def setup_sectlabel_bow_glove_infer(request, clf_datasets_manager, tmpdir_factory): track_for_best = request.param sample_proportion = 0.5 datasets_manager = clf_datasets_manager word_embedder = WordEmbedder(embedding_type="glove_6B_50") bow_encoder = BOW_Encoder(embedder=word_embedder) classifier = SimpleClassifier( encoder=bow_encoder, encoding_dim=word_embedder.get_embedding_dimension(), num_classes=2, classification_layer_bias=True, datasets_manager=datasets_manager, ) train_metric = PrecisionRecallFMeasure(datasets_manager=datasets_manager) validation_metric = PrecisionRecallFMeasure( datasets_manager=datasets_manager) test_metric = PrecisionRecallFMeasure(datasets_manager=datasets_manager) optimizer = torch.optim.Adam(params=classifier.parameters()) batch_size = 1 save_dir = tmpdir_factory.mktemp("experiment_1") num_epochs = 1 save_every = 1 log_train_metrics_every = 10 engine = Engine( model=classifier, datasets_manager=datasets_manager, optimizer=optimizer, batch_size=batch_size, save_dir=save_dir, num_epochs=num_epochs, save_every=save_every, log_train_metrics_every=log_train_metrics_every, train_metric=train_metric, validation_metric=validation_metric, test_metric=test_metric, track_for_best=track_for_best, sample_proportion=sample_proportion, ) engine.run() model_filepath = pathlib.Path(save_dir).joinpath("best_model.pt") infer = ClassificationInference( model=classifier, model_filepath=str(model_filepath), datasets_manager=datasets_manager, ) return infer
bidirectional=BIDIRECTIONAL, combine_strategy=COMBINE_STRATEGY, device=torch.device(DEVICE), ) encoding_dim = (2 * HIDDEN_DIMENSION if BIDIRECTIONAL and COMBINE_STRATEGY == "concat" else HIDDEN_DIMENSION) model = SimpleClassifier( encoder=encoder, encoding_dim=encoding_dim, num_classes=NUM_CLASSES, classification_layer_bias=True, ) optimizer = optim.Adam(params=model.parameters(), lr=LEARNING_RATE) metric = PrecisionRecallFMeasure( idx2labelname_mapping=train_dataset.idx2classname) engine = Engine( model=model, train_dataset=train_dataset, validation_dataset=validation_dataset, test_dataset=test_dataset, optimizer=optimizer, batch_size=BATCH_SIZE, save_dir=MODEL_SAVE_DIR, num_epochs=NUM_EPOCHS, save_every=SAVE_EVERY, log_train_metrics_every=LOG_TRAIN_METRICS_EVERY, tensorboard_logdir=TENSORBOARD_LOGDIR,
device=args.device) encoder = BOW_Encoder(embedder=embedder, aggregation_type=args.word_aggregation, device=args.device) model = SimpleClassifier( encoder=encoder, encoding_dim=1024, num_classes=data_manager.num_labels["label"], classification_layer_bias=True, datasets_manager=data_manager, device=args.device, ) optimizer = optim.Adam(params=model.parameters(), lr=args.lr) train_metric = PrecisionRecallFMeasure(datasets_manager=data_manager) dev_metric = PrecisionRecallFMeasure(datasets_manager=data_manager) test_metric = PrecisionRecallFMeasure(datasets_manager=data_manager) engine = Engine( model=model, datasets_manager=data_manager, optimizer=optimizer, batch_size=args.bs, save_dir=args.model_save_dir, num_epochs=args.epochs, save_every=args.save_every, log_train_metrics_every=args.log_train_metrics_every, device=args.device, train_metric=train_metric,
def setup_engine_test_with_simple_classifier(request, tmpdir_factory): MAX_NUM_WORDS = 1000 MAX_LENGTH = 50 vocab_store_location = tmpdir_factory.mktemp("tempdir").join("vocab.json") DEBUG = True BATCH_SIZE = 1 NUM_TOKENS = 3 EMB_DIM = 300 train_dataset = SectLabelDataset( filename=SECT_LABEL_FILE, dataset_type="train", max_num_words=MAX_NUM_WORDS, max_instance_length=MAX_LENGTH, word_vocab_store_location=vocab_store_location, debug=DEBUG, word_embedding_type="random", word_embedding_dimension=EMB_DIM, ) validation_dataset = SectLabelDataset( filename=SECT_LABEL_FILE, dataset_type="valid", max_num_words=MAX_NUM_WORDS, max_instance_length=MAX_LENGTH, word_vocab_store_location=vocab_store_location, debug=DEBUG, word_embedding_type="random", word_embedding_dimension=EMB_DIM, ) test_dataset = SectLabelDataset( filename=SECT_LABEL_FILE, dataset_type="test", max_num_words=MAX_NUM_WORDS, max_instance_length=MAX_LENGTH, word_vocab_store_location=vocab_store_location, debug=DEBUG, word_embedding_type="random", word_embedding_dimension=EMB_DIM, ) VOCAB_SIZE = MAX_NUM_WORDS + len(train_dataset.word_vocab.special_vocab) NUM_CLASSES = train_dataset.get_num_classes() NUM_EPOCHS = 1 embedding = Embedding.from_pretrained(torch.zeros([VOCAB_SIZE, EMB_DIM])) labels = torch.LongTensor([1]) metric = PrecisionRecallFMeasure( idx2labelname_mapping=train_dataset.idx2classname) embedder = VanillaEmbedder(embedding_dim=EMB_DIM, embedding=embedding) encoder = BOW_Encoder(emb_dim=EMB_DIM, embedder=embedder, dropout_value=0, aggregation_type="sum") tokens = np.random.randint(0, VOCAB_SIZE - 1, size=(BATCH_SIZE, NUM_TOKENS)) tokens = torch.LongTensor(tokens) model = SimpleClassifier( encoder=encoder, encoding_dim=EMB_DIM, num_classes=NUM_CLASSES, classification_layer_bias=False, ) optimizer = optim.SGD(model.parameters(), lr=0.01) engine = Engine( model, train_dataset, validation_dataset, test_dataset, optimizer=optimizer, batch_size=BATCH_SIZE, save_dir=tmpdir_factory.mktemp("model_save"), num_epochs=NUM_EPOCHS, save_every=1, log_train_metrics_every=10, metric=metric, track_for_best=request.param, ) options = { "MAX_NUM_WORDS": MAX_NUM_WORDS, "MAX_LENGTH": MAX_LENGTH, "BATCH_SIZE": BATCH_SIZE, "NUM_TOKENS": NUM_TOKENS, "EMB_DIM": EMB_DIM, "VOCAB_SIZE": VOCAB_SIZE, "NUM_CLASSES": NUM_CLASSES, "NUM_EPOCHS": NUM_EPOCHS, } return engine, tokens, labels, options