极链ai云使用RTX3090报错：RuntimeError: Could not run ‘torchvision::nms‘ with arguments from the ‘CUDA

最新推荐文章于 2025-04-07 00:54:08 发布
原创 最新推荐文章于 2025-04-07 00:54:08 发布 · 1.6k 阅读 · 2 ·
CC 4.0 BY-SA版权
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
文章标签：

#人工智能 #深度学习 #pytorch

使用极链ai云配置好的Pytorch框架跑Yolov5的时候，会出现RuntimeError: Could not run ‘torchvision::nms’ with arguments from the 'CUDA的错误。
在这里插入图片描述
经过查询，是因为torch、torchvision和CUDA版本的问题，后来使用该文章中添加链接描述的配置解决了问题。（自己选用的是CUDA11.0，刚好是一致的！！）

# CUDA 11.0
pip install torch==1.7.1+cu110 torchvision==0.8.2+cu110 torchaudio==0.7.2 -f
最低0.47元/天 解锁文章
深度剖析问题：Could not run ‘torchvision::nms‘ with arguments from the ‘CUDA‘ backend.
Flying Bulldog 的博客
05-21 1万+
（2）根据后台提示的信息，分析源码，进行问题的解决，下面是解决问题的过程：分析代码行：return torch.ops.torchvision.nms(boxes, scores, iou_threshold)，ctrl + 鼠标左键点击 nms，进入到下一个文件，截图如下图所示：在函数nms内部做一个标志（print(22222222222222)），观察能否调用函数nms，经测试发现没有调用函数nms。
YOLOX安装、测试，自定义coco数据集进行测试
李昂的博客
08-06 4504
官网链接：https://github.com/Megvii-BaseDetection/YOLOX 一、配置环境 本机环境是 Ubuntu 18.04 Cuda 10.2 RTX 2080ti 1、创建虚拟环境 conda create -n yolox python=3.7 2.安装torch conda activate yolox pip install torch==1.7.0 torchvision==0.8.0 torchaudio==0.7.0 3、安装YOLOX git clone h
一、 Could not run ‘torchvision::nms‘ with arguments from the ‘CUDA‘ backend解决方法.
monkey_lc的博客
06-17 2870
方法一：上述链接中内容比较详细，我这里简要提一下，在第一步框选的路径下，创建新的文件夹，内容放在文章末尾，然后命名xx（随意），然后在上图return返回值部分，改为 return xx.nms就行了（但是我自己的这样改，还是报错，没有找到声明，我不知道如何解决qaq，浪费了n小时时间，所以有了第二个方案）lt = torch.max(boxes1[:, None, :2], boxes2[:, :2]) # [N,M,2] # N中一个和M个比较；# 得分最大框对应的索引, 以及对应的坐标。
YOLOv5 报错：“NotImplementedError: Could not run ‘torchvision::nms‘ with arguments from the ‘CUDA‘ back
热门推荐
Dontla的博客
08-28 1万+
是torchvisiao-cuda没装好，重装下 参考文章：解决“NotImplementedError: Could not run ‘torchvision::nms‘ with arguments from the ‘CUDA‘ backend.”
NotImplementedError: Could not run ‘torchvision::nms‘ with arguments from the ‘CUDA‘ backend. 错误纠正
qq_61776376的博客
03-17 4119
但是NotImplementedError: Could not run 'torchvision::nms' with arguments from the 'CUDA' backend这个错误是由cup版本的torchvision引起的，我看了好多博主说是torch与torchvision版本不对的报错，接下来我说下我是怎么处理的。cu121表示cuda的版本号，我记得我的是12.2没有可以直接用121也行，进入这个页面，ctrl+f就可以自己搜到自己的版本号了。查看自己的版本号，右上角有个。
YOLOv5运行问题：Could not run ‘torchvision::nms‘ with arguments from the ‘CUDA‘ backend.
weixin_43497556的博客
05-13 2221
解决YOLOv5的Could not run ‘torchvision::nms‘ with arguments from the ‘CUDA‘ backend.问题
D:\anaconda\envs\mamba\python.exe E:\ultralytics-v8.3.63\ultralytics\models\yolo\pwcmamba\ceshi.py WARNING ⚠️ no model scale passed. Assuming scale='n'. 解析第0层，from=-1，当前ch列表长度=1 解析第0层后，save列表：[] 解析第1层，from=-1，当前ch列表长度=1 解析第1层后，save列表：[] 解析第2层，from=-1，当前ch列表长度=2 解析第2层后，save列表：[] 解析第3层，from=-1，当前ch列表长度=3 解析第3层后，save列表：[] 解析第4层，from=-1，当前ch列表长度=4 解析第4层后，save列表：[] 解析第5层，from=-1，当前ch列表长度=5 解析第5层后，save列表：[] 解析第6层，from=-1，当前ch列表长度=6 解析第6层后，save列表：[] 解析第7层，from=-1，当前ch列表长度=7 解析第7层后，save列表：[] 解析第8层，from=-1，当前ch列表长度=8 解析第8层后，save列表：[] 解析第9层，from=-1，当前ch列表长度=9 解析第9层后，save列表：[] 解析第10层，from=-1，当前ch列表长度=10 解析第10层后，save列表：[] 解析第11层，from=-1，当前ch列表长度=11 解析第11层后，save列表：[] 解析第12层，from=[-1, 6]，当前ch列表长度=12 Concat层12：将历史层6加入save列表 解析第12层后，save列表：[6] 解析第13层，from=-1，当前ch列表长度=13 解析第13层后，save列表：[6] 解析第14层，from=-1，当前ch列表长度=14 解析第14层后，save列表：[6] 解析第15层，from=-1，当前ch列表长度=15 解析第15层后，save列表：[6] 解析第16层，from=-1，当前ch列表长度=16 解析第16层后，save列表：[6] 解析第17层，from=[-1, 4]，当前ch列表长度=17 Concat层17：将历史层4加入save列表 解析第17层后，save列表：[4, 6] 解析第18层，from=-1，当前ch列表长度=18 解析第18层后，save列表：[4, 6] 解析第19层，from=-1，当前ch列表长度=19 解析第19层后，save列表：[4, 6] 解析第20层，from=-1，当前ch列表长度=20 解析第20层后，save列表：[4, 6] 