def convert_tf_checkpoint_to_pytorch(tf_checkpoint_path, bert_config_file, pytorch_dump_path): # Initialise PyTorch model config = AlbertConfig.from_pretrained(bert_config_file) # print("Building PyTorch model from configuration: {}".format(str(config))) model = AlbertForPreTraining(config) # Load weights from tf checkpoint load_tf_weights_in_albert(model, config, tf_checkpoint_path) # Save pytorch-model print("Save PyTorch model to {}".format(pytorch_dump_path)) torch.save(model.state_dict(), pytorch_dump_path)
def __init__(self, model_path: str, model_file: str, vocab_file: str = "vocab.txt", config_file: str = "config.json", device: typing.Union[torch.device, int, str] = "cpu", turns: int = 3, uttr_len: int = 20, resp_len: int = 20, data_type: str = "uru", add_special_tokens: bool = True): """ :param model_path: str型,模型的路径,需要包含训练好的模型,预训练模型pytorch_model.bin以及对应的词表和config文件 :param model_file: str型,训练好的模型的文件名 :param vocab_file: str型,词表的文件名 :param config_file: str型,预训练模型的配置文件 """ super().__init__() self.preprocessor = CNAlbertPreprocessorForMultiQA( Path(model_path) / vocab_file, uttr_len=uttr_len, resp_len=resp_len, add_special_tokens=add_special_tokens) # 初始化模型 config = AlbertConfig.from_pretrained(Path(model_path) / config_file) model = AlbertIMN(uttr_len, resp_len, turns, config, model_path, data_type=data_type) cls_task = tasks.Classification(num_classes=2, losses=[nn.CrossEntropyLoss()]) cls_task.metrics = ['accuracy'] params = model.get_default_params() params['task'] = cls_task model.params = params model.build() model = model.float() # 加载模型 self.predictor = Predictor(model, save_dir=model_path, checkpoint=model_file, device=device) self.device = self.predictor._device self.turns = turns self.uttr_len = uttr_len self.resp_len = resp_len self.data_type = data_type
from albert_pytorch.model.modeling_albert_bright import AlbertModel, AlbertConfig from albert_pytorch.model.tokenization_bert import BertTokenizer from snlp.tools.vector_similarity import cosine_similarity albert_path = "/home/speech/models/albert_tiny_pytorch_489k" vocab_file = "vocab.txt" config_file = "config.json" text_1 = "咱两谁最漂亮" text_2 = "咱俩谁最漂亮" text_3 = "你好" tokenizer = BertTokenizer.from_pretrained(Path(albert_path) / vocab_file) config = AlbertConfig.from_pretrained(Path(albert_path) / config_file) model = AlbertModel.from_pretrained(Path(albert_path), config=config) start = time.time() input_ids_1 = tokenizer.encode_plus(text_1, add_special_tokens=True)['input_ids'] input_ids_2 = tokenizer.encode_plus(text_2, add_special_tokens=True)['input_ids'] input_ids_3 = tokenizer.encode_plus(text_3, add_special_tokens=True)['input_ids'] input_ids_3.extend([0, 0, 0, 0]) # print(input_ids_1) result = model(torch.tensor([input_ids_1, input_ids_2, input_ids_3]))[1] result = result.detach().cpu().numpy()
def main(): parser = argparse.ArgumentParser() ## Required parameters parser.add_argument( "--data_dir", default=None, type=str, required=True, help= "The input data dir. Should contain the .tsv files (or other data files) for the task." ) parser.add_argument("--model_type", default=None, type=str, required=True, help="Model type selected in the list: ") parser.add_argument( "--model_name_or_path", default=None, type=str, required=True, help="Path to pre-trained model or shortcut name selected in the list") parser.add_argument( "--task_name", default=None, type=str, required=True, help="The name of the task to train selected in the list: " + ", ".join(processors.keys())) parser.add_argument( "--output_dir", default=None, type=str, required=True, help= "The output directory where the model predictions and checkpoints will be written." ) parser.add_argument("--vocab_file", default='', type=str) parser.add_argument("--spm_model_file", default='', type=str) ## Other parameters parser.add_argument( "--config_name", default="", type=str, help="Pretrained config name or path if not the same as model_name") parser.add_argument( "--tokenizer_name", default="", type=str, help="Pretrained tokenizer name or path if not the same as model_name") parser.add_argument( "--cache_dir", default="", type=str, help= "Where do you want to store the pre-trained models downloaded from s3") parser.add_argument( "--max_seq_length", default=512, type=int, help= "The