SimpleGenerator()
model = tk.dl.models.Model.load(MODELS_DIR / f'model.fold0.h5',
gen,
batch_size=BATCH_SIZE,
multi_gpu=True)
pred_list = []
for cv_index in tk.tqdm(range(CV_COUNT), desc='predict'):
if cv_index != 0:
model.load_weights(MODELS_DIR / f'model.fold{cv_index}.h5')
X_t = X_list[cv_index]
pred = _evaluation.predict_tta(model, X_t, mode='bin')
pred_list.append(pred)
if data_name == 'val':
pred = np.empty((len(X), 1), dtype=np.float32)
for vi, p in zip(vi_list, pred_list):
pred[vi] = p
else:
pred = pred_list
cache_path.parent.mkdir(parents=True, exist_ok=True)
joblib.dump(pred, cache_path, compress=3)
return pred
