def test_no_val_end_module(tmpdir): """Tests use case where trainer saves the model, and user loads it from tags independently.""" class CurrentTestModel(LightTrainDataloader, LightValidationStepMixin, TestModelBase): pass hparams = tutils.get_default_hparams() model = CurrentTestModel(hparams) # logger file to get meta logger = tutils.get_default_logger(tmpdir) # fit model trainer = Trainer(max_epochs=1, logger=logger, checkpoint_callback=ModelCheckpoint(tmpdir)) result = trainer.fit(model) # traning complete assert result == 1, 'amp + ddp model failed to complete' # save model new_weights_path = os.path.join(tmpdir, 'save_test.ckpt') trainer.save_checkpoint(new_weights_path) # load new model tags_path = tutils.get_data_path(logger, path_dir=tmpdir) tags_path = os.path.join(tags_path, 'meta_tags.csv') model_2 = LightningTestModel.load_from_checkpoint( checkpoint_path=new_weights_path, tags_csv=tags_path) model_2.eval()
def test_no_val_end_module(monkeypatch, tmpdir, tmpdir_server, url_ckpt): """Tests use case where trainer saves the model, and user loads it from tags independently.""" # set $TORCH_HOME, which determines torch hub's cache path, to tmpdir monkeypatch.setenv('TORCH_HOME', tmpdir) model = EvalModelTemplate() # logger file to get meta logger = tutils.get_default_logger(tmpdir) # fit model trainer = Trainer(max_epochs=1, logger=logger, checkpoint_callback=ModelCheckpoint(tmpdir)) result = trainer.fit(model) # traning complete assert result == 1, 'amp + ddp model failed to complete' # save model new_weights_path = os.path.join(tmpdir, 'save_test.ckpt') trainer.save_checkpoint(new_weights_path) # load new model hparams_path = tutils.get_data_path(logger, path_dir=tmpdir) hparams_path = os.path.join(hparams_path, 'hparams.yaml') ckpt_path = f'http://{tmpdir_server[0]}:{tmpdir_server[1]}/{os.path.basename(new_weights_path)}' if url_ckpt else new_weights_path model_2 = EvalModelTemplate.load_from_checkpoint(checkpoint_path=ckpt_path, hparams_file=hparams_path) model_2.eval()
def test_loading_meta_tags(tmpdir): """ test for backward compatibility to meta_tags.csv """ tutils.reset_seed() hparams = EvalModelTemplate.get_default_hparams() # save tags logger = tutils.get_default_logger(tmpdir) logger.log_hyperparams(Namespace(some_str='a_str', an_int=1, a_float=2.0)) logger.log_hyperparams(hparams) logger.save() # load hparams path_expt_dir = tutils.get_data_path(logger, path_dir=tmpdir) hparams_path = os.path.join(path_expt_dir, TensorBoardLogger.NAME_HPARAMS_FILE) hparams = load_hparams_from_yaml(hparams_path) # save as legacy meta_tags.csv tags_path = os.path.join(path_expt_dir, 'meta_tags.csv') save_hparams_to_tags_csv(tags_path, hparams) tags = load_hparams_from_tags_csv(tags_path) assert hparams == tags
def test_no_val_end_module(tmpdir): """Tests use case where trainer saves the model, and user loads it from tags independently.""" model = EvalModelTemplate() # logger file to get meta logger = tutils.get_default_logger(tmpdir) # fit model trainer = Trainer( max_epochs=1, logger=logger, checkpoint_callback=ModelCheckpoint(tmpdir) ) result = trainer.fit(model) # traning complete assert result == 1, 'amp + ddp model failed to complete' # save model new_weights_path = os.path.join(tmpdir, 'save_test.ckpt') trainer.save_checkpoint(new_weights_path) # load new model hparams_path = tutils.get_data_path(logger, path_dir=tmpdir) hparams_path = os.path.join(hparams_path, 'hparams.yaml') model_2 = EvalModelTemplate.load_from_checkpoint( checkpoint_path=new_weights_path, hparams_file=hparams_path ) model_2.eval()
def test_no_val_module(tmpdir): """Tests use case where trainer saves the model, and user loads it from tags independently.""" model = EvalModelTemplate() # logger file to get meta logger = tutils.get_default_logger(tmpdir) trainer = Trainer(max_epochs=1, logger=logger, checkpoint_callback=ModelCheckpoint(tmpdir)) # fit model result = trainer.fit(model) # training complete assert result == 1, 'amp + ddp model failed to complete' # save model new_weights_path = os.path.join(tmpdir, 'save_test.ckpt') trainer.save_checkpoint(new_weights_path) # assert ckpt has hparams ckpt = torch.load(new_weights_path) assert CHECKPOINT_KEY_MODULE_ARGS in ckpt.keys( ), 'module_arguments missing from checkpoints' # load new model hparams_path = tutils.get_data_path(logger, path_dir=tmpdir) hparams_path = os.path.join(hparams_path, 'hparams.yaml') model_2 = EvalModelTemplate.load_from_checkpoint( checkpoint_path=new_weights_path, hparams_file=hparams_path) model_2.eval()
def test_model_saving_loading(tmpdir): """Tests use case where trainer saves the model, and user loads it from tags independently.""" tutils.reset_seed() hparams = tutils.get_default_hparams() model = LightningTestModel(hparams) # logger file to get meta logger = tutils.get_default_testtube_logger(tmpdir, False) trainer_options = dict( max_epochs=1, logger=logger, checkpoint_callback=ModelCheckpoint(tmpdir) ) # fit model trainer = Trainer(**trainer_options) result = trainer.fit(model) # traning complete assert result == 1, 'amp + ddp model failed to complete' # make a prediction dataloaders = model.test_dataloader() if not isinstance(dataloaders, list): dataloaders = [dataloaders] for dataloader in dataloaders: for batch in dataloader: break x, y = batch x = x.view(x.size(0), -1) # generate preds before saving model model.eval() pred_before_saving = model(x) # save model new_weights_path = os.path.join(tmpdir, 'save_test.ckpt') trainer.save_checkpoint(new_weights_path) # load new model tags_path = tutils.get_data_path(logger, path_dir=tmpdir) tags_path = os.path.join(tags_path, 'meta_tags.csv') model_2 = LightningTestModel.load_from_checkpoint( checkpoint_path=new_weights_path, tags_csv=tags_path ) model_2.eval() # make prediction # assert that both predictions are the same new_pred = model_2(x) assert torch.all(torch.eq(pred_before_saving, new_pred)).item() == 1
def test_running_test_pretrained_model_distrib(tmpdir, backend): """Verify `test()` on pretrained model.""" tutils.reset_seed() tutils.set_random_master_port() hparams = tutils.get_default_hparams() model = LightningTestModel(hparams) # exp file to get meta logger = tutils.get_default_logger(tmpdir) # exp file to get weights checkpoint = tutils.init_checkpoint_callback(logger) trainer_options = dict( progress_bar_refresh_rate=0, max_epochs=2, train_percent_check=0.4, val_percent_check=0.2, checkpoint_callback=checkpoint, logger=logger, gpus=[0, 1], distributed_backend=backend, ) # fit model trainer = Trainer(**trainer_options) result = trainer.fit(model) log.info(os.listdir(tutils.get_data_path(logger, path_dir=tmpdir))) # correct result and ok accuracy assert result == 1, 'training failed to complete' pretrained_model = tutils.load_model(logger, trainer.checkpoint_callback.dirpath, module_class=LightningTestModel) # run test set new_trainer = Trainer(**trainer_options) new_trainer.test(pretrained_model) # test we have good test accuracy tutils.assert_ok_model_acc(new_trainer) dataloaders = model.test_dataloader() if not isinstance(dataloaders, list): dataloaders = [dataloaders] for dataloader in dataloaders: tutils.run_prediction(dataloader, pretrained_model)
def test_loading_meta_tags(tmpdir): hparams = tutils.get_default_hparams() # save tags logger = tutils.get_default_logger(tmpdir) logger.log_hyperparams(Namespace(some_str='a_str', an_int=1, a_float=2.0)) logger.log_hyperparams(hparams) logger.save() # load tags path_expt_dir = tutils.get_data_path(logger, path_dir=tmpdir) tags_path = os.path.join(path_expt_dir, 'meta_tags.csv') tags = load_hparams_from_tags_csv(tags_path) assert tags.batch_size == 32 and tags.hidden_dim == 1000
def test_loading_yaml(tmpdir): tutils.reset_seed() hparams = EvalModelTemplate.get_default_hparams() # save tags logger = tutils.get_default_logger(tmpdir) logger.log_hyperparams(Namespace(some_str='a_str', an_int=1, a_float=2.0)) logger.log_hyperparams(hparams) logger.save() # load hparams path_expt_dir = tutils.get_data_path(logger, path_dir=tmpdir) hparams_path = os.path.join(path_expt_dir, 'hparams.yaml') tags = load_hparams_from_yaml(hparams_path) assert tags['batch_size'] == 32 and tags['hidden_dim'] == 1000