maximum total input sequence length after tokenization. Sequences longer " "than this will be truncated, sequences shorter will be padded.") parser.add_argument("--do_train", action='store_true', help="Whether to run training.") parser.add_argument("--do_eval", action='store_true', help="Whether to run eval on the dev set.") parser.add_argument( "--do_predict", action='store_true', help="Whether to run the model in inference mode on the test set.") parser.add_argument( "--do_lower_case", action='store_true', help="Set this flag if you are using an uncased model.") parser.add_argument("--per_gpu_train_batch_size", default=8, type=int, help="Batch size per GPU/CPU for training.") parser.add_argument("--per_gpu_eval_batch_size", default=8, type=int, help="Batch size per GPU/CPU for evaluation.") parser.add_argument( '--gradient_accumulation_steps', type=int, default=1, help= "Number of updates steps to accumulate before performing a backward/update pass." ) parser.add_argument("--learning_rate", default=5e-5, type=float, help="The initial learning rate for Adam.") parser.add_argument("--weight_decay", default=0.0, type=float, help="Weight deay if we apply some.") parser.add_argument("--adam_epsilon", default=1e-6, type=float, help="Epsilon for Adam optimizer.") parser.add_argument("--max_grad_norm", default=1.0, type=float, help="Max gradient norm.") parser.add_argument("--num_train_epochs", default=3.0, type=float, help="Total number of training epochs to perform.") parser.add_argument( "--max_steps", default=-1, type=int, help= "If > 0: set total number of training steps to perform. Override num_train_epochs." ) parser.add_argument( "--warmup_proportion", default=0.1, type=float, help= "Proportion of training to perform linear learning rate warmup for,E.g., 0.1 = 10% of training." ) parser.add_argument('--logging_steps', type=int, default=10, help="Log every X updates steps.") parser.add_argument('--save_steps', type=int, default=1000, help="Save checkpoint every X updates steps.") parser.add_argument( "--eval_all_checkpoints", action='store_true', help= "Evaluate all checkpoints starting with the same prefix as model_name ending and ending with step number" ) parser.add_argument("--no_cuda", action='store_true', help="Avoid using CUDA when available") parser.add_argument('--overwrite_output_dir', action='store_true', help="Overwrite the content of the output directory") parser.add_argument( '--overwrite_cache', action='store_true', help="Overwrite the cached training and evaluation sets") parser.add_argument('--seed', type=int, default=42, help="random seed for initialization") parser.add_argument( '--fp16', action='store_true', help= "Whether to use 16-bit (mixed) precision (through NVIDIA apex) instead of 32-bit" ) parser.add_argument( '--fp16_opt_level', type=str, default='O1', help= "For fp16: Apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']." "See details at https://nvidia.github.io/apex/amp.html") parser.add_argument("--local_rank", type=int, default=-1, help="For distributed training: local_rank") parser.add_argument('--server_ip', type=str, default='', help="For distant debugging.") parser.add_argument('--server_port', type=str, default='', help="For distant debugging.") os.environ['CUDA_VISIBLE_DEVICES'] = "0" args = parser.parse_args() if not os.path.exists(args.output_dir): os.mkdir(args.output_dir) args.output_dir = args.output_dir + '{}'.format(args.model_type) if not os.path.exists(args.output_dir): os.mkdir(args.output_dir) init_logger(log_file=args.output_dir + '/{}-{}.log'.format(args.model_type, args.task_name)) if os.path.exists(args.output_dir) and os.listdir( args.output_dir ) and args.do_train and not args.overwrite_output_dir: raise ValueError( "Output directory ({}) already exists and is not empty. Use --overwrite_output_dir to overcome." .format(args.output_dir)) # Setup distant debugging if needed if args.server_ip and args.server_port: # Distant debugging - see https://code.visualstudio.com/docs/python/debugging#_attach-to-a-local-script import ptvsd print("Waiting for debugger attach") ptvsd.enable_attach(address=(args.server_ip, args.server_port), redirect_output=True) ptvsd.wait_for_attach() # Setup CUDA, GPU & distributed