train-classif.py [159:184]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    trainer.reload_checkpoint()
    evaluator = Evaluator(trainer, params)

    # evaluation
    if params.eval_only:
        scores = evaluator.run_all_evals(trainer, evals=['classif', 'recognition'], data_loader=valid_data_loader)

        for k, v in scores.items():
            logger.info('%s -> %.6f' % (k, v))
        logger.info("__log__:%s" % json.dumps(scores))
        exit()

    # training
    for epoch in range(trainer.epoch, params.epochs):

        # update epoch / sampler / learning rate
        trainer.epoch = epoch
        logger.info("============ Starting epoch %i ... ============" % trainer.epoch)
        if params.multi_gpu:
            train_sampler.set_epoch(epoch)

        # update learning rate
        trainer.update_learning_rate()

        # train
        for i, (images, targets) in enumerate(train_data_loader):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



train-distillation.py [170:195]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    trainer.reload_checkpoint()
    evaluator = Evaluator(trainer, params)

    # evaluation
    if params.eval_only:
        scores = evaluator.run_all_evals(trainer, evals=['classif', 'recognition'], data_loader=valid_data_loader)

        for k, v in scores.items():
            logger.info('%s -> %.6f' % (k, v))
        logger.info("__log__:%s" % json.dumps(scores))
        exit()

    # training
    for epoch in range(trainer.epoch, params.epochs):

        # update epoch / sampler / learning rate
        trainer.epoch = epoch
        logger.info("============ Starting epoch %i ... ============" % trainer.epoch)
        if params.multi_gpu:
            train_sampler.set_epoch(epoch)

        # update learning rate
        trainer.update_learning_rate()

        # train
        for i, (images, targets) in enumerate(train_data_loader):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -