ckptconfig = CheckpointConfig( save_checkpoint_steps=ds_train.get_dataset_size() * config.epochs, keep_checkpoint_max=10) ckpoint_cb = ModelCheckpoint(prefix='widedeep_train', directory=config.ckpt_path + '/ckpt_' + str(get_rank()) + '/', config=ckptconfig) callback_list = [ TimeMonitor(ds_train.get_dataset_size()), eval_callback, callback ] if int(get_rank()) == 0: callback_list.append(ckpoint_cb) model.train(epochs, ds_train, callbacks=callback_list, sink_size=ds_train.get_dataset_size()) if __name__ == "__main__": wide_and_deep_config = WideDeepConfig() wide_and_deep_config.argparse_init() compute_emb_dim(wide_and_deep_config) context.set_context(mode=context.GRAPH_MODE, device_target="Ascend", save_graphs=True) init() context.set_auto_parallel_context(parallel_mode=ParallelMode.DATA_PARALLEL, gradients_mean=True, device_num=get_group_size()) train_and_eval(wide_and_deep_config)
def test_eval(config): """ test evaluate """ data_path = config.data_path batch_size = config.batch_size ds_eval = create_dataset(data_path, train_mode=False, epochs=2, batch_size=batch_size) print("ds_eval.size: {}".format(ds_eval.get_dataset_size())) net_builder = ModelBuilder() train_net, eval_net = net_builder.get_net(config) param_dict = load_checkpoint(config.ckpt_path) load_param_into_net(eval_net, param_dict) auc_metric = AUCMetric() model = Model(train_net, eval_network=eval_net, metrics={"auc": auc_metric}) eval_callback = EvalCallBack(model, ds_eval, auc_metric, config) model.eval(ds_eval, callbacks=eval_callback) if __name__ == "__main__": widedeep_config = WideDeepConfig() widedeep_config.argparse_init() test_eval(widedeep_config)
batch_size=batch_size) print("ds_train.size: {}".format(ds_train.get_dataset_size())) net_builder = ModelBuilder() train_net, _ = net_builder.get_net(configure) train_net.set_train() model = Model(train_net) callback = LossCallBack(config=configure) ckptconfig = CheckpointConfig( save_checkpoint_steps=ds_train.get_dataset_size(), keep_checkpoint_max=5) ckpoint_cb = ModelCheckpoint(prefix='widedeep_train', directory=configure.ckpt_path, config=ckptconfig) model.train(epochs, ds_train, callbacks=[ TimeMonitor(ds_train.get_dataset_size()), callback, ckpoint_cb ]) if __name__ == "__main__": config = WideDeepConfig() config.argparse_init() context.set_context(mode=context.GRAPH_MODE, device_target=config.device_target) test_train(config)