def main(): _copy_and_replace_files() model = ignnition.create_model(model_dir=Path(__file__).parent / __test__) model.computational_graph() model.train_and_validate() model.predict() _clean_files()
def main(): model = ignnition.create_model(model_dir='./') model.computational_graph() val_dataset = model.CONFIG["predict_dataset"] n_links = val_dataset.split('_')[1] all_predictions = np.array(model.evaluate()) np.save("./data/nlinks_"+str(n_links), all_predictions)
def main(): model = ignnition.create_model(model_dir='./') model.computational_graph() all_metrics = model.evaluate() convert_to_np = [] for elem in all_metrics: convert_to_np.append(elem.numpy()) with open('Results.pkl', 'wb') as f: pickle.dump(convert_to_np, f)
def main(): model = ignnition.create_model('./train_options.ini') model.computational_graph() model.train_and_evaluate()
def main(): model = ignnition.create_model('./train_options.ini') model.train_and_evaluate()
def main(): model = ignnition.create_model(model_dir='./') model.computational_graph() model.train_and_validate()
def main(): model = ignnition.create_model( model_dir='exception/load_model_path_required') model.computational_graph() model.predict()