import argparse

import torch.distributed as dist
import torch.nn.functional as F
import torch.optim as optim
import torch.optim.lr_scheduler as lr_scheduler
import torch.utils.data
from torch.nn.parallel import DistributedDataParallel as DDP

import test  # import test.py to get mAP after each epoch
from models.yolo import Model
from utils import google_utils
from utils.datasets import *
from utils.utils import *
import torch.multiprocessing as mp

mixed_precision = True
try:  # Mixed precision training https://github.com/NVIDIA/apex
    import apex
    from apex import amp
except:
    print('Apex recommended for faster mixed precision training: https://github.com/NVIDIA/apex')
    mixed_precision = False  # not installed

# Hyperparameters
hyp = {'optimizer': 'SGD',  # ['adam', 'SGD', None] if none, default is SGD
       'lr0': 0.01,  # initial learning rate (SGD=1E-2, Adam=1E-3)
       'momentum': 0.937,  # SGD momentum/Adam beta1
       'weight_decay': 5e-4,  # optimizer weight decay
       'giou': 0.05,  # giou loss gain
       'cls': 0.5,  # cls loss gain
       'cls_pw': 1.0,  # cls BCELoss positive_weight
       'obj': 1.0,  # obj loss gain (*=img_size/320 if img_size != 320)
       'obj_pw': 1.0,  # obj BCELoss positive_weight
       'iou_t': 0.20,  # iou training threshold
       'anchor_t': 4.0,  # anchor-multiple threshold
       'fl_gamma': 0.0,  # focal loss gamma (efficientDet default is gamma=1.5)
       'hsv_h': 0.015,  # image HSV-Hue augmentation (fraction)
       'hsv_s': 0.7,  # image HSV-Saturation augmentation (fraction)
       'hsv_v': 0.4,  # image HSV-Value augmentation (fraction)
       'degrees': 0.0,  # image rotation (+/- deg)
       'translate': 0.0,  # image translation (+/- fraction)
       'scale': 0.5,  # image scale (+/- gain)
       'shear': 0.0}  # image shear (+/- deg)


def train(hyp, tb_writer, opt, device):
    print(f'Hyperparameters {hyp}')
    log_dir = tb_writer.log_dir if tb_writer else 'runs/evolution'  # run directory
    wdir = str(Path(log_dir) / 'weights') + os.sep  # weights directory
    os.makedirs(wdir, exist_ok=True)
    last = wdir + 'last.pt'
    best = wdir + 'best.pt'
    results_file = log_dir + os.sep + 'results.txt'
    epochs, batch_size, total_batch_size, weights, rank = \
        opt.epochs, opt.batch_size, opt.total_batch_size, opt.weights, opt.local_rank
    print('===============================>', rank)
    # TODO: Init DDP logging. Only the first process is allowed to log.
    # Since I see lots of print here, the logging configuration is skipped here. We may see repeated outputs.

    # Save run settings
    with open(Path(log_dir) / 'hyp.yaml', 'w') as f:
        yaml.dump(hyp, f, sort_keys=False)
    with open(Path(log_dir) / 'opt.yaml', 'w') as f:
        yaml.dump(vars(opt), f, sort_keys=False)

    # Configure
    init_seeds(2 + rank)
    with open(opt.data) as f:
        data_dict = yaml.load(f, Loader=yaml.FullLoader)  # model dict
    train_path = data_dict['train']
    test_path = data_dict['val']
    nc, names = (1, ['item']) if opt.single_cls else (int(data_dict['nc']), data_dict['names'])  # number classes, names
    assert len(names) == nc, '%g names found for nc=%g dataset in %s' % (len(names), nc, opt.data)  # check

    # Remove previous results
    if rank in [-1, 0]:
        for f in glob.glob('*_batch*.jpg') + glob.glob(results_file):
            os.remove(f)

    # Create model
    model = Model(opt.cfg, nc=nc).to(device)

    # Image sizes
    gs = int(max(model.stride))  # grid size (max stride)
    imgsz, imgsz_test = [check_img_size(x, gs) for x in opt.img_size]  # verify imgsz are gs-multiples

