def main(): ############################################################################### # Load data ############################################################################### dictionary = data.Dictionary() train_corpus = data.Corpus(dictionary) dev_corpus = data.Corpus(dictionary) test_corpus = data.Corpus(dictionary) task_names = ['snli', 'multinli'] if args.task == 'allnli' else [args.task] for task in task_names: skip_first_line = True if task == 'sick' else False train_corpus.parse(task, args.data, 'train.txt', args.tokenize, num_examples=args.max_example, skip_first_line=skip_first_line) if task == 'multinli': dev_corpus.parse(task, args.data, 'dev_matched.txt', args.tokenize) dev_corpus.parse(task, args.data, 'dev_mismatched.txt', args.tokenize) test_corpus.parse(task, args.data, 'test_matched.txt', args.tokenize, is_test_corpus=False) test_corpus.parse(task, args.data, 'test_mismatched.txt', args.tokenize, is_test_corpus=False) else: dev_corpus.parse(task, args.data, 'dev.txt', args.tokenize, skip_first_line=skip_first_line) test_corpus.parse(task, args.data, 'test.txt', args.tokenize, is_test_corpus=False, skip_first_line=skip_first_line) print('train set size = ', len(train_corpus.data)) print('development set size = ', len(dev_corpus.data)) print('test set size = ', len(test_corpus.data)) print('vocabulary size = ', len(dictionary)) # save the dictionary object to use during testing helper.save_object(dictionary, args.save_path + args.task + '_dictionary.pkl') embeddings_index = helper.load_word_embeddings(args.word_vectors_directory, args.word_vectors_file, dictionary.word2idx) print('number of OOV words = ', len(dictionary) - len(embeddings_index)) # ############################################################################### # # Build the model # ############################################################################### model = SentenceClassifier(dictionary, embeddings_index, args) optim_fn, optim_params = helper.get_optimizer(args.optimizer) optimizer = optim_fn(filter(lambda p: p.requires_grad, model.parameters()), **optim_params) best_acc = 0 if args.cuda: model = model.cuda() if args.resume: if os.path.isfile(args.resume): print("=> loading checkpoint '{}'".format(args.resume)) checkpoint = torch.load(args.resume) args.start_epoch = checkpoint['epoch'] best_acc = checkpoint['best_acc'] model.load_state_dict(checkpoint['state_dict']) optimizer.load_state_dict(checkpoint['optimizer']) print("=> loaded checkpoint '{}' (epoch {})".format( args.resume, checkpoint['epoch'])) else: print("=> no checkpoint found at '{}'".format(args.resume)) # ############################################################################### # # Train the model # ############################################################################### train = Train(model, optimizer, dictionary, embeddings_index, args, best_acc) bestmodel = train.train_epochs(train_corpus, dev_corpus, args.start_epoch, args.epochs) test_batches = helper.batchify(test_corpus.data, args.batch_size) if 'multinli' in task_names: print( 'Skipping evaluating best model. Evaluate using the test script.') else: test_accuracy, test_f1 = evaluate(bestmodel, test_batches, dictionary) print('accuracy: %.2f%%' % test_accuracy) print('f1: %.2f%%' % test_f1)
args.max_doc_length) train_corpus.parse(args.data + 'train.txt', max_example=args.max_example) print('train set size = ', len(train_corpus)) dev_corpus = data.Corpus(args.tokenize, args.max_query_length, args.max_doc_length) dev_corpus.parse(args.data + 'dev.txt') print('development set size = ', len(dev_corpus)) dictionary = data.Dictionary() dictionary.build_dict(train_corpus, args.max_words) # save the dictionary object to use during testing helper.save_object(dictionary, args.save_path + 'dictionary.p') print('vocabulary size = ', len(dictionary)) embeddings_index = helper.load_word_embeddings(args.word_vectors_directory, args.word_vectors_file, dictionary.word2idx) print('number of OOV words = ', len(dictionary) - len(embeddings_index)) # ############################################################################### # # Build the model # ############################################################################### model = NSRF(dictionary, embeddings_index, args) print(model) optimizer = optim.Adam(filter(lambda p: p.requires_grad, model.parameters()), args.lr) best_loss = sys.maxsize param_dict = helper.count_parameters(model) print('number of trainable parameters = ',
ndcg_10 += NDCG(score, click_labels, 5) map = map / num_batches ndcg_1 = ndcg_1 / num_batches ndcg_3 = ndcg_3 / num_batches ndcg_10 = ndcg_10 / num_batches print('MAP - ', map) print('NDCG@1 - ', ndcg_1) print('NDCG@3 - ', ndcg_3) print('NDCG@10 - ', ndcg_10) if __name__ == "__main__": dictionary = helper.load_object(args.save_path + 'dictionary.p') embeddings_index = helper.load_word_embeddings( args.word_vectors_directory, 'glove.840B.300d.query.clicks.txt') model = CNN_ARC_II(dictionary, embeddings_index, args) if 'CUDA_VISIBLE_DEVICES' in os.environ: cuda_visible_devices = [ int(x) for x in os.environ['CUDA_VISIBLE_DEVICES'].split(',') ] if len(cuda_visible_devices) > 1: model = torch.nn.DataParallel(model, device_ids=cuda_visible_devices) if args.cuda: model = model.cuda() helper.load_model_states_from_checkpoint( model, os.path.join(args.save_path, 'model_best.pth.tar'), 'state_dict')
