YOLOv8实战中国交通标志识别

[bai666ai]

课程名称	适应人群
YOLOv8实战中国交通标志识别	希望学习YOLOv8目标检测技术的学员和从业者

在无人驾驶中，交通标志识别是一项重要的任务。YOLOv8是前沿的目标检测技术，它基于先前 YOLO 版本在目标检测任务上的成功，进一步提升性能和灵活性。

本课程将手把手地带大家使用YOLOv8训练TT100K中国交通标志数据集，完成一个多目标检测实战项目。可实时检测图像、视频、摄像头和流媒体(http/rtsp)中的交通标志，并提供PySide6开发的可视化演示界面 。

TT100K（Tsinghua-Tencent 100K）是一个专门用于交通标志检测的大规模数据集。该数据集由清华大学与腾讯公司联合开发。TT100K数据集包含了超过10万张图片。图片中包含了不同类型的交通标志，总计约有200,000个标签。本课程会讲述使用Python程序将TT100K数据集的格式转换成PASCAL VOC格式和YOLO格式的方法，并提供相应代码。

本课程分别在Windows和Ubuntu系统上做项目演示。包括：安装软件环境（Nvidia显卡驱动、cuda和cudnn）、安装PyTorch、安装YOLOv8、 TT00K数据集数据格式转换、准备数据集（自动划分训练集和验证集）、修改配置文件、训练数据集（合适的命令参数选择）、测试训练出的网络模型和性能统计、项目可视化演示界面。 

本课程新增了在阿里云上使用免费GPU算力的项目实战演示流程。GPU免费算力的领取方式和阿里云平台上的项目实战操作流程可见课程视频。

[bai666ai]

电脑端播放课程视频时，在屏幕左上方会有“下载课件”的按钮。项目流程的课件中有网盘链接可下载其它课程资料。

[bai666ai]

@蜡笔small欣️ 检查下数据集放置的位置是否正确

[蜡笔small欣️]

执行训练语句时出现(mypytorch) D:\ultralytics\ultralytics>yolo detect train data=D:/ultralytics/ultralytics/datasets/VOC-tt100k.yaml model=D:/ultralytics/ultralytics/weights/yolov8s.pt epochs=150 imgsz=640 batch=16 workers=4 patience=150 name=train_yolov8s
New https://pypi.org/project/ultralytics/8.0.198 available Update with 'pip install -U ultralytics'
Ultralytics YOLOv8.0.186 Python-3.9.18 torch-2.0.1+cu118 CUDA:0 (NVIDIA GeForce RTX 4060 Laptop GPU, 8188MiB)
engine\trainer: task=detect, mode=train, model=D:/ultralytics/ultralytics/weights/yolov8s.pt, data=D:/ultralytics/ultralytics/datasets/VOC-tt100k.yaml, epochs=150, patience=150, batch=16, imgsz=640, save=True, save_period=-1, cache=False, device=None, workers=4, project=None, name=train_yolov8s, exist_ok=False, pretrained=True, optimizer=auto, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=10, resume=False, amp=True, fraction=1.0, profile=False, freeze=None, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, show=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, vid_stride=1, stream_buffer=False, line_width=None, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, boxes=True, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=None, workspace=4, nms=False, lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=7.5, cls=0.5, dfl=1.5, pose=12.0, kobj=1.0, label_smoothing=0.0, nbs=64, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0, cfg=None, tracker=botsort.yaml, save_dir=runs\detect\train_yolov8s6

Dataset 'D://ultralytics/ultralytics/datasets/VOC-tt100k.yaml' images not found , missing path 'D:\ultralytics\ultralytics\VOCdevkit \images\val'
Downloading https://github.com/ultralytics/yolov5/releases/download/v1.0/VOCtrainval_06-Nov-2007.zip to 'D:\ultralytics\ultralytics\VOCdevkit \images\VOCtrainval_06-Nov-2007.zip'...
Downloading https://github.com/ultralytics/yolov5/releases/download/v1.0/VOCtrainval_11-May-2012.zip to 'D:\ultralytics\ultralytics\VOCdevkit \images\VOCtrainval_11-May-2012.zip'...
Downloading https://github.com/ultralytics/yolov5/releases/download/v1.0/VOCtest_06-Nov-2007.zip to 'D:\ultralytics\ultralytics\VOCdevkit \images\VOCtest_06-Nov-2007.zip'...，但是我的文件已经配置好了，它仍然在下载VOCdevkit

[bai666ai]

@蜡笔small欣️ 电脑端播放课程视频时，在屏幕左上方会有“下载课件”的按钮。项目流程的课件中有网盘链接可下载其它课程资料。

[蜡笔small欣️]

请问可以提供yltralytics训练后的全部文件吗，遇到了问题训练失败

[weixin_45622433]

@bai666ai 我的是GPU 也这样的报错 还能怎么处理呢

[bai666ai]

@蜡笔small欣️ 检查下安装的pytorch是否是gpu版本

[蜡笔small欣️]

optimizer: SGD(lr=0.01, momentum=0.9) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0005), 63 bias(decay=0.0)
Image sizes 640 train, 640 val
Using 4 dataloader workers
Logging results to runs\detect\train_yolov8s16
Starting training for 150 epochs...

  Epoch    GPU_mem   box_loss   cls_loss   dfl_loss  Instances       Size
  1/150      4.17G      1.565      21.98     0.9978         38        640:   1%|          | 4/513 [00:01<02:47,  3.05it/s]C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [64,0,0] Assertion `index >= -sizes[i] && index < sizes[i] && "index out of bounds"` failed.

C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [65,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [66,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [67,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [68,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [69,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [70,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [71,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [72,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [73,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [74,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [75,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [76,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [77,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [78,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [79,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [80,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [81,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [82,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [83,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [84,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [85,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [86,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [87,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [88,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [89,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [90,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [91,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [92,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [93,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [94,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [2207,0,0], thread: [95,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
1/150 4.17G 1.565 21.98 0.9978 38 640: 1%| | 4/513 [00:01<04:06, 2.06it/s]
Traceback (most recent call last):
File "\?\D:\AAnaconda\envs\mypytorch\Scripts\yolo-script.py", line 33, in
sys.exit(load_entry_point('ultralytics', 'console_scripts', 'yolo')())
File "d:\ultralytics\ultralytics\cfg_init_.py", line 445, in entrypoint
getattr(model, mode)(**overrides) # default args from model
File "d:\ultralytics\ultralytics\engine\model.py", line 337, in train
self.trainer.train()
File "d:\ultralytics\ultralytics\engine\trainer.py", line 195, in train
self._do_train(world_size)
File "d:\ultralytics\ultralytics\engine\trainer.py", line 348, in _do_train
self.loss, self.loss_items = self.model(batch)
File "D:\AAnaconda\envs\mypytorch\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "d:\ultralytics\ultralytics\nn\tasks.py", line 44, in forward
return self.loss(x, *args, **kwargs)
File "d:\ultralytics\ultralytics\nn\tasks.py", line 215, in loss
return self.criterion(preds, batch)
File "d:\ultralytics\ultralytics\utils\loss.py", line 181, in call
_, target_bboxes, target_scores, fg_mask, _ = self.assigner(
File "D:\AAnaconda\envs\mypytorch\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "D:\AAnaconda\envs\mypytorch\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, *kwargs)
File "d:\ultralytics\ultralytics\utils\tal.py", line 115, in forward
mask_pos, align_metric, overlaps = self.get_pos_mask(pd_scores, pd_bboxes, gt_labels, gt_bboxes, anc_points,
File "d:\ultralytics\ultralytics\utils\tal.py", line 136, in get_pos_mask
align_metric, overlaps = self.get_box_metrics(pd_scores, pd_bboxes, gt_labels, gt_bboxes, mask_in_gts * mask_gt)
File "d:\ultralytics\ultralytics\utils\tal.py", line 155, in get_box_metrics
bbox_scores[mask_gt] = pd_scores[ind[0], :, ind[1]][mask_gt] # b, max_num_obj, hw
RuntimeError: CUDA error: device-side assert triggered
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
这个问题怎么解决呢

[bai666ai]

@简谐波430 检查下安装的pytorch是否是gpu版本

[简谐波430]

@简谐波430 最后训练的时候不调用GPU，训练很慢

[简谐波430]

我是按部就班做的，为啥不调用GPU处理呢？

[看我不看我]

@bai666ai windows版本的，项目可视化演示界面这个视频看不了

[bai666ai]

@看我不看我 电脑端播放课程视频时，在屏幕左上方会有“下载课件”的按钮。项目流程的课件中有网盘链接可下载其它课程资料。可视化也在网盘上。

[看我不看我]

请问可视化的部分在哪里呀，为啥没有这部分的网盘链接

[bai666ai]

电脑端播放课程视频时，在屏幕左上方会有“下载课件”的按钮。项目流程的课件中有网盘链接可下载其它课程资料。
购课后可加入QQ群：564189992

[bai666ai]

@2301_77747794 可以到课程网盘上下载，testfiles.zip解压

[2301_77747794]

你这里面使用的视频可不可以发一下呀，就是用于展示系统功能的那种含有交通标志的视频

[人间正道是沧桑171]

D:/ultralytics/ultralytics路径下，执行python脚本
之后生成的文件夹里面都是空的是为什么？

[abs123456_]

为什么进行预测没有predict文件

[连冠]

请问训练数据集的时候，出现这种是什么原因:
CUDA error: out of memory
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

[fyzxxx_]

请问实现可视化以后，识别视频老是会崩溃是什么问题