    # Optimizer
    nbs = 64  # nominal batch size
    # default DDP implementation is slow for accumulation according to: https://pytorch.org/docs/stable/notes/ddp.html
    # all-reduce operation is carried out during loss.backward().
    # Thus, there would be redundant all-reduce communications in a accumulation procedure,
    # which means, the result is still right but the training speed gets slower.
    # TODO: If acceleration is needed, there is an implementation of allreduce_post_accumulation
    # in https://github.com/NVIDIA/DeepLearningExamples/blob/master/PyTorch/LanguageModeling/BERT/run_pretraining.py
    accumulate = max(round(nbs / total_batch_size), 1)  # accumulate loss before optimizing
    hyp['weight_decay'] *= total_batch_size * accumulate / nbs  # scale weight_decay

    pg0, pg1, pg2 = [], [], []  # optimizer parameter groups
    for k, v in model.named_parameters():
        if v.requires_grad:
            if '.bias' in k:
                pg2.append(v)  # biases
            elif '.weight' in k and '.bn' not in k:
                pg1.append(v)  # apply weight decay
            else:
                pg0.append(v)  # all else

    if hyp['optimizer'] == 'adam':  # https://pytorch.org/docs/stable/_modules/torch/optim/lr_scheduler.html#OneCycleLR
        optimizer = optim.Adam(pg0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999))  # adjust beta1 to momentum
    else:
        if device.type == 'npu':
            optimizer = apex.optimizers.NpuFusedSGD(pg0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)
        else:
            optimizer = optim.SGD(pg0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)

    optimizer.add_param_group({'params': pg1, 'weight_decay': hyp['weight_decay']})  # add pg1 with weight_decay
    optimizer.add_param_group({'params': pg2})  # add pg2 (biases)
    print('Optimizer groups: %g .bias, %g conv.weight, %g other' % (len(pg2), len(pg1), len(pg0)))
    del pg0, pg1, pg2

    start_epoch, best_fitness = 0, 0.0
    if weights.endswith('.pt'):  # pytorch format
        ckpt = torch.load(weights, map_location=device)  # load checkpoint

        # load model
        try:
            exclude = ['anchor']  # exclude keys
            ckpt['model'] = {k: v for k, v in ckpt['model'].float().state_dict().items()
                             if k in model.state_dict() and not any(x in k for x in exclude)
                             and model.state_dict()[k].shape == v.shape}
            model.load_state_dict(ckpt['model'], strict=False)
            print('Transferred %g/%g items from %s' % (len(ckpt['model']), len(model.state_dict()), weights))
        except KeyError as e:
            s = "%s is not compatible with %s. This may be due to model differences or %s may be out of date. " \
                "Please delete or update %s and try again, or use --weights '' to train from scratch." \
                % (weights, opt.cfg, weights, weights)
            raise KeyError(s) from e

        # load optimizer
        if ckpt['optimizer'] is not None:
            optimizer.load_state_dict(ckpt['optimizer'])

        # epochs
        start_epoch = ckpt['epoch'] + 1
        if epochs < start_epoch:
            print('%s has been trained for %g epochs. Fine-tuning for %g additional epochs.' %
                  (weights, ckpt['epoch'], epochs))
            epochs += ckpt['epoch']  # finetune additional epochs

        del ckpt

    # Mixed precision training https://github.com/NVIDIA/apex
    if mixed_precision:
        if device.type == 'npu':
            model, optimizer = amp.initialize(model, optimizer, opt_level='O1', verbosity=0, loss_scale=64, combine_grad=True)
        else:
            model, optimizer = amp.initialize(model, optimizer, opt_level='O1', verbosity=0, loss_scale=64)

    # Scheduler https://arxiv.org/pdf/1812.01187.pdf
    lf = lambda x: (((1 + math.cos(x * math.pi / epochs)) / 2) ** 1.0) * 0.8 + 0.2  # cosine
    scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)
    # https://discuss.pytorch.org/t/a-problem-occured-when-resuming-an-optimizer/28822
    # plot_lr_scheduler(optimizer, scheduler, epochs)

    # SyncBatchNorm
    if opt.sync_bn and device.type != 'cpu' and rank != -1:
        model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model).to(device)
        print('Using SyncBatchNorm()')

    # Exponential moving average
    ema = torch_utils.ModelEMA(model) if rank in [-1, 0] else None

    # DDP mode
    if device.type == 'cuda' and rank != -1:
        model = DDP(model, device_ids=[rank], output_device=rank)
    elif device.type == 'npu' and rank != -1:
        model = DDP(model, device_ids=[rank], broadcast_buffers=False)