dictionary, args.max_query_length, args.max_doc_length, is_test_corpus=True) print('train set size = ', len(train_corpus.data)) print('dev set size = ', len(dev_corpus.data)) print('vocabulary size = ', len(dictionary)) # save the dictionary object to use during testing helper.save_object(dictionary, args.save_path + 'dictionary.p') # embeddings_index = helper.load_word_embeddings(args.word_vectors_directory, args.word_vectors_file) # helper.save_word_embeddings(args.word_vectors_directory, 'glove.840B.300d.match.tensor.txt', embeddings_index, # dictionary.idx2word) embeddings_index = helper.load_word_embeddings( args.word_vectors_directory, 'glove.840B.300d.match.tensor.txt') print('Number of OOV words = ', len(dictionary) - len(embeddings_index)) # ############################################################################### # # Build the model # ############################################################################### model = CNN_ARC_II(dictionary, embeddings_index, args) optimizer = optim.Adam(filter(lambda p: p.requires_grad, model.parameters()), args.lr) best_loss = -1 param_dict = helper.count_parameters(model) print('Number of trainable parameters = ', numpy.sum(list(param_dict.values())))
args = util.get_args() ############################################################################### # Load data ############################################################################### dictionary = data.Dictionary() test_corpus = data.Corpus(args.data, 'session_test.txt', dictionary) print('test set size = ', len(test_corpus.data)) print('vocabulary size = ', len(dictionary)) # embeddings_index = helper.load_word_embeddings(args.word_vectors_directory, args.word_vectors_file) # helper.save_word_embeddings(args.word_vectors_directory, 'glove.840B.300d.desm.txt', embeddings_index, # dictionary.idx2word) embeddings_index = helper.load_word_embeddings(args.word_vectors_directory, 'glove.840B.300d.desm.txt') print('Number of OOV words = ', len(dictionary) - len(embeddings_index)) # ############################################################################### # # Test # ############################################################################### def compute_document_embedding(document_body): emb = numpy.zeros(300) total_found = 0 for term in document_body: if term in embeddings_index: emb = numpy.add(numpy.array(embeddings_index[term]), emb) total_found += 1
'session_train.txt', dictionary, args.max_query_length, args.max_doc_length) dev_corpus = data.Corpus(args.data + 'session_with_clicks/', 'session_dev.txt', dictionary, args.max_query_length, args.max_doc_length, is_test_corpus=True) print('train set size = ', len(train_corpus)) print('dev set size = ', len(dev_corpus)) print('vocabulary size = ', len(dictionary)) # save the dictionary object to use during testing helper.save_object(dictionary, args.save_path + 'dictionary.p') embeddings_index = helper.load_word_embeddings(args.word_vectors_directory, args.word_vectors_file) helper.save_word_embeddings(args.word_vectors_directory, 'glove.6B.200d.query.clicks.txt', embeddings_index, dictionary.idx2word) # embeddings_index = helper.load_word_embeddings(args.word_vectors_directory, 'glove.6B.200d.query.clicks.txt') print('Number of OOV words = ', len(dictionary) - len(embeddings_index)) # ############################################################################### # # Build the model # ############################################################################### model = NSRM(dictionary, embeddings_index, args) optimizer = optim.Adam(filter(lambda p: p.requires_grad, model.parameters()), args.lr) best_loss = -1
def main(): # if output directory doesn't exist, create it if not os.path.exists(args.save_path): os.makedirs(args.save_path) # set the random seed manually for reproducibility. numpy.random.seed(args.seed) torch.manual_seed(args.seed) if torch.cuda.is_available(): if not args.cuda: print( "WARNING: You have a CUDA device, so you should probably run with --cuda" ) else: torch.cuda.manual_seed(args.seed) print('\ncommand-line params : {0}\n'.format(sys.argv[1:])) print('{0}\n'.format(args)) ############################################################################### # Load data ############################################################################### dictionary = data.Dictionary() tasks = [] train_dict, dev_dict = {}, {} if 'quora' in args.task: print('**Task name : Quora**') # load quora dataset quora_train = data.Corpus(args.data, dictionary) quora_train.parse('quora/train.txt', 'quora', args.tokenize, args.max_example) print('Found {} pairs of train sentences.'.format(len( quora_train.data))) quora_dev = data.Corpus(args.data, dictionary) quora_dev.parse('quora/dev.txt', 'quora', args.tokenize) print('Found {} pairs of dev sentences.'.format(len(quora_dev.data))) quora_test = data.Corpus(args.data, dictionary) quora_test.parse('quora/test.txt', 'quora', args.tokenize) print('Found {} pairs of test sentences.'.format(len(quora_test.data))) tasks.append(('quora', 2)) train_dict['quora'] = quora_train dev_dict['quora'] = quora_dev if 'snli' in args.task: print('**Task name : SNLI**') # load snli dataset snli_train = data.Corpus(args.data, dictionary) snli_train.parse('snli/train.txt', 'snli', args.tokenize, args.max_example) print('Found {} pairs of train sentences.'.format(len( snli_train.data))) snli_dev = data.Corpus(args.data, dictionary) snli_dev.parse('snli/dev.txt', 'snli', args.tokenize) print('Found {} pairs of dev sentences.'.format(len(snli_dev.data))) snli_test = data.Corpus(args.data, dictionary) snli_test.parse('snli/test.txt', 'snli', args.tokenize) print('Found {} pairs of test sentences.'.format(len(snli_test.data))) tasks.append(('snli', 3)) train_dict['snli'] = snli_train dev_dict['snli'] = snli_dev if 'multinli' in args.task: print('**Task name : Multi-NLI**') # load multinli dataset multinli_train = data.Corpus(args.data, dictionary) multinli_train.parse('multinli/train.txt', 'multinli', args.tokenize, args.max_example) print('Found {} pairs of train sentences.'.format( len(multinli_train.data))) multinli_dev = data.Corpus(args.data, dictionary) multinli_dev.parse('multinli/dev_matched.txt', 'multinli', args.tokenize) multinli_dev.parse('multinli/dev_mismatched.txt', 'multinli', args.tokenize) print('Found {} pairs of dev sentences.'.format(len( multinli_dev.data))) multinli_test = data.Corpus(args.data, dictionary) multinli_test.parse('multinli/test_matched.txt', 'multinli', args.tokenize) multinli_test.parse('multinli/test_mismatched.txt', 'multinli', args.tokenize) print('Found {} pairs of test sentences.'.format( len(multinli_test.data))) tasks.append(('multinli', 3)) train_dict['multinli'] = multinli_train dev_dict['multinli'] = multinli_dev if 'allnli' in args.task: print('**Task name : AllNLI**') # load allnli dataset allnli_train = data.Corpus(args.data, dictionary) allnli_train.parse('snli/train.txt', 'snli', args.tokenize, args.max_example) allnli_train.parse('multinli/train.txt', 'multinli', args.tokenize, args.max_example) print('Found {} pairs of train sentences.'.format( len(allnli_train.data))) allnli_dev = data.Corpus(args.data, dictionary) allnli_dev.parse('snli/dev.txt', 'snli', args.tokenize) allnli_dev.parse('multinli/dev_matched.txt', 'multinli', args.tokenize) allnli_dev.parse('multinli/dev_mismatched.txt', 'multinli', args.tokenize) print('Found {} pairs of dev sentences.'.format(len(allnli_dev.data))) allnli_test = data.Corpus(args.data, dictionary) allnli_test.parse('snli/test.txt', 'snli', args.tokenize) allnli_test.parse('multinli/test_matched.txt', 'multinli', args.tokenize) allnli_test.parse('multinli/test_mismatched.txt', 'multinli', args.tokenize) print('Found {} pairs of test sentences.'.format(len( allnli_test.data))) tasks.append(('allnli', 3)) train_dict['allnli'] = allnli_train dev_dict['allnli'] = allnli_dev print('\nvocabulary size = ', len(dictionary)) # save the dictionary object to use during testing helper.save_object(dictionary, args.save_path + 'dictionary.p') embeddings_index = helper.load_word_embeddings(args.word_vectors_directory, args.word_vectors_file, dictionary.word2idx) print('number of OOV words = ', len(dictionary) - len(embeddings_index)) # ############################################################################### # # Build the model # ############################################################################### if not tasks: return model = MultitaskDomainAdapter(dictionary, embeddings_index, args, tasks) print(model) optim_fn, optim_params = helper.get_optimizer(args.optimizer) optimizer = optim_fn(filter(lambda p: p.requires_grad, model.parameters()), **optim_params) best_accuracy = 0 # for training on multiple GPUs. use CUDA_VISIBLE_DEVICES=0,1 to specify which GPUs to use if 'CUDA_VISIBLE_DEVICES' in os.environ: cuda_visible_devices = [ int(x) for x in os.environ['CUDA_VISIBLE_DEVICES'].split(',') ] if len(cuda_visible_devices) > 1: model = torch.nn.DataParallel(model, device_ids=cuda_visible_devices) if args.cuda: model = model.cuda() if args.resume: if os.path.isfile(args.resume): print("=> loading checkpoint '{}'".format(args.resume)) checkpoint = torch.load(args.resume) args.start_epoch = checkpoint['epoch'] best_accuracy = checkpoint['best_acc'] model.load_state_dict(checkpoint['state_dict']['model']) optimizer.load_state_dict(checkpoint['optimizer']) print("=> loaded checkpoint '{}' (epoch {})".format( args.resume, checkpoint['epoch'])) else: print("=> no checkpoint found at '{}'".format(args.resume)) # ############################################################################### # # Train the model # ############################################################################### train = Train(model, optimizer, dictionary, embeddings_index, args, best_accuracy) train.set_train_dev_corpus(train_dict, dev_dict) train.train_epochs(args.start_epoch, args.epochs)