training if args.local_rank == -1 or args.no_cuda: device = torch.device("cuda" if torch.cuda.is_available() and not args.no_cuda else "cpu") args.n_gpu = torch.cuda.device_count() else: # Initializes the distributed backend which will take care of sychronizing nodes/GPUs torch.cuda.set_device(args.local_rank) device = torch.device("cuda", args.local_rank) torch.distributed.init_process_group(backend='nccl') args.n_gpu = 1 args.device = device # Setup logging logger.warning( "Process rank: %s, device: %s, n_gpu: %s, distributed training: %s, 16-bits training: %s", args.local_rank, device, args.n_gpu, bool(args.local_rank != -1), args.fp16) # Set seed seed_everything(args.seed) # Prepare GLUE task args.task_name = args.task_name.lower() if args.task_name not in processors: raise ValueError("Task not found: %s" % (args.task_name)) processor = processors[args.task_name]() args.output_mode = output_modes[args.task_name] label_list = processor.get_labels() num_labels = len(label_list) # Load pretrained model and tokenizer if args.local_rank not in [-1, 0]: torch.distributed.barrier( ) # Make sure only the first process in distributed training will download model & vocab args.model_type = args.model_type.lower() config = AlbertConfig.from_pretrained( args.config_name if args.config_name else args.model_name_or_path, num_labels=num_labels, finetuning_task=args.task_name) tokenizer = tokenization_albert.FullTokenizer( vocab_file=args.vocab_file, do_lower_case=args.do_lower_case, spm_model_file=args.spm_model_file) model = AlbertForSentenceRanking.from_pretrained( args.model_name_or_path, from_tf=bool('.ckpt' in args.model_name_or_path), config=config) if args.local_rank == 0: torch.distributed.barrier( ) # Make sure only the first process in distributed training will download model & vocab model.to(args.device) logger.info("Training/evaluation parameters %s", args) # Training if args.do_train: train_dataset = load_and_cache_examples(args, args.task_name, tokenizer, data_type='train') global_step, tr_loss = train(args, train_dataset, model, tokenizer) logger.info(" global_step = %s, average loss = %s", global_step, tr_loss) # Saving best-practices: if you use defaults names for the model, you can reload it using from_pretrained() if args.do_train and (args.local_rank == -1 or torch.distributed.get_rank() == 0): # Create output directory if needed if not os.path.exists(args.output_dir) and args.local_rank in [-1, 0]: os.makedirs(args.output_dir) logger.info("Saving model checkpoint to %s", args.output_dir) # Save a trained model, configuration and tokenizer using `save_pretrained()`. # They can then be reloaded using `from_pretrained()` model_to_save = model.module if hasattr( model, 'module') else model # Take care of distributed/parallel training model_to_save.save_pretrained(args.output_dir) # Good practice: save your training arguments together with the trained model torch.save(args, os.path.join(args.output_dir, 'training_args.bin')) # Evaluation results = [] if args.do_eval and args.local_rank in [-1, 0]: tokenizer = tokenization_albert.FullTokenizer( vocab_file=args.vocab_file, do_lower_case=args.do_lower_case, spm_model_file=args.spm_model_file) checkpoints = [(0, args.output_dir)] if args.eval_all_checkpoints: checkpoints = list( os.path.dirname(c) for c in sorted( glob.glob(args.output_dir + '/**/' + WEIGHTS_NAME, recursive=True))) checkpoints = [(int(checkpoint.split('-')[-1]), checkpoint) for checkpoint in checkpoints if checkpoint.find('checkpoint') != -1] checkpoints = sorted(checkpoints, key=lambda x: x[0]) logger.info("Evaluate the following checkpoints: %s", checkpoints) for _, checkpoint in checkpoints: global_step = checkpoint.split( '-')[-1] if len(checkpoints) > 1 else "" prefix = checkpoint.split( '/')[-1] if checkpoint.find('checkpoint') != -1 else "" model = AlbertForSentenceRanking.from_pretrained(checkpoint) model.to(args.device) result = evaluate(args, model, tokenizer, prefix=prefix) results.extend([(k + '_{}'.format(global_step), v) for k, v in result.items()]) output_eval_file = os.path.join(args.output_dir, "checkpoint_eval_results.txt") with open(output_eval_file, "w") as writer: for key, value in results: writer.write("%s = %s\n" % (key, str(value)))