    # Trainloader
    dataloader, dataset = create_dataloader(train_path, imgsz, batch_size, gs, opt, hyp=hyp, augment=True,
                                            cache=opt.cache_images, rect=opt.rect, local_rank=rank,
                                            world_size=opt.world_size)
    mlc = np.concatenate(dataset.labels, 0)[:, 0].max()  # max label class
    nb = len(dataloader)  # number of batches
    assert mlc < nc, 'Label class %g exceeds nc=%g in %s. Possible class labels are 0-%g' % (mlc, nc, opt.data, nc - 1)

    # Model parameters
    hyp['cls'] *= nc / 80.  # scale coco-tuned hyp['cls'] to current dataset
    model.nc = nc  # attach number of classes to model
    model.hyp = hyp  # attach hyperparameters to model
    model.gr = 1.0  # giou loss ratio (obj_loss = 1.0 or giou)
    model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device)  # attach class weights
    model.names = names

    # Class frequency
    if rank in [-1, 0]:
        labels = np.concatenate(dataset.labels, 0)
        c = torch.tensor(labels[:, 0])  # classes
        # cf = torch.bincount(c.long(), minlength=nc) + 1.
        # model._initialize_biases(cf.to(device))
        plot_labels(labels, save_dir=log_dir)
        if tb_writer:
            # tb_writer.add_hparams(hyp, {})  # causes duplicate https://github.com/ultralytics/yolov5/pull/384
            tb_writer.add_histogram('classes', c, 0)

        # Check anchors
        if not opt.noautoanchor:
            check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz)

    # Start training
    t0 = time.time()
    nw = max(3 * nb, 1e3)  # number of warmup iterations, max(3 epochs, 1k iterations)
    maps = np.zeros(nc)  # mAP per class
    results = (0, 0, 0, 0, 0, 0, 0)  # 'P', 'R', 'mAP', 'F1', 'val GIoU', 'val Objectness', 'val Classification'
    scheduler.last_epoch = start_epoch - 1  # do not move
    if rank in [0, -1]:
        print('Image sizes %g train, %g test' % (imgsz, imgsz_test))
        print('Using %g dataloader workers' % dataloader.num_workers)
        print('Starting training for %g epochs...' % epochs)
    # torch.autograd.set_detect_anomaly(True)
    for epoch in range(start_epoch, epochs):  # epoch ------------------------------------------------------------------
        model.train()

        # Update image weights (optional)
        # When in DDP mode, the generated indices will be broadcasted to synchronize dataset.
        if dataset.image_weights:
            # Generate indices.
            if rank in [-1, 0]:
                w = model.class_weights.cpu().numpy() * (1 - maps) ** 2  # class weights
                image_weights = labels_to_image_weights(dataset.labels, nc=nc, class_weights=w)
                dataset.indices = random.choices(range(dataset.n), weights=image_weights,
                                                 k=dataset.n)  # rand weighted idx
            # Broadcast.
            if rank != -1:
                indices = torch.zeros([dataset.n], dtype=torch.int)
                if rank == 0:
                    indices[:] = torch.from_tensor(dataset.indices, dtype=torch.int)
                dist.broadcast(indices, 0)
                if rank != 0:
                    dataset.indices = indices.cpu().numpy()

        # Update mosaic border
        # b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs)
        # dataset.mosaic_border = [b - imgsz, -b]  # height, width borders

        mloss = torch.zeros(4, device=device)  # mean losses
        if rank != -1:
            dataloader.sampler.set_epoch(epoch)
        optimizer.zero_grad()
        start_time = time.time()
        d_1 = time.time()
        for i, (imgs, targets, paths, _) in enumerate(dataloader):  # batch -------------------------------------------
            t_time = time.time()
            d_time = t_time - d_1
            ni = i + nb * epoch  # number integrated batches (since train start)
            imgs = imgs.to(device, non_blocking=True).float() / 255.0  # uint8 to float32, 0 - 255 to 0.0 - 1.0

            # Warmup
            if ni <= nw:
                xi = [0, nw]  # x interp
                # model.gr = np.interp(ni, xi, [0.0, 1.0])  # giou loss ratio (obj_loss = 1.0 or giou)
                accumulate = max(1, np.interp(ni, xi, [1, nbs / total_batch_size]).round())
                for j, x in enumerate(optimizer.param_groups):
                    # bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0
                    x['lr'] = np.interp(ni, xi, [0.1 if j == 2 else 0.0, x['initial_lr'] * lf(epoch)])
                    if 'momentum' in x:
                        x['momentum'] = np.interp(ni, xi, [0.9, hyp['momentum']])

            # Multi-scale
            if opt.multi_scale:
                sz = random.randrange(imgsz * 0.5, imgsz * 1.5 + gs) // gs * gs  # size
                sf = sz / max(imgs.shape[2:])  # scale factor
                if sf != 1:
                    ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]]  # new shape (stretched to gs-multiple)
                    imgs = F.interpolate(imgs, size=ns, mode='bilinear', align_corners=False)

            # Forward
            pred = model(imgs)

            # Loss
            loss, loss_items = compute_loss(pred, targets.to(device), model)  # scaled by batch_size
            if rank != -1:
                loss *= opt.world_size  # gradient averaged between devices in DDP mode
            if not torch.isfinite(loss):
                print('WARNING: non-finite loss, ending training ', loss_items)
                return results

            # Backward
            if mixed_precision:
                with amp.scale_loss(loss, optimizer) as scaled_loss:
                    scaled_loss.backward()
            else:
                loss.backward()

            # Optimize
            if ni % accumulate == 0:
                optimizer.step()
                optimizer.zero_grad()
                if ema is not None:
                    x = torch.tensor([1.]).to(device)
                    if device.type == 'npu':
                        params_fp32_fused = optimizer.get_model_combined_params()
                        ema.update(model, x, params_fp32_fused[0])
                    else:
                        ema.update(model, x)

            if i <= 10:
                sum_time = (time.time() - start_time) / (i + 1)
                if i == 10:
                    start_time = time.time()
            else:
                sum_time = (time.time() - start_time) / (i - 10)
            ptime = time.time() - d_1
            # Print
            if rank in [-1, 0]:
                mloss = (mloss * i + loss_items) / (i + 1)  # update mean losses
                mem = '%.3gG' % (torch.cuda.memory_cached() / 1E9 if torch.cuda.is_available() else 0)  # (GB)
                s = ('%10s' * 2 + '%10.4g' * 6) % (
                    '%g/%g' % (epoch, epochs - 1), mem, *mloss, targets.shape[0], imgs.shape[-1])
                print(
                    'Epoch:[%2g][%4g/%4g][%s][FPS:%3.1f][mTime:%3.3f][pTime:%3.3f][dTime:%3.3f] GIoU:%.3f objectness:%.3f classfication:%.3f totalLoss:%.3f' % (
                    epoch, i, nb, device, opt.total_batch_size / sum_time, sum_time, ptime, d_time, *mloss))

                # Plot
                if ni < 3:
                    f = str(Path(log_dir) / ('train_batch%g.jpg' % ni))  # filename
                    result = plot_images(images=imgs, targets=targets, paths=paths, fname=f)
                    if tb_writer and result is not None:
                        tb_writer.add_image(f, result, dataformats='HWC', global_step=epoch)
                        # tb_writer.add_graph(model, imgs)  # add model to tensorboard

            d_1 = time.time()
            # end batch ------------------------------------------------------------------------------------------------

        # Scheduler
        scheduler.step()

        # save every epoch
        if rank in [-1, 0]:
            final_epoch = epoch + 1 == epochs
            ckpt = {
                    'epoch': epoch,
                    'model': ema.ema.module if hasattr(ema, 'module') else ema.ema,
                    'optimizer': None if final_epoch else optimizer.state_dict()
            }
            torch.save(ckpt, 'yolov5_' + str(rank) + '.pt')
            print('ckpt saved...')

        # end epoch ----------------------------------------------------------------------------------------------------
    # end training

    if rank in [-1, 0]:
        # Strip optimizers
        n = ('_' if len(opt.name) and not opt.name.isnumeric() else '') + opt.name
        fresults, flast, fbest = 'results%s.txt' % n, wdir + 'last%s.pt' % n, wdir + 'best%s.pt' % n
        for f1, f2 in zip([wdir + 'last.pt', wdir + 'best.pt', 'results.txt'], [flast, fbest, fresults]):
            if os.path.exists(f1):
                os.rename(f1, f2)  # rename
                ispt = f2.endswith('.pt')  # is *.pt
                strip_optimizer(f2) if ispt else None  # strip optimizer
                os.system('gsutil cp %s gs://%s/weights' % (f2, opt.bucket)) if opt.bucket and ispt else None  # upload
        # Finish
        if not opt.evolve:
            plot_results(save_dir=log_dir)  # save as results.png
        print('%g epochs completed in %.3f hours.\n' % (epoch - start_epoch + 1, (time.time() - t0) / 3600))

    dist.destroy_process_group() if rank not in [-1, 0] else None
    torch.cuda.empty_cache()
    return results


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('--cfg', type=str, default='models/yolov5s.yaml', help='model.yaml path')
    parser.add_argument('--data', type=str, default='data/coco128.yaml', help='data.yaml path')
    parser.add_argument('--hyp', type=str, default='', help='hyp.yaml path (optional)')
    parser.add_argument('--epochs', type=int, default=300)
    parser.add_argument('--batch-size', type=int, default=16, help="Total batch size for all gpus.")
    parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='train,test sizes')
    parser.add_argument('--rect', action='store_true', help='rectangular training')
    parser.add_argument('--resume', nargs='?', const='get_last', default=False,
                        help='resume from given path/to/last.pt, or most recent run if blank.')
    parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
    parser.add_argument('--notest', action='store_true', help='only test final epoch')
    parser.add_argument('--noautoanchor', action='store_true', help='disable autoanchor check')
    parser.add_argument('--evolve', action='store_true', help='evolve hyperparameters')
    parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
    parser.add_argument('--cache-images', action='store_true', help='cache images for faster training')
    parser.add_argument('--weights', type=str, default='', help='initial weights path')
    parser.add_argument('--name', default='', help='renames results.txt to results_name.txt if supplied')
    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu or npu')
    parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
    parser.add_argument('--single-cls', action='store_true', help='train as single-class dataset')
    parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
    parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')
    parser.add_argument('--npu', default=-1, type=int, help='NPU id to use.')
    parser.add_argument('--eval-freq', default=1, type=int, help='do evaluation per eval_freq training iteration.')

    # NPU DDP mode
    parser.add_argument('--world-size', default=1, type=int, help='number of nodes for distributed training')
    parser.add_argument('--device-num', default=1, type=int, help='multi NPU parameter, GPU or CPU do not modify')
    parser.add_argument('--addr', default='90.90.176.102', type=str, help='DDP master node IP')
    parser.add_argument('--dist-url', default='tcp://224.66.41.62:23456', type=str,
                        help='url used to set up distributed training')
    opt = parser.parse_args()

    if opt.dist_url == "env://":
        opt.world_size = int(os.environ["WORLD_SIZE"])
    ngpus_per_node = opt.device_num
    opt.npu_ddp = (opt.device_num > 1 or opt.world_size > 1)
    if opt.npu_ddp:
        print('multi npu training')
        os.environ['MASTER_ADDR'] = opt.addr  # master ip
        os.environ['MASTER_PORT'] = '29501'
        os.environ['KERNEL_NAME_ID'] = str(0)
        opt.world_size = ngpus_per_node * opt.world_size  # the sum of GPU or NPU in all the nodes
        main_worker(opt)
    else:
        print('multi npu training failed to init...')

def main_worker(opt):
    if opt.npu_ddp:
        opt.npu = opt.local_rank
        os.environ['KERNEL_NAME_ID'] = str(opt.local_rank)
        print("[npu id:", opt.local_rank, "]", "+++++++++++++++++++++++++++KERNEL_NAME_ID:", os.environ['KERNEL_NAME_ID'])
    last = get_latest_run() if opt.resume == 'get_last' else opt.resume  # resume from most recent run
    if last and not opt.weights:
        print(f'Resuming training from {last}')
    opt.weights = last if opt.resume and not opt.weights else opt.weights
    opt.cfg = check_file(opt.cfg)  # check file
    opt.data = check_file(opt.data)  # check file
    if opt.hyp:  # update hyps
        opt.hyp = check_file(opt.hyp)  # check file
        with open(opt.hyp) as f:
            hyp.update(yaml.load(f, Loader=yaml.FullLoader))  # update hyps
    opt.img_size.extend([opt.img_size[-1]] * (2 - len(opt.img_size)))  # extend to 2 sizes (train, test)
    global mixed_precision
    device = torch_utils.select_device(opt.device, opt.local_rank, apex=mixed_precision, batch_size=opt.batch_size)
    opt.total_batch_size = opt.batch_size
    if device.type == 'cpu':
        mixed_precision = False
    elif opt.local_rank != -1 and device.type == 'cuda':
        # DDP mode
        assert torch.cuda.device_count() > opt.local_rank
        torch.cuda.set_device(opt.local_rank)
        device = torch.device("cuda", opt.local_rank)
        dist.init_process_group(backend='nccl', init_method='env://')  # distributed backend

