fp16

游雁

2024-02-23 8827e26b8d487f123f8d7d5cbd8d00b81dcefcff

 funasr/bin/train.py

@@ -1,3 +1,6 @@
#!/usr/bin/env python3
# -*- encoding: utf-8 -*-

import os
import sys
import torch
@@ -40,15 +43,17 @@


def main(**kwargs):
    print(kwargs)
    
    # set random seed
    tables.print()
    set_all_random_seed(kwargs.get("seed", 0))
    torch.backends.cudnn.enabled = kwargs.get("cudnn_enabled", torch.backends.cudnn.enabled)
    torch.backends.cudnn.benchmark = kwargs.get("cudnn_benchmark", torch.backends.cudnn.benchmark)
    torch.backends.cudnn.deterministic = kwargs.get("cudnn_deterministic", True)
    
    local_rank = int(os.environ.get('LOCAL_RANK', 0))
    if local_rank == 0:
        tables.print()
    # Check if we are using DDP or FSDP
    use_ddp = 'WORLD_SIZE' in os.environ and int(os.environ["WORLD_SIZE"]) > 1
    use_fsdp = kwargs.get("use_fsdp", None)
@@ -76,9 +81,8 @@
        frontend = frontend_class(**kwargs["frontend_conf"])
        kwargs["frontend"] = frontend
        kwargs["input_size"] = frontend.output_size()
    
    # import pdb;
    # pdb.set_trace()


    # build model
    model_class = tables.model_classes.get(kwargs["model"])
    model = model_class(**kwargs, **kwargs["model_conf"], vocab_size=len(tokenizer.token_list))
@@ -92,17 +96,22 @@
            init_param = (init_param,)
        logging.info("init_param is not None: %s", init_param)
        for p in init_param:
            logging.info(f"Loading pretrained params from {p}")
            load_pretrained_model(
                model=model,
                path=p,
                ignore_init_mismatch=kwargs.get("ignore_init_mismatch", True),
                oss_bucket=kwargs.get("oss_bucket", None),
                scope_map=kwargs.get("scope_map", None),
                excludes=kwargs.get("excludes", None),
            )
    else:
            if os.path.exists(p):
                logging.info(f"Loading pretrained params from {p}")
                load_pretrained_model(
                    model=model,
                    path=p,
                    ignore_init_mismatch=kwargs.get("ignore_init_mismatch", True),
                    oss_bucket=kwargs.get("oss_bucket", None),
                    scope_map=kwargs.get("scope_map", None),
                    excludes=kwargs.get("excludes", None),
                )
            else:
                logging.info(f"Checkpoint does not exist, init randomly: {p}")
    elif kwargs.get("init", None):
        initialize(model, kwargs.get("init", "kaiming_normal"))
    else:
        print("No initialize method")


    # freeze_param
@@ -141,30 +150,36 @@
    scheduler_class = scheduler_classes.get(scheduler)
    scheduler = scheduler_class(optim, **kwargs.get("scheduler_conf"))

    # import pdb;
    # pdb.set_trace()

    # dataset
    dataset_class = tables.dataset_classes.get(kwargs.get("dataset", "AudioDataset"))
    dataset_tr = dataset_class(kwargs.get("train_data_set_list"), frontend=frontend, tokenizer=tokenizer, **kwargs.get("dataset_conf"))
    dataset_tr = dataset_class(kwargs.get("train_data_set_list"), frontend=frontend, tokenizer=tokenizer, is_training=True, **kwargs.get("dataset_conf"))
    dataset_val = dataset_class(kwargs.get("valid_data_set_list"), frontend=frontend, tokenizer=tokenizer, is_training=False, **kwargs.get("dataset_conf"))

    # dataloader
    batch_sampler = kwargs["dataset_conf"].get("batch_sampler", "DynamicBatchLocalShuffleSampler")
    batch_sampler_class = tables.batch_sampler_classes.get(batch_sampler)
    batch_sampler_val = None
    if batch_sampler is not None:
        batch_sampler_class = tables.batch_sampler_classes.get(batch_sampler)
        batch_sampler = batch_sampler_class(dataset_tr, **kwargs.get("dataset_conf"))
        batch_sampler_val = batch_sampler_class(dataset_val, is_training=False, **kwargs.get("dataset_conf"))
    dataloader_tr = torch.utils.data.DataLoader(dataset_tr,
                                                collate_fn=dataset_tr.collator,
                                                batch_sampler=batch_sampler,
                                                num_workers=kwargs.get("dataset_conf").get("num_workers", 4),
                                                pin_memory=True)
    

    dataloader_val = torch.utils.data.DataLoader(dataset_val,
                                                collate_fn=dataset_val.collator,
                                                batch_sampler=batch_sampler_val,
                                                num_workers=kwargs.get("dataset_conf").get("num_workers", 4),
                                                pin_memory=True)
    trainer = Trainer(
        model=model,
        optim=optim,
        scheduler=scheduler,
        dataloader_train=dataloader_tr,
        dataloader_val=None,
        dataloader_val=dataloader_val,
        local_rank=local_rank,
        use_ddp=use_ddp,
        use_fsdp=use_fsdp,