ytvos_engine.py

import math
import sys
from typing import Iterable
import torch
import util.misc as utils


def train_one_epoch(model: torch.nn.Module, criterion: torch.nn.Module,
                    data_loader: Iterable, optimizer: torch.optim.Optimizer,
                    device: torch.device, epoch: int, max_norm: float = 0,  ):
    model.train()
    criterion.train()
    metric_logger = utils.MetricLogger(delimiter="  ")
    metric_logger.add_meter('lr', utils.SmoothedValue(window_size=1, fmt='{value:.6f}'))
    header = 'Epoch: [{}]'.format(epoch)
    print_freq = 10
    for qsamples, qtargets, ssamples, stargets,  _ in metric_logger.log_every(data_loader, print_freq, header):
        ssamples = ssamples.to(device)
        scaptions = [t["caption"] for t in stargets]
        stargets = utils.targets_to(stargets, device)

        qsamples = qsamples.to(device)
        q_captions = [t["caption"] for t in qtargets]
        qtargets = utils.targets_to(qtargets, device)
        outputs = model(qsamples, q_captions, qtargets, ssamples, scaptions, stargets)
        loss_dict = criterion(outputs, qtargets)

        weight_dict = criterion.weight_dict
        losses = sum(loss_dict[k] * weight_dict[k] for k in loss_dict.keys() if k in weight_dict)


        loss_dict_reduced = utils.reduce_dict(loss_dict)
        loss_dict_reduced_unscaled = {f'{k}_unscaled': v
                                      for k, v in loss_dict_reduced.items()}
        loss_dict_reduced_scaled = {k: v * weight_dict[k]
                                    for k, v in loss_dict_reduced.items() if k in weight_dict}
        losses_reduced_scaled = sum(loss_dict_reduced_scaled.values())

        loss_value = losses_reduced_scaled.item()
        if not math.isfinite(loss_value):
            print("Loss is {}, stopping training".format(loss_value))
            print(loss_dict_reduced)
            sys.exit(1)
        optimizer.zero_grad()
        losses.backward()
        if max_norm > 0:
            grad_total_norm = torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm)
        else:
            grad_total_norm = utils.get_total_grad_norm(model.parameters(), max_norm)
        optimizer.step()

        metric_logger.update(loss=loss_value, **loss_dict_reduced_scaled, **loss_dict_reduced_unscaled)
        metric_logger.update(lr=optimizer.param_groups[0]["lr"])
        metric_logger.update(grad_norm=grad_total_norm)


    metric_logger.synchronize_between_processes()
    print("Averaged stats:", metric_logger)
    return {k: meter.global_avg for k, meter in metric_logger.meters.items()}