        opt.world_size = dist.get_world_size()
        assert opt.batch_size % opt.world_size == 0, "Batch size is not a multiple of the number of devices given!"
        opt.batch_size = opt.total_batch_size // opt.world_size
    elif opt.local_rank != -1 and device.type == 'npu':
        dist.init_process_group(backend='hccl', world_size=opt.world_size, rank=opt.local_rank)
        assert opt.batch_size % opt.world_size == 0, "Batch size is not a multiple of the number of devices given!"
        opt.batch_size = opt.total_batch_size // opt.world_size
    print(opt)

    # Train
    if not opt.evolve:
        if opt.local_rank in [-1, 0]:
            print('Start Tensorboard with "tensorboard --logdir=runs", view at http://localhost:6006/')
            tb_writer = None
        else:
            tb_writer = None
        train(hyp, tb_writer, opt, device)

    # Evolve hyperparameters (optional)
    else:
        assert opt.local_rank == -1, "DDP mode currently not implemented for Evolve!"

        tb_writer = None
        opt.notest, opt.nosave = True, True  # only test/save final epoch
        if opt.bucket:
            os.system('gsutil cp gs://%s/evolve.txt .' % opt.bucket)  # download evolve.txt if exists

        for _ in range(10):  # generations to evolve
            if os.path.exists('evolve.txt'):  # if evolve.txt exists: select best hyps and mutate
                # Select parent(s)
                parent = 'single'  # parent selection method: 'single' or 'weighted'
                x = np.loadtxt('evolve.txt', ndmin=2)
                n = min(5, len(x))  # number of previous results to consider
                x = x[np.argsort(-fitness(x))][:n]  # top n mutations
                w = fitness(x) - fitness(x).min()  # weights
                if parent == 'single' or len(x) == 1:
                    # x = x[random.randint(0, n - 1)]  # random selection
                    x = x[random.choices(range(n), weights=w)[0]]  # weighted selection
                elif parent == 'weighted':
                    x = (x * w.reshape(n, 1)).sum(0) / w.sum()  # weighted combination

                # Mutate
                mp, s = 0.9, 0.2  # mutation probability, sigma
                npr = np.random
                npr.seed(int(time.time()))
                g = np.array([1, 1, 1, 1, 1, 1, 1, 0, .1, 1, 0, 1, 1, 1, 1, 1, 1, 1])  # gains
                ng = len(g)
                v = np.ones(ng)
                while all(v == 1):  # mutate until a change occurs (prevent duplicates)
                    v = (g * (npr.random(ng) < mp) * npr.randn(ng) * npr.random() * s + 1).clip(0.3, 3.0)
                for i, k in enumerate(hyp.keys()):  # plt.hist(v.ravel(), 300)
                    hyp[k] = x[i + 7] * v[i]  # mutate

            # Clip to limits
            keys = ['lr0', 'iou_t', 'momentum', 'weight_decay', 'hsv_s', 'hsv_v', 'translate', 'scale', 'fl_gamma']
            limits = [(1e-5, 1e-2), (0.00, 0.70), (0.60, 0.98), (0, 0.001), (0, .9), (0, .9), (0, .9), (0, .9), (0, 3)]
            for k, v in zip(keys, limits):
                hyp[k] = np.clip(hyp[k], v[0], v[1])

            # Train mutation
            results = train(hyp.copy(), tb_writer, opt, device)

            # Write mutation results
            print_mutation(hyp, results, opt.bucket)

            # Plot results
            # plot_evolution_results(hyp)

if __name__ == '__main__':
    main()