def dataset_build(self, opt): fields = onmt.inputters.get_fields("text", 0, 0) if hasattr(opt, 'src_vocab') and len(opt.src_vocab) > 0: with codecs.open(opt.src_vocab, 'w', 'utf-8') as f: f.write('a\nb\nc\nd\ne\nf\n') if hasattr(opt, 'tgt_vocab') and len(opt.tgt_vocab) > 0: with codecs.open(opt.tgt_vocab, 'w', 'utf-8') as f: f.write('a\nb\nc\nd\ne\nf\n') src_reader = onmt.inputters.str2reader[opt.data_type].from_opt(opt) tgt_reader = onmt.inputters.str2reader["text"].from_opt(opt) train_data_files = preprocess.build_save_dataset( 'train', fields, src_reader, tgt_reader, opt) preprocess.build_save_vocab(train_data_files, fields, opt) preprocess.build_save_dataset( 'valid', fields, src_reader, tgt_reader, opt) # Remove the generated *pt files. for pt in glob.glob(SAVE_DATA_PREFIX + '*.pt'): os.remove(pt) if hasattr(opt, 'src_vocab') and os.path.exists(opt.src_vocab): os.remove(opt.src_vocab) if hasattr(opt, 'tgt_vocab') and os.path.exists(opt.tgt_vocab): os.remove(opt.tgt_vocab)
def dataset_build(self, opt): fields = onmt.io.get_fields("text", 0, 0) train_data_files = preprocess.build_save_dataset('train', fields, opt) preprocess.build_save_vocab(train_data_files, fields, opt) preprocess.build_save_dataset('valid', fields, opt) # Remove the generated *pt files. for pt in glob.glob(SAVE_DATA_PREFIX + '*.pt'): os.remove(pt)
def dataset_build(self, opt): fields = onmt.io.get_fields("text", 0, 0) train_data_files = preprocess.build_save_dataset('train', fields, opt) preprocess.build_save_vocab(train_data_files, fields, opt) preprocess.build_save_dataset('valid', fields, opt) # Remove the generated *pt files. for pt in glob.glob(SAVE_DATA_PREFIX + '*.pt'): os.remove(pt)
def dataset_build(self, opt): fields = inputters.get_fields("text", 0, 0) if hasattr(opt, 'src_vocab') and len(opt.src_vocab) > 0: with codecs.open(opt.src_vocab, 'w', 'utf-8') as f: f.write('a\nb\nc\nd\ne\nf\n') if hasattr(opt, 'tgt_vocab') and len(opt.tgt_vocab) > 0: with codecs.open(opt.tgt_vocab, 'w', 'utf-8') as f: f.write('a\nb\nc\nd\ne\nf\n') train_data_files = preprocess.build_save_dataset('train', fields, opt) preprocess.build_save_vocab(train_data_files, fields, opt) preprocess.build_save_dataset('valid', fields, opt) # Remove the generated *pt files. for pt in glob.glob(SAVE_DATA_PREFIX + '*.pt'): os.remove(pt) if hasattr(opt, 'src_vocab') and os.path.exists(opt.src_vocab): os.remove(opt.src_vocab) if hasattr(opt, 'tgt_vocab') and os.path.exists(opt.tgt_vocab): os.remove(opt.tgt_vocab)
def dataset_build(self, opt): fields = onmt.inputters.get_fields("text", 0, 0) if hasattr(opt, "src_vocab") and len(opt.src_vocab) > 0: with codecs.open(opt.src_vocab, "w", "utf-8") as f: f.write("a\nb\nc\nd\ne\nf\n") if hasattr(opt, "tgt_vocab") and len(opt.tgt_vocab) > 0: with codecs.open(opt.tgt_vocab, "w", "utf-8") as f: f.write("a\nb\nc\nd\ne\nf\n") train_data_files = preprocess.build_save_dataset("train", fields, opt) preprocess.build_save_vocab(train_data_files, fields, opt) preprocess.build_save_dataset("valid", fields, opt) # Remove the generated *pt files. for pt in glob.glob(SAVE_DATA_PREFIX + "*.pt"): os.remove(pt) if hasattr(opt, "src_vocab") and os.path.exists(opt.src_vocab): os.remove(opt.src_vocab) if hasattr(opt, "tgt_vocab") and os.path.exists(opt.tgt_vocab): os.remove(opt.tgt_vocab)