# ------------------------------------------------------------------------
# LW-DETR
# Copyright (c) 2024 Baidu. All Rights Reserved.
# Licensed under the Apache License, Version 2.0 [see LICENSE for details]
# ------------------------------------------------------------------------
# Conditional DETR
# Copyright (c) 2021 Microsoft. All Rights Reserved.
# Licensed under the Apache License, Version 2.0 [see LICENSE for details]
# ------------------------------------------------------------------------
# Copied from DETR (https://github.com/facebookresearch/detr)
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
# ------------------------------------------------------------------------

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

import torch
import util.misc as utils
from datasets.coco_eval import CocoEvaluator


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,
                    ema_m: torch.nn.Module=None, schedules: dict={}, 
                    num_training_steps_per_epoch=None, vit_encoder_num_layers=None, args=None):
    model.train()
    criterion.train()
    metric_logger = utils.MetricLogger(delimiter="  ")
    metric_logger.add_meter('lr', utils.SmoothedValue(window_size=1, fmt='{value:.6f}'))
    metric_logger.add_meter('class_error', utils.SmoothedValue(window_size=1, fmt='{value:.2f}'))
    header = 'Epoch: [{}]'.format(epoch)
    print_freq = 10
    start_steps=epoch * num_training_steps_per_epoch

    for data_iter_step, (samples, targets) in enumerate(metric_logger.log_every(data_loader, print_freq, header)):
        it = start_steps + data_iter_step
        if 'dp' in schedules:
            if args.distributed:
                model.module.update_drop_path(schedules['dp'][it], vit_encoder_num_layers)
            else:
                model.update_drop_path(schedules['dp'][it], vit_encoder_num_layers)
        if 'do' in schedules:
            if args.distributed:
                model.module.update_dropout(schedules['do'][it])
            else:
                model.update_dropout(schedules['do'][it])
        
        samples = samples.to(device)
        targets = [{k: v.to(device) for k, v in t.items()} for t in targets]
        
        outputs = model(samples, targets)
        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()
        if ema_m is not None:
            if epoch >= 0:
                ema_m.update(model)
        metric_logger.update(loss=loss_value, **loss_dict_reduced_scaled, **loss_dict_reduced_unscaled)
        metric_logger.update(class_error=loss_dict_reduced['class_error'])
        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, postprocessors, data_loader, base_ds, device, args = None):
    model.eval()
    if args.fp16_eval:
        model.half()
    criterion.eval()

    metric_logger = utils.MetricLogger(delimiter="  ")
    metric_logger.add_meter('class_error', utils.SmoothedValue(window_size=1, fmt='{value:.2f}'))
    header = 'Test:'

    iou_types = tuple(k for k in ('segm', 'bbox') if k in postprocessors.keys())
    coco_evaluator = CocoEvaluator(base_ds, iou_types)

    for samples, targets in metric_logger.log_every(data_loader, 10, header):
        samples = samples.to(device)
        targets = [{k: v.to(device) for k, v in t.items()} for t in targets]

        if args.fp16_eval:
            samples.tensors = samples.tensors.half()
        
        outputs = model(samples)

        if args.fp16_eval:
            for key in outputs.keys():
                if key == 'enc_outputs':
                    for sub_key in outputs[key].keys():
                        outputs[key][sub_key] = outputs[key][sub_key].float()
                elif key == 'aux_outputs':
                    for idx in range(len(outputs[key])):
                        for sub_key in outputs[key][idx].keys():
                            outputs[key][idx][sub_key] = outputs[key][idx][sub_key].float()
                else:
                    outputs[key] = outputs[key].float()

        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)
        metric_logger.update(class_error=loss_dict_reduced['class_error'])

        orig_target_sizes = torch.stack([t["orig_size"] for t in targets], dim=0)
        results = postprocessors['bbox'](outputs, orig_target_sizes)
        res = {target['image_id'].item(): output for target, output in zip(targets, results)}
        if coco_evaluator is not None:
            coco_evaluator.update(res)

    # gather the stats from all processes
    metric_logger.synchronize_between_processes()
    print("Averaged stats:", metric_logger)
    if coco_evaluator is not None:
        coco_evaluator.synchronize_between_processes()

    # accumulate predictions from all images
    if coco_evaluator is not None:
        coco_evaluator.accumulate()
        coco_evaluator.summarize()
    stats = {k: meter.global_avg for k, meter in metric_logger.meters.items()}
    if coco_evaluator is not None:
        if 'bbox' in postprocessors.keys():
            stats['coco_eval_bbox'] = coco_evaluator.coco_eval['bbox'].stats.tolist()
        if 'segm' in postprocessors.keys():
            stats['coco_eval_masks'] = coco_evaluator.coco_eval['segm'].stats.tolist()
    return stats, coco_evaluator