Function do_train

tools/plain_train_net.py:126–189

(cfg, model, resume=False)

def do_train(cfg, model, resume=False):
    model.train()
    optimizer = build_optimizer(cfg, model)
    scheduler = build_lr_scheduler(cfg, optimizer)

    checkpointer = DetectionCheckpointer(
        model, cfg.OUTPUT_DIR, optimizer=optimizer, scheduler=scheduler
    )
    start_iter = (
        checkpointer.resume_or_load(cfg.MODEL.WEIGHTS, resume=resume).get("iteration", -1) + 1
    )
    max_iter = cfg.SOLVER.MAX_ITER

    periodic_checkpointer = PeriodicCheckpointer(
        checkpointer, cfg.SOLVER.CHECKPOINT_PERIOD, max_iter=max_iter
    )

    writers = (
        [
            CommonMetricPrinter(max_iter),
            JSONWriter(os.path.join(cfg.OUTPUT_DIR, "metrics.json")),
            TensorboardXWriter(cfg.OUTPUT_DIR),
        ]
        if comm.is_main_process()
        else []
    )

    # compared to "train_net.py", we do not support accurate timing and
    # precise BN here, because they are not trivial to implement in a small training loop
    data_loader = build_detection_train_loader(cfg)
    logger.info("Starting training from iteration {}".format(start_iter))
    with EventStorage(start_iter) as storage:
        for data, iteration in zip(data_loader, range(start_iter, max_iter)):
            iteration = iteration + 1
            storage.step()

            loss_dict = model(data)
            losses = sum(loss_dict.values())
            assert torch.isfinite(losses).all(), loss_dict

            loss_dict_reduced = {k: v.item() for k, v in comm.reduce_dict(loss_dict).items()}
            losses_reduced = sum(loss for loss in loss_dict_reduced.values())
            if comm.is_main_process():
                storage.put_scalars(total_loss=losses_reduced, **loss_dict_reduced)

            optimizer.zero_grad()
            losses.backward()
            optimizer.step()
            storage.put_scalar("lr", optimizer.param_groups[0]["lr"], smoothing_hint=False)
            scheduler.step()

            if (
                cfg.TEST.EVAL_PERIOD > 0
                and iteration % cfg.TEST.EVAL_PERIOD == 0
                and iteration != max_iter
            ):
                do_test(cfg, model)
                # Compared to "train_net.py", the test results are not dumped to EventStorage