河道漂浮物识别 YOLOv8

河道漂浮物识别根据智能视频分析，河道漂浮物识别自动分析识别视频图像信息内容，不用人工干涉；河道漂浮物识别监控区域里的河面漂浮物，出现异常状况时更快开展预警信息，真真正正完成预警信息、正常的检验、规范化管理，合理帮助管理者最大限度地降低乱报和少报；还能够查询视频录像，便捷过后管理方法查看。

YOLOv8 算法的核心特性和改动可以归结为如下：

提供了一个全新的 SOTA 模型，包括 P5 640 和 P6 1280 分辨率的目标检测网络和基于 YOLACT 的实例分割模型。和 YOLOv5 一样，基于缩放系数也提供了 N/S/M/L/X 尺度的不同大小模型，用于满足不同场景需求

Backbone:
骨干网络和 Neck 部分可能参考了 YOLOv7 ELAN 设计思想，将 YOLOv5 的 C3 结构换成了梯度流更丰富的 C2f 结构，并对不同尺度模型调整了不同的通道数。

Head： Head部分较yolov5而言有两大改进：1）换成了目前主流的解耦头结构(Decoupled-Head)，将分类和检测头分离 2）同时也从 Anchor-Based 换成了 Anchor-Free

Loss ：1) YOLOv8抛弃了以往的IOU匹配或者单边比例的分配方式，而是使用了Task-Aligned Assigner正负样本匹配方式。2）并引入了 Distribution Focal Loss(DFL)

Train:训练的数据增强部分引入了 YOLOX 中的最后 10 epoch 关闭 Mosiac 增强的操作，可以有效地提升精度

河流水面上的漂浮物顺着河流降低，易于集聚在河流的凹岸和堤坝前。它不但对池河的水体、水景观、供电、海产品、航运业等造成不利影响，并且降低了水电工程核心区的发电效率，对核心区的运转安全性构成了威协。视河流漂浮物识别实时监测河流和湖水地区。当检测到水面上面有很多废弃物时，直接警报并通告管理者及时处理。与此同时，将警报截屏和视频保存到数据表中，生成汇报并发送给有关管理者。以后可依据时间范围查看播放报警记录和警报截屏，进一步提高检测地区的操纵高效率，合理处理大城市水问题，提升地区水管理水平。

# Ultralytics YOLO 🚀, GPL-3.0 license
from copy import copy

import numpy as np
import torch
import torch.nn as nn

from ultralytics.nn.tasks import DetectionModel
from ultralytics.yolo import v8
from ultralytics.yolo.data import build_dataloader
from ultralytics.yolo.data.dataloaders.v5loader import create_dataloader
from ultralytics.yolo.engine.trainer import BaseTrainer
from ultralytics.yolo.utils import DEFAULT_CFG, RANK, colorstr
from ultralytics.yolo.utils.loss import BboxLoss
from ultralytics.yolo.utils.ops import xywh2xyxy
from ultralytics.yolo.utils.plotting import plot_images, plot_labels, plot_results
from ultralytics.yolo.utils.tal import TaskAlignedAssigner, dist2bbox, make_anchors
from ultralytics.yolo.utils.torch_utils import de_parallel


# BaseTrainer python usage
class DetectionTrainer(BaseTrainer):

    def get_dataloader(self, dataset_path, batch_size, mode='train', rank=0):
        # TODO: manage splits differently
        # calculate stride - check if model is initialized
        gs = max(int(de_parallel(self.model).stride.max() if self.model else 0), 32)
        return create_dataloader(path=dataset_path,
                                 imgsz=self.args.imgsz,
                                 batch_size=batch_size,
                                 stride=gs,
                                 hyp=vars(self.args),
                                 augment=mode == 'train',
                                 cache=self.args.cache,
                                 pad=0 if mode == 'train' else 0.5,
                                 rect=self.args.rect or mode == 'val',
                                 rank=rank,
                                 workers=self.args.workers,
                                 close_mosaic=self.args.close_mosaic != 0,
                                 prefix=colorstr(f'{mode}: '),
                                 shuffle=mode == 'train',
                                 seed=self.args.seed)[0] if self.args.v5loader else \
            build_dataloader(self.args, batch_size, img_path=dataset_path, stride=gs, rank=rank, mode=mode,
                             rect=mode == 'val', names=self.data['names'])[0]

