src/paws_train.py [210:265]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
         world_size=world_size,
         rank=rank,
         root_path=root_path,
         image_folder=image_folder,
         training=True,
         copy_data=copy_data)
    iter_supervised = None
    ipe = len(unsupervised_loader)
    logger.info(f'iterations per epoch: {ipe}')

    # -- init optimizer and scheduler
    scaler = torch.cuda.amp.GradScaler(enabled=use_fp16)
    encoder, optimizer, scheduler = init_opt(
        encoder=encoder,
        weight_decay=wd,
        start_lr=start_lr,
        ref_lr=lr,
        final_lr=final_lr,
        ref_mom=mom,
        nesterov=nesterov,
        iterations_per_epoch=ipe,
        warmup=warmup,
        num_epochs=num_epochs)
    if world_size > 1:
        encoder = DistributedDataParallel(encoder, broadcast_buffers=False)

    start_epoch = 0
    # -- load training checkpoint
    if load_model:
        encoder, optimizer, start_epoch = load_checkpoint(
            r_path=load_path,
            encoder=encoder,
            opt=optimizer,
            scaler=scaler,
            use_fp16=use_fp16)
        for _ in range(start_epoch):
            for _ in range(ipe):
                scheduler.step()

    # -- TRAINING LOOP
    best_loss = None
    for epoch in range(start_epoch, num_epochs):
        logger.info('Epoch %d' % (epoch + 1))

        # -- update distributed-data-loader epoch
        unsupervised_sampler.set_epoch(epoch)
        if supervised_sampler is not None:
            supervised_sampler.set_epoch(epoch)

        loss_meter = AverageMeter()
        ploss_meter = AverageMeter()
        rloss_meter = AverageMeter()
        time_meter = AverageMeter()
        data_meter = AverageMeter()

        for itr, udata in enumerate(unsupervised_loader):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/suncet_train.py [201:256]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
         world_size=world_size,
         rank=rank,
         root_path=root_path,
         image_folder=image_folder,
         training=True,
         copy_data=copy_data)
    iter_supervised = None
    ipe = len(unsupervised_loader)
    logger.info(f'iterations per epoch: {ipe}')

    # -- init optimizer and scheduler
    scaler = torch.cuda.amp.GradScaler(enabled=use_fp16)
    encoder, optimizer, scheduler = init_opt(
        encoder=encoder,
        weight_decay=wd,
        start_lr=start_lr,
        ref_lr=lr,
        final_lr=final_lr,
        ref_mom=mom,
        nesterov=nesterov,
        iterations_per_epoch=ipe,
        warmup=warmup,
        num_epochs=num_epochs)
    if world_size > 1:
        encoder = DistributedDataParallel(encoder, broadcast_buffers=False)

    start_epoch = 0
    # -- load training checkpoint
    if load_model:
        encoder, optimizer, start_epoch = load_checkpoint(
            r_path=load_path,
            encoder=encoder,
            opt=optimizer,
            scaler=scaler,
            use_fp16=use_fp16)
        for _ in range(start_epoch):
            for _ in range(ipe):
                scheduler.step()

    # -- TRAINING LOOP
    best_loss = None
    for epoch in range(start_epoch, num_epochs):
        logger.info('Epoch %d' % (epoch + 1))

        # -- update distributed-data-loader epoch
        unsupervised_sampler.set_epoch(epoch)
        if supervised_sampler is not None:
            supervised_sampler.set_epoch(epoch)

        loss_meter = AverageMeter()
        ploss_meter = AverageMeter()
        rloss_meter = AverageMeter()
        time_meter = AverageMeter()
        data_meter = AverageMeter()

        for itr, udata in enumerate(unsupervised_loader):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -