self.ends: list self.labels: list """ def __init__(self, words, starts, ends, labels): self.words = words self.starts = starts self.ends = ends self.labels = labels self.predict_labels = [] if __name__ == '__main__': # parameters config_file = 'default.ini' config = Configurable(config_file) # model model = CompanyPredict() # load data train_data = read_pkl(config.train_pkl) dev_data = None if config.para_dev_file: dev_data = read_pkl(config.dev_pkl) test_data = read_pkl(config.test_pkl) word_list = read_pkl(config.load_feature_voc) p_label_list, s_label_list = read_pkl(config.load_label_voc) word_voc = VocabSrc(word_list) p_label_voc = VocabTgt(p_label_list) s_label_voc = VocabTgt(s_label_list)
help= 'The maximum total input sequence length after WordPiece tokenization.' ) parse.add_argument( '-warmup_proportion', type=float, default=0.1, help='Proportion of training to perform linear learning rate warmup for ' 'E.g., 0.1 = 10% of training.') parse.add_argument('-do_lower_case', type=bool, default=True, help='Whether to lower case the input text.') args, extra_args = parse.parse_known_args() config = Configurable(args.config_file, extra_args) bert_config = modeling.BertConfig.from_json_file(args.bert_config_file) if args.max_seq_length > bert_config.max_position_embeddings: raise ValueError( "Cannot use sequence length %d because the BERT model " "was only trained up to sequence length %d" % (args.max_seq_length, bert_config.max_position_embeddings)) tokenizer = tokenization.FullTokenizer(vocab_file=args.vocab_file, do_lower_case=args.do_lower_case) if config.decode: path = './data/test.txt' dev_data, sentence_length = dataLoader.decoder_sentence(path) with open(config.save_dirs + '/' + config.word_path, 'rb') as f:
# 'gateNoDilateRicherContextRefine', # 'gateDilateNoRicherContextRefine', 'noneofall', # 'gatedilatericherRefine', 'dilate', 'gatedilate', # 'gatedilateNoricherNoSkipRefine', 'gatedilatericher', # 'gateDilateNoRicherNoSkipRefineContext' ]) argparser.add_argument('--dis', type=str, default='none', choices=[ 'Kumar_discriminator', 'Dakai_discriminator', 'PatchGANDiscriminator', 'PatchGAN' ]) argparser.add_argument('--split', type=str, default='0.6') argparser.add_argument('--batch-size', type=str, default='4') args, extra_args = argparser.parse_known_args() config = Configurable(args, extra_args) torch.set_num_threads((config.workers + 1) * len(config.gpu_count)) config.train = args.train config.use_cuda = False if gpu and args.use_cuda: config.use_cuda = True print("\nGPU using status: ", config.use_cuda) main(config)
numpy.random.seed(666) # gpu gpu = torch.cuda.is_available() print("GPU available: ", gpu) print("CuDNN: ", torch.backends.cudnn.enabled) # parameters parse = argparse.ArgumentParser('Attention Target Classifier') parse.add_argument('--config_file', type=str, default='default.ini') parse.add_argument('--thread', type=int, default=1) parse.add_argument('--use_cuda', action='store_true', default=False) parse.add_argument('--model', type=str, default='model.742') args, extra_args = parse.parse_known_args() config = Configurable(args.config_file, extra_args) torch.set_num_threads(args.thread) config.use_cuda = False if gpu and args.use_cuda: config.use_cuda = True print("\nGPU using status: ", config.use_cuda) # load vocab and model feature_list = read_pkl(config.load_feature_voc) label_list = read_pkl(config.load_label_voc) feature_vec = VocabSrc(feature_list) label_vec = VocabTgt(label_list) # model if config.which_model == 'Vanilla': model = Vanilla(config, feature_vec.size, config.embed_dim, PAD,
del optimizer empty_cache() return {'train/seg_acc': results.avg[0]} if __name__ == '__main__': torch.manual_seed(6666) torch.cuda.manual_seed(6666) random.seed(6666) np.random.seed(6666) gpu = torch.cuda.is_available() print("GPU available: ", gpu) torch.backends.cudnn.benchmark = True # cudn print("CuDNN: \n", torch.backends.cudnn.enabled) argparser = argparse.ArgumentParser() argparser.add_argument('--config_file', default='da_seg_configuration.txt') argparser.add_argument('--use-cuda', action='store_true', default=True) argparser.add_argument('--train', help='test not need write', default=True) args, extra_args = argparser.parse_known_args() config = Configurable(args.config_file, extra_args, isTrain=args.train) torch.set_num_threads(config.workers + 1) config.train = args.train config.use_cuda = False if gpu and args.use_cuda: config.use_cuda = True print("\nGPU using status: ", config.use_cuda) main(config)