yolov8推理由avi改为mp4

修改\ultralytics-main\ultralytics\engine\predictor.py,即可

# Ultralytics YOLO 🚀, AGPL-3.0 license
"""
Run prediction on images, videos, directories, globs, YouTube, webcam, streams, etc.Usage - sources:$ yolo mode=predict model=yolov8n.pt source=0                               # webcamimg.jpg                         # imagevid.mp4                         # videoscreen                          # screenshotpath/                           # directorylist.txt                        # list of imageslist.streams                    # list of streams'path/*.jpg'                    # glob'https://youtu.be/LNwODJXcvt4'  # YouTube'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP, TCP streamUsage - formats:$ yolo mode=predict model=yolov8n.pt                 # PyTorchyolov8n.torchscript        # TorchScriptyolov8n.onnx               # ONNX Runtime or OpenCV DNN with dnn=Trueyolov8n_openvino_model     # OpenVINOyolov8n.engine             # TensorRTyolov8n.mlpackage          # CoreML (macOS-only)yolov8n_saved_model        # TensorFlow SavedModelyolov8n.pb                 # TensorFlow GraphDefyolov8n.tflite             # TensorFlow Liteyolov8n_edgetpu.tflite     # TensorFlow Edge TPUyolov8n_paddle_model       # PaddlePaddleyolov8n_ncnn_model         # NCNN
"""import platform
import re
import threading
from pathlib import Pathimport cv2
import numpy as np
import torchfrom ultralytics.cfg import get_cfg, get_save_dir
from ultralytics.data import load_inference_source
from ultralytics.data.augment import LetterBox, classify_transforms
from ultralytics.nn.autobackend import AutoBackend
from ultralytics.utils import DEFAULT_CFG, LOGGER, MACOS, WINDOWS, callbacks, colorstr, ops
from ultralytics.utils.checks import check_imgsz, check_imshow
from ultralytics.utils.files import increment_path
from ultralytics.utils.torch_utils import select_device, smart_inference_modeSTREAM_WARNING = """
WARNING ⚠️ inference results will accumulate in RAM unless `stream=True` is passed, causing potential out-of-memory
errors for large sources or long-running streams and videos. See https://docs.ultralytics.com/modes/predict/ for help.Example:results = model(source=..., stream=True)  # generator of Results objectsfor r in results:boxes = r.boxes  # Boxes object for bbox outputsmasks = r.masks  # Masks object for segment masks outputsprobs = r.probs  # Class probabilities for classification outputs
"""class BasePredictor:"""BasePredictor.A base class for creating predictors.Attributes:args (SimpleNamespace): Configuration for the predictor.save_dir (Path): Directory to save results.done_warmup (bool): Whether the predictor has finished setup.model (nn.Module): Model used for prediction.data (dict): Data configuration.device (torch.device): Device used for prediction.dataset (Dataset): Dataset used for prediction.vid_writer (dict): Dictionary of {save_path: video_writer, ...} writer for saving video output."""def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):"""Initializes the BasePredictor class.Args:cfg (str, optional): Path to a configuration file. Defaults to DEFAULT_CFG.overrides (dict, optional): Configuration overrides. Defaults to None."""self.args = get_cfg(cfg, overrides)self.save_dir = get_save_dir(self.args)if self.args.conf is None:self.args.conf = 0.25  # default conf=0.25self.done_warmup = Falseif self.args.show:self.args.show = check_imshow(warn=True)# Usable if setup is doneself.model = Noneself.data = self.args.data  # data_dictself.imgsz = Noneself.device = Noneself.dataset = Noneself.vid_writer = {}  # dict of {save_path: video_writer, ...}self.plotted_img = Noneself.source_type = Noneself.seen = 0self.windows = []self.batch = Noneself.results = Noneself.transforms = Noneself.callbacks = _callbacks or callbacks.get_default_callbacks()self.txt_path = Noneself._lock = threading.Lock()  # for automatic thread-safe inferencecallbacks.add_integration_callbacks(self)def preprocess(self, im):"""Prepares input image before inference.Args:im (torch.Tensor | List(np.ndarray)): BCHW for tensor, [(HWC) x B] for list."""not_tensor = not isinstance(im, torch.Tensor)if not_tensor:im = np.stack(self.pre_transform(im))im = im[..., ::-1].transpose((0, 3, 1, 2))  # BGR to RGB, BHWC to BCHW, (n, 3, h, w)im = np.ascontiguousarray(im)  # contiguousim = torch.from_numpy(im)im = im.to(self.device)im = im.half() if self.model.fp16 else im.float()  # uint8 to fp16/32if not_tensor:im /= 255  # 0 - 255 to 0.0 - 1.0return imdef inference(self, im, *args, **kwargs):"""Runs inference on a given image using the specified model and arguments."""visualize = (increment_path(self.save_dir / Path(self.batch[0][0]).stem, mkdir=True)if self.args.visualize and (not self.source_type.tensor)else False)return self.model(im, augment=self.args.augment, visualize=visualize, embed=self.args.embed, *args, **kwargs)def pre_transform(self, im):"""Pre-transform input image before inference.Args:im (List(np.ndarray)): (N, 3, h, w) for tensor, [(h, w, 3) x N] for list.Returns:(list): A list of transformed images."""same_shapes = len({x.shape for x in im}) == 1letterbox = LetterBox(self.imgsz, auto=same_shapes and self.model.pt, stride=self.model.stride)return [letterbox(image=x) for x in im]def postprocess(self, preds, img, orig_imgs):"""Post-processes predictions for an image and returns them."""return predsdef __call__(self, source=None, model=None, stream=False, *args, **kwargs):"""Performs inference on an image or stream."""self.stream = streamif stream:return self.stream_inference(source, model, *args, **kwargs)else:return list(self.stream_inference(source, model, *args, **kwargs))  # merge list of Result into onedef predict_cli(self, source=None, model=None):"""Method used for CLI prediction.It uses always generator as outputs as not required by CLI mode."""gen = self.stream_inference(source, model)for _ in gen:  # noqa, running CLI inference without accumulating any outputs (do not modify)passdef setup_source(self, source):"""Sets up source and inference mode."""self.imgsz = check_imgsz(self.args.imgsz, stride=self.model.stride, min_dim=2)  # check image sizeself.transforms = (getattr(self.model.model,"transforms",classify_transforms(self.imgsz[0], crop_fraction=self.args.crop_fraction),)if self.args.task == "classify"else None)self.dataset = load_inference_source(source=source,batch=self.args.batch,vid_stride=self.args.vid_stride,buffer=self.args.stream_buffer,)self.source_type = self.dataset.source_typeif not getattr(self, "stream", True) and (self.source_type.streamor self.source_type.screenshotor len(self.dataset) > 1000  # many imagesor any(getattr(self.dataset, "video_flag", [False]))):  # videosLOGGER.warning(STREAM_WARNING)self.vid_writer = {}@smart_inference_mode()def stream_inference(self, source=None, model=None, *args, **kwargs):"""Streams real-time inference on camera feed and saves results to file."""if self.args.verbose:LOGGER.info("")# Setup modelif not self.model:self.setup_model(model)with self._lock:  # for thread-safe inference# Setup source every time predict is calledself.setup_source(source if source is not None else self.args.source)# Check if save_dir/ label file existsif self.args.save or self.args.save_txt:(self.save_dir / "labels" if self.args.save_txt else self.save_dir).mkdir(parents=True, exist_ok=True)# Warmup modelif not self.done_warmup:self.model.warmup(imgsz=(1 if self.model.pt or self.model.triton else self.dataset.bs, 3, *self.imgsz))self.done_warmup = Trueself.seen, self.windows, self.batch = 0, [], Noneprofilers = (ops.Profile(device=self.device),ops.Profile(device=self.device),ops.Profile(device=self.device),)self.run_callbacks("on_predict_start")for self.batch in self.dataset:self.run_callbacks("on_predict_batch_start")paths, im0s, s = self.batch# Preprocesswith profilers[0]:im = self.preprocess(im0s)# Inferencewith profilers[1]:preds = self.inference(im, *args, **kwargs)if self.args.embed:yield from [preds] if isinstance(preds, torch.Tensor) else preds  # yield embedding tensorscontinue# Postprocesswith profilers[2]:self.results = self.postprocess(preds, im, im0s)self.run_callbacks("on_predict_postprocess_end")# Visualize, save, write resultsn = len(im0s)for i in range(n):self.seen += 1self.results[i].speed = {"preprocess": profilers[0].dt * 1e3 / n,"inference": profilers[1].dt * 1e3 / n,"postprocess": profilers[2].dt * 1e3 / n,}if self.args.verbose or self.args.save or self.args.save_txt or self.args.show:s[i] += self.write_results(i, Path(paths[i]), im, s)# Print batch resultsif self.args.verbose:LOGGER.info("\n".join(s))self.run_callbacks("on_predict_batch_end")yield from self.results# Release assetsfor v in self.vid_writer.values():if isinstance(v, cv2.VideoWriter):v.release()# Print final resultsif self.args.verbose and self.seen:t = tuple(x.t / self.seen * 1e3 for x in profilers)  # speeds per imageLOGGER.info(f"Speed: %.1fms preprocess, %.1fms inference, %.1fms postprocess per image at shape "f"{(min(self.args.batch, self.seen), 3, *im.shape[2:])}" % t)if self.args.save or self.args.save_txt or self.args.save_crop:nl = len(list(self.save_dir.glob("labels/*.txt")))  # number of labelss = f"\n{nl} label{'s' * (nl > 1)} saved to {self.save_dir / 'labels'}" if self.args.save_txt else ""LOGGER.info(f"Results saved to {colorstr('bold', self.save_dir)}{s}")self.run_callbacks("on_predict_end")def setup_model(self, model, verbose=True):"""Initialize YOLO model with given parameters and set it to evaluation mode."""self.model = AutoBackend(weights=model or self.args.model,device=select_device(self.args.device, verbose=verbose),dnn=self.args.dnn,data=self.args.data,fp16=self.args.half,batch=self.args.batch,fuse=True,verbose=verbose,)self.device = self.model.device  # update deviceself.args.half = self.model.fp16  # update halfself.model.eval()def write_results(self, i, p, im, s):"""Write inference results to a file or directory."""string = ""  # print stringif len(im.shape) == 3:im = im[None]  # expand for batch dimif self.source_type.stream or self.source_type.from_img or self.source_type.tensor:  # batch_size >= 1string += f"{i}: "frame = self.dataset.countelse:match = re.search(r"frame (\d+)/", s[i])frame = int(match.group(1)) if match else None  # 0 if frame undeterminedself.txt_path = self.save_dir / "labels" / (p.stem + ("" if self.dataset.mode == "image" else f"_{frame}"))string += "%gx%g " % im.shape[2:]result = self.results[i]result.save_dir = self.save_dir.__str__()  # used in other locationsstring += result.verbose() + f"{result.speed['inference']:.1f}ms"# Add predictions to imageif self.args.save or self.args.show:self.plotted_img = result.plot(line_width=self.args.line_width,boxes=self.args.show_boxes,conf=self.args.show_conf,labels=self.args.show_labels,im_gpu=None if self.args.retina_masks else im[i],)# Save resultsif self.args.save_txt:result.save_txt(f"{self.txt_path}.txt", save_conf=self.args.save_conf)if self.args.save_crop:result.save_crop(save_dir=self.save_dir / "crops", file_name=self.txt_path.stem)if self.args.show:self.show(str(p))if self.args.save:self.save_predicted_images(str(self.save_dir / p.name), frame)return stringdef save_predicted_images(self, save_path="", frame=0):"""Save video predictions as mp4 at specified path."""im = self.plotted_img# Save videos and streamsif self.dataset.mode in {"stream", "video"}:fps = self.dataset.fps if self.dataset.mode == "video" else 30frames_path = f'{save_path.split(".", 1)[0]}_frames/'if save_path not in self.vid_writer:  # new videoif self.args.save_frames:Path(frames_path).mkdir(parents=True, exist_ok=True)# Always save as MP4 regardless of OSsuffix, fourcc = (".mp4", "avc1")self.vid_writer[save_path] = cv2.VideoWriter(filename=str(Path(save_path).with_suffix(suffix)),fourcc=cv2.VideoWriter_fourcc(*fourcc),fps=fps,  # integer required, floats produce error in MP4 codecframeSize=(im.shape[1], im.shape[0]),  # (width, height))# Save videoself.vid_writer[save_path].write(im)if self.args.save_frames:cv2.imwrite(f"{frames_path}{frame}.jpg", im)# Save imageselse:cv2.imwrite(save_path, im)def show(self, p=""):"""Display an image in a window using OpenCV imshow()."""im = self.plotted_imgif platform.system() == "Linux" and p not in self.windows:self.windows.append(p)cv2.namedWindow(p, cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO)  # allow window resize (Linux)cv2.resizeWindow(p, im.shape[1], im.shape[0])  # (width, height)cv2.imshow(p, im)cv2.waitKey(300 if self.dataset.mode == "image" else 1)  # 1 milliseconddef run_callbacks(self, event: str):"""Runs all registered callbacks for a specific event."""for callback in self.callbacks.get(event, []):callback(self)def add_callback(self, event: str, func):"""Add callback."""self.callbacks[event].append(func)

本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如若转载,请注明出处:http://www.mzph.cn/web/15354.shtml

如若内容造成侵权/违法违规/事实不符,请联系多彩编程网进行投诉反馈email:809451989@qq.com,一经查实,立即删除!

相关文章

Android开发-Android开发中的TCP与UDP通信策略的实现

Android 开发中的 TCP 与 UDP 通信策略的实现 1. 前言2. 准备工作3. Kotlin 中 TCP 通信实现客户端代码示例:服务器代码示例: 4. Kotlin 中 UDP 通信实现客户端代码示例:服务器代码示例: 5. TCP 与 UDP 应用场景分析TCP 实现可靠传…

搭建访问阿里云百炼大模型环境

最近这波大降价,还有限时免费,还不赶快试试在线大模型?下面整理访问百炼平台的千问模型方法。 创建RAM子账号并授权 创建RAM子账号 1. “访问控制RAM”入口(控制台URL) 然后点击进入“RAM管理控制台” 2. 添加用户 …

vue 区分多环境打包

需求:区分不同的环境(测试、正式环境),接口文档地址不同; 配置步骤: 1、在根目录下面新建 .env.xxx 文件(xxx 根据环境不同配置) 文件中一定要配置的参数项为:NODE_ENV…

【Python搞定车载自动化测试】——Python实现CAN总线Bootloader刷写(含Python源码)

系列文章目录 【Python搞定车载自动化测试】系列文章目录汇总 文章目录 系列文章目录💯💯💯 前言💯💯💯一、环境搭建1.软件环境2.硬件环境 二、目录结构三、源码展示1.诊断基础函数方法2.诊断业务函数方法…

python 火焰检测

在日常生活,总是离不开火,有时候我们需要预防火灾发生,但是我们又不可能一直盯着,这时候我们就需要一款程序帮我们盯着,一旦发生火灾从而告知我们,今天就带大家编写这么一款应用。 安装需要的库 pip install opencv-python 代码实现 import cv2 # Library for…

qmt量化教程4----订阅全推数据

文章链接 qmt量化教程4----订阅全推数据 (qq.com) 上次写了订阅单股数据的教程 量化教程3---miniqmt当作第三方库设置,提供源代码 全推就主动推送,当行情有变化就会触发回调函数,推送实时数据,可以理解为数据驱动类型&#xff0…

mysql中使用 mysqldump 实现跨机器备份|数据同步

1.如果同步数据库,必须先创建数据库: mysqldump -h 192.168.1.10 --lock-tablesfalse -uroot -proot db_name | mysql -h127.0.0.1 -uroot -proot db_name2.过滤掉不想要的表(没试过,但是试过转为sql文件的) mysqldump -h 192.168.1.10 --…

vs2019 c++ 函数的返回值是对象的值传递时候,将调用对象的移动构造函数

以前倒没有注意过这个问题。但编译器这么处理也符合移动构造的语义。因为本来函数体内的变量也要离开作用域被销毁回收了。测试如下: 谢谢

实现信号发生控制

1. 信号发生器的基本原理 信号发生器是一种能够产生特定波形和频率的电子设备,常用于模拟信号的产生和测试。 信号发生器的基本原理 信号发生器的工作原理基于不同的技术,但最常见的类型包括模拟信号发生器和数字信号发生器(DDS&#xff0…

[SCTF2019]babyre

打开看看还是有花指令 解除后首先pass1是解maze,好像又是三维的 x是25,也就是向下跳五层,注意是立体的 得到 passwd1: ddwwxxssxaxwwaasasyywwdd 接着往下看 有一个加密函数IDA逆向常用宏定义_lodword-CSDN博客 unsigned __int64 __fastca…

primeflex样式库笔记 Display相关的案例

回顾 宽度设置的基本总结 w-full:表示widtdh:100%;占满父容器的宽度。 w-screen:表示占满整个屏幕的宽度。 w-1到w-12,是按百分比划分宽度,数字越大,占据的比例就越大。 w-1rem到w-30rem&…

Oracle的安装以及一些相关问题

系列文章目录 Oracle的安装以及一些相关问题 文章目录 系列文章目录前言一、Oracle的安装二、常用命令三、误删dbf四、PLSQL乱码五、oracle更换数据库字符集总结 前言 一段时间没更新,主要最近一直在找工作,最终还是顺着春招找到工作了,现在…

美信時代監控易:堆疊交換機的監控與配置管理策略

隨著企業數字化轉型的加速,網絡架構的複雜性日益提升,堆疊交換機作為高可靠性、靈活擴展性的解決方案,在網絡基礎設施中扮演著至關重要的角色。然而,如何確保堆疊交換機的穩定運行,實現高效監控與配置管理,…

剖析 OceanBase 应对高并发的技术策略

推荐一个AI网站,免费使用豆包AI模型,快去白嫖👉海鲸AI 在当今互联网时代,高并发场景下的数据库处理能力成为了许多应用的关键需求。为了满足用户对快速响应和高吞吐量的期望,数据库系统需要采用一系列技术来优化并发性…

七大经典排序算法——冒泡排序

文章目录 📑冒泡排序介绍🌤️代码实现🌤️做个简单的优化🌤️复杂度和稳定性分析☁️结语 📑冒泡排序介绍 冒泡排序是一种简单但效率较低的排序算法。它重复地比较相邻的两个元素,如果顺序不对则交换它们&…

C++ socket epoll IO多路复用

IO多路复用通常用于处理单进程高并发,在Linux中,一切皆文件,一个socket连接会对应一个文件描述符,在监听多个文件描述符的状态应用中epoll相对于select和poll效率更高 epoll本质是系统在内核维护了一颗红黑树,监听的文…

Linux中bash脚本怎么表示一个字符串变量

Linux中bash脚本怎么表示一个字符串变量 在Bash脚本中,你可以使用单引号()或双引号(")来表示一个字符串变量。以下是两种方式的示例: 使用单引号(): my_variable…

flink 和 clipper搭配使用

Flink是一个用于流处理和批处理的开源框架,可以实时数据处理和分析。 Clipper 是一个用于机器学习模型服务化的开源框架,能够轻松部署和管理机器学习模型,使模型可以通过统一的接口提供在线推理服务。 flink和clipper搭配使用: …

Leetcode | 5-21| 每日一题

2769. 找出最大的可达成数字 考点: 暴力 数学式子计算 思维 题解 通过式子推导: 第一想法是二分确定区间在区间内进行查找是否符合条件的, 本题最关键的便是 条件确定 , 第二种方法: 一般是通过数学公式推导的,这种题目我称为数学式编程题 代码 条件判断式 class Solution { …

需求分析的任务

1 确定对系统的综合要求 虽然功能需求是对软件系统的一项基本需求,但却并不是唯一的需求。通常对软件系统有下述几方面的综合要求。 1.功能需求 这方面的需求指定系统必须提供的服务。通过需求分析应该划分出系统必须完成的所有功能。 2.性能…