engine.py

"""
Train and eval functions used in main.py
"""
import math
import os
import sys
from typing import Iterable

import torch

import util.misc as utils

def to_device(data, device):
    if type(data) == dict:
        return {k: v.to(device) for k, v in data.items()}
    return [{k: v.to(device) if isinstance(v, torch.Tensor) else v
             for k, v in t.items()} for t in data]
    

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 samples, extra_samples, targets in metric_logger.log_every(data_loader, print_freq, header):
        samples = samples.to(device)
        extra_samples = to_device(extra_samples, device)
        targets = to_device(targets, device)

        outputs, extra_info = model(samples, extra_samples)
        loss_dict = criterion(outputs, targets)
        weight_dict = criterion.weight_dict
        losses = sum(loss_dict[k] * weight_dict[k] for k in loss_dict.keys() if k in weight_dict)

        # reduce losses over all GPUs for logging purposes
        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:
            torch.nn.utils.clip_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"])
    # gather the stats from all processes
    metric_logger.synchronize_between_processes()
    print("Averaged stats:", metric_logger)
    return {k: meter.global_avg for k, meter in metric_logger.meters.items()}


@torch.no_grad()
def evaluate(model, criterion, data_loader, device, output_dir):
    model.eval()
    criterion.eval()

    metric_logger = utils.MetricLogger(delimiter="  ")    
    header = 'Val:'

    for samples, extra_samples, targets in metric_logger.log_every(data_loader, 10, header):
        samples = samples.to(device)
        extra_samples = to_device(extra_samples, device)
        targets = to_device(targets, device)

        outputs, extra_info = model(samples, extra_samples)
        loss_dict = criterion(outputs, targets)
        weight_dict = criterion.weight_dict

        # reduce losses over all GPUs for logging purposes
        loss_dict_reduced = utils.reduce_dict(loss_dict)
        loss_dict_reduced_scaled = {k: v * weight_dict[k]
                                    for k, v in loss_dict_reduced.items() if k in weight_dict}
        loss_dict_reduced_unscaled = {f'{k}_unscaled': v
                                      for k, v in loss_dict_reduced.items()}
        metric_logger.update(loss=sum(loss_dict_reduced_scaled.values()),
                             **loss_dict_reduced_scaled,
                             **loss_dict_reduced_unscaled)
       
    # gather the stats from all processes
    metric_logger.synchronize_between_processes()
    print("Averaged stats:", metric_logger)
    stats = {k: meter.global_avg for k, meter in metric_logger.meters.items()}
    return stats