    def preprocess_batch(self, batch):
        batch['img'] = batch['img'].to(self.device, non_blocking=True).float() / 255
        return batch

    def set_model_attributes(self):
        # nl = de_parallel(self.model).model[-1].nl  # number of detection layers (to scale hyps)
        # self.args.box *= 3 / nl  # scale to layers
        # self.args.cls *= self.data["nc"] / 80 * 3 / nl  # scale to classes and layers
        # self.args.cls *= (self.args.imgsz / 640) ** 2 * 3 / nl  # scale to image size and layers
        self.model.nc = self.data['nc']  # attach number of classes to model
        self.model.names = self.data['names']  # attach class names to model
        self.model.args = self.args  # attach hyperparameters to model
        # TODO: self.model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc

    def get_model(self, cfg=None, weights=None, verbose=True):
        model = DetectionModel(cfg, ch=3, nc=self.data['nc'], verbose=verbose and RANK == -1)
        if weights:
            model.load(weights)

        return model

    def get_validator(self):
        self.loss_names = 'box_loss', 'cls_loss', 'dfl_loss'
        return v8.detect.DetectionValidator(self.test_loader, save_dir=self.save_dir, args=copy(self.args))

    def criterion(self, preds, batch):
        if not hasattr(self, 'compute_loss'):
            self.compute_loss = Loss(de_parallel(self.model))
        return self.compute_loss(preds, batch)

    def label_loss_items(self, loss_items=None, prefix='train'):
        """
        Returns a loss dict with labelled training loss items tensor
        """
        # Not needed for classification but necessary for segmentation & detection
        keys = [f'{prefix}/{x}' for x in self.loss_names]
        if loss_items is not None:
            loss_items = [round(float(x), 5) for x in loss_items]  # convert tensors to 5 decimal place floats
            return dict(zip(keys, loss_items))
        else:
            return keys

    def progress_string(self):
        return ('\n' + '%11s' *
                (4 + len(self.loss_names))) % ('Epoch', 'GPU_mem', *self.loss_names, 'Instances', 'Size')

    def plot_training_samples(self, batch, ni):
        plot_images(images=batch['img'],
                    batch_idx=batch['batch_idx'],
                    cls=batch['cls'].squeeze(-1),
                    bboxes=batch['bboxes'],
                    paths=batch['im_file'],
                    fname=self.save_dir / f'train_batch{ni}.jpg')

    def plot_metrics(self):
        plot_results(file=self.csv)  # save results.png

    def plot_training_labels(self):
        boxes = np.concatenate([lb['bboxes'] for lb in self.train_loader.dataset.labels], 0)
        cls = np.concatenate([lb['cls'] for lb in self.train_loader.dataset.labels], 0)
        plot_labels(boxes, cls.squeeze(), names=self.data['names'], save_dir=self.save_dir)


# Criterion class for computing training losses
class Loss:

    def __init__(self, model):  # model must be de-paralleled

        device = next(model.parameters()).device  # get model device
        h = model.args  # hyperparameters

        m = model.model[-1]  # Detect() module
        self.bce = nn.BCEWithLogitsLoss(reduction='none')
        self.hyp = h
        self.stride = m.stride  # model strides
        self.nc = m.nc  # number of classes
        self.no = m.no
        self.reg_max = m.reg_max
        self.device = device

        self.use_dfl = m.reg_max > 1
        roll_out_thr = h.min_memory if h.min_memory > 1 else 64 if h.min_memory else 0  # 64 is default

        self.assigner = TaskAlignedAssigner(topk=10,
                                            num_classes=self.nc,
                                            alpha=0.5,
                                            beta=6.0,
                                            roll_out_thr=roll_out_thr)
        self.bbox_loss = BboxLoss(m.reg_max - 1, use_dfl=self.use_dfl).to(device)
        self.proj = torch.arange(m.reg_max, dtype=torch.float, device=device)

    def preprocess(self, targets, batch_size, scale_tensor):
        if targets.shape[0] == 0:
            out = torch.zeros(batch_size, 0, 5, device=self.device)
        else:
            i = targets[:, 0]  # image index
            _, counts = i.unique(return_counts=True)
            out = torch.zeros(batch_size, counts.max(), 5, device=self.device)
            for j in range(batch_size):
                matches = i == j
                n = matches.sum()
                if n:
                    out[j, :n] = targets[matches, 1:]
            out[..., 1:5] = xywh2xyxy(out[..., 1:5].mul_(scale_tensor))
        return out

