def _get_pytext_config( self, test_file_name: TestFileName, task_class: Type[NewTask], model_class: Type[Model], ) -> PyTextConfig: test_file_metadata = get_test_file_metadata(test_file_name) return PyTextConfig( task=task_class.Config( data=Data.Config( source=TSVDataSource.Config( train_filename=test_file_metadata.filename, eval_filename=test_file_metadata.filename, test_filename=test_file_metadata.filename, field_names=test_file_metadata.field_names, ), batcher=Batcher.Config( ), # Use Batcher to avoid shuffling. ), trainer=TaskTrainer.Config(epochs=1), model=model_class.Config( inputs=type(model_class.Config.inputs)( dense=FloatListTensorizer.Config( column=test_file_metadata.dense_col_name, dim=test_file_metadata.dense_feat_dim, ))), ), use_tensorboard=False, use_cuda_if_available=False, version=LATEST_VERSION, )
def _get_config_with_export_list( self, task_class: Type[NewTask], model_class: Type[Model], test_file_metadata: TestFileMetadata, ) -> PyTextConfig: return PyTextConfig( task=task_class.Config( data=Data.Config( source=TSVDataSource.Config( train_filename=test_file_metadata.filename, eval_filename=test_file_metadata.filename, test_filename=test_file_metadata.filename, field_names=test_file_metadata.field_names, ), batcher=PoolingBatcher.Config(train_batch_size=1, test_batch_size=1), ), trainer=TaskTrainer.Config(epochs=1), model=model_class.Config( inputs=type(model_class.Config.inputs)( dense=FloatListTensorizer.Config( column=test_file_metadata.dense_col_name, error_check=True, dim=test_file_metadata.dense_feat_dim, ))), ), use_tensorboard=False, use_cuda_if_available=False, export=ExportConfig( export_torchscript_path="/tmp/model_torchscript.pt"), version=LATEST_VERSION, )
def test_batch_predict_caffe2_model(self): with tempfile.NamedTemporaryFile() as snapshot_file, tempfile.NamedTemporaryFile() as caffe2_model_file: train_data = tests_module.test_file("train_data_tiny.tsv") eval_data = tests_module.test_file("test_data_tiny.tsv") config = PyTextConfig( task=DocumentClassificationTask.Config( model=DocModel.Config( inputs=DocModel.Config.ModelInput( tokens=TokenTensorizer.Config(), dense=FloatListTensorizer.Config( column="dense", dim=1, error_check=True ), labels=LabelTensorizer.Config(), ) ), data=Data.Config( source=TSVDataSource.Config( train_filename=train_data, eval_filename=eval_data, test_filename=eval_data, field_names=["label", "slots", "text", "dense"], ) ), ), version=21, save_snapshot_path=snapshot_file.name, export_caffe2_path=caffe2_model_file.name, ) task = create_task(config.task) task.export(task.model, caffe2_model_file.name) model = task.model save(config, model, meta=None, tensorizers=task.data.tensorizers) pt_results = task.predict(task.data.data_source.test) def assert_caffe2_results_correct(caffe2_results): for pt_res, res in zip(pt_results, caffe2_results): np.testing.assert_array_almost_equal( pt_res["score"].tolist()[0], [score[0] for score in res.values()], ) results = batch_predict_caffe2_model( snapshot_file.name, caffe2_model_file.name ) self.assertEqual(4, len(results)) assert_caffe2_results_correct(results) results = batch_predict_caffe2_model( snapshot_file.name, caffe2_model_file.name, cache_size=2 ) self.assertEqual(4, len(results)) assert_caffe2_results_correct(results) results = batch_predict_caffe2_model( snapshot_file.name, caffe2_model_file.name, cache_size=-1 ) self.assertEqual(4, len(results)) assert_caffe2_results_correct(results)