    def bbox_decode(self, anchor_points, pred_dist):
        if self.use_dfl:
            b, a, c = pred_dist.shape  # batch, anchors, channels
            pred_dist = pred_dist.view(b, a, 4, c // 4).softmax(3).matmul(self.proj.type(pred_dist.dtype))
            # pred_dist = pred_dist.view(b, a, c // 4, 4).transpose(2,3).softmax(3).matmul(self.proj.type(pred_dist.dtype))
            # pred_dist = (pred_dist.view(b, a, c // 4, 4).softmax(2) * self.proj.type(pred_dist.dtype).view(1, 1, -1, 1)).sum(2)
        return dist2bbox(pred_dist, anchor_points, xywh=False)

    def __call__(self, preds, batch):
        loss = torch.zeros(3, device=self.device)  # box, cls, dfl
        feats = preds[1] if isinstance(preds, tuple) else preds
        pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split(
            (self.reg_max * 4, self.nc), 1)

        pred_scores = pred_scores.permute(0, 2, 1).contiguous()
        pred_distri = pred_distri.permute(0, 2, 1).contiguous()

        dtype = pred_scores.dtype
        batch_size = pred_scores.shape[0]
        imgsz = torch.tensor(feats[0].shape[2:], device=self.device, dtype=dtype) * self.stride[0]  # image size (h,w)
        anchor_points, stride_tensor = make_anchors(feats, self.stride, 0.5)

        # targets
        targets = torch.cat((batch['batch_idx'].view(-1, 1), batch['cls'].view(-1, 1), batch['bboxes']), 1)
        targets = self.preprocess(targets.to(self.device), batch_size, scale_tensor=imgsz[[1, 0, 1, 0]])
        gt_labels, gt_bboxes = targets.split((1, 4), 2)  # cls, xyxy
        mask_gt = gt_bboxes.sum(2, keepdim=True).gt_(0)

        # pboxes
        pred_bboxes = self.bbox_decode(anchor_points, pred_distri)  # xyxy, (b, h*w, 4)

        _, target_bboxes, target_scores, fg_mask, _ = self.assigner(
            pred_scores.detach().sigmoid(), (pred_bboxes.detach() * stride_tensor).type(gt_bboxes.dtype),
            anchor_points * stride_tensor, gt_labels, gt_bboxes, mask_gt)

        target_bboxes /= stride_tensor
        target_scores_sum = max(target_scores.sum(), 1)

        # cls loss
        # loss[1] = self.varifocal_loss(pred_scores, target_scores, target_labels) / target_scores_sum  # VFL way
        loss[1] = self.bce(pred_scores, target_scores.to(dtype)).sum() / target_scores_sum  # BCE

        # bbox loss
        if fg_mask.sum():
            loss[0], loss[2] = self.bbox_loss(pred_distri, pred_bboxes, anchor_points, target_bboxes, target_scores,
                                              target_scores_sum, fg_mask)

        loss[0] *= self.hyp.box  # box gain
        loss[1] *= self.hyp.cls  # cls gain
        loss[2] *= self.hyp.dfl  # dfl gain

        return loss.sum() * batch_size, loss.detach()  # loss(box, cls, dfl)


def train(cfg=DEFAULT_CFG, use_python=False):
    model = cfg.model or './yolov8s.pt'
    data = cfg.data or './data/bicycle.yaml'  # or yolo.ClassificationDataset("mnist")
    device = cfg.device if cfg.device is not None else ''

    args = dict(model=model, data=data, device=[0,1,2,3])
    #args = dict(model=model, data=data, device=device)
    if use_python:
        from ultralytics import YOLO
        YOLO(model).train(**args)
    else:
        trainer = DetectionTrainer(overrides=args)
        trainer.train()


if __name__ == '__main__':
    train()

水环境治理难题一直遭受世界各国人们的高度关注。水面上的飘浮废弃物不仅仅会造成消极的视觉冲击，还会继续常常造成水质问题；河面漂浮物危害水口，威协运作安全性；阻拦船只出航，威协航运业安全性；破坏生态环境，威协生活饮水安全。浮物检验报警设备可及时处理异常事件，实时监测预警信息，实时检测分辨湖水周边的浮物。与此同时，前沿机器设备与后台管理连动，初次搜集、传送、分析数据，为河流和水利枢纽主管给予更形象化的数据支持，为指挥者给予迅速、更全方位的重要依据。