解析第21层，from=[-1, 14]，当前ch列表长度=21 Concat层21：将历史层14加入save列表 解析第21层后，save列表：[4, 6, 14] 解析第22层，from=-1，当前ch列表长度=22 解析第22层后，save列表：[4, 6, 14] 解析第23层，from=-1，当前ch列表长度=23 解析第23层后，save列表：[4, 6, 14] 解析第24层，from=-1，当前ch列表长度=24 解析第24层后，save列表：[4, 6, 14] 解析第25层，from=[-1, 9]，当前ch列表长度=25 Concat层25：将历史层9加入save列表 解析第25层后，save列表：[4, 6, 9, 14] 解析第26层，from=-1，当前ch列表长度=26 解析第26层后，save列表：[4, 6, 9, 14] 解析第27层，from=-1，当前ch列表长度=27 解析第27层后，save列表：[4, 6, 9, 14] 解析第28层，from=[19, 23, 27]，当前ch列表长度=28 层28：将from列表中的19加入save列表 层28：将from列表中的23加入save列表 层28：将from列表中的27加入save列表 解析第28层后，save列表：[4, 6, 9, 14, 19, 23, 27] Layer 0: Conv, input device: cuda:0 Layer 0: Conv, output device: cuda:0 Layer 1: Conv, input device: cuda:0 Layer 1: Conv, output device: cuda:0 Layer 2: C2f, input device: cuda:0 Layer 2: C2f, output device: cuda:0 Layer 3: Conv, input device: cuda:0 Layer 3: Conv, output device: cuda:0 Layer 4: C2f, input device: cuda:0 Layer 4: C2f, output device: cuda:0 Layer 5: Conv, input device: cuda:0 Layer 5: Conv, output device: cuda:0 Layer 6: C2f, input device: cuda:0 Layer 6: C2f, output device: cuda:0 Layer 7: Conv, input device: cuda:0 Layer 7: Conv, output device: cuda:0 Layer 8: PWCMamba, input device: cuda:0 Layer 8: PWCMamba, output device: cuda:0 Layer 9: SPPF, input device: cuda:0 Layer 9: SPPF, output device: cuda:0 Layer 10: Conv, input device: cuda:0 Layer 10: Conv, output device: cuda:0 Layer 11: Upsample, input device: cuda:0 Layer 11: Upsample, output device: cuda:0 Layer 12: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 16, 16]) (通道数: 64) 输入1形状: torch.Size([1, 128, 16, 16]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 16, 16]) (拼接后通道数: 192) Layer 12: Concat, output device: cuda:0 Layer 13: Conv, input device: cuda:0 Layer 13: Conv, output device: cuda:0 Layer 14: PWCMamba, input device: cuda:0 Layer 14: PWCMamba, output device: cuda:0 Layer 15: Conv, input device: cuda:0 Layer 15: Conv, output device: cuda:0 Layer 16: Upsample, input device: cuda:0 Layer 16: Upsample, output device: cuda:0 Layer 17: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 32, 32]) (通道数: 32) 输入1形状: torch.Size([1, 64, 32, 32]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 32, 32]) (拼接后通道数: 96) Layer 17: Concat, output device: cuda:0 Layer 18: Conv, input device: cuda:0 Layer 18: Conv, output device: cuda:0 Layer 19: PWCMamba, input device: cuda:0 Layer 19: PWCMamba, output device: cuda:0 Layer 20: Conv, input device: cuda:0 Layer 20: Conv, output device: cuda:0 Layer 21: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 16, 16]) (通道数: 32) 输入1形状: torch.Size([1, 64, 16, 16]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 16, 16]) (拼接后通道数: 96) Layer 21: Concat, output device: cuda:0 Layer 22: Conv, input device: cuda:0 Layer 22: Conv, output device: cuda:0 Layer 23: PWCMamba, input device: cuda:0 Layer 23: PWCMamba, output device: cuda:0 Layer 24: Conv, input device: cuda:0 Layer 24: Conv, output device: cuda:0 Layer 25: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 8, 8]) (通道数: 64) 输入1形状: torch.Size([1, 128, 8, 8]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 8, 8]) (拼接后通道数: 192) Layer 25: Concat, output device: cuda:0 Layer 26: Conv, input device: cuda:0 Layer 26: Conv, output device: cuda:0 Layer 27: PWCMamba, input device: cuda:0 Layer 27: PWCMamba, output device: cuda:0 Layer 28: Detect, input device: cuda:0 Layer 28: Detect, output device: cuda:0 Layer 0: Conv, input device: cuda:0 Layer 0: Conv, output device: cuda:0 Layer 1: Conv, input device: cuda:0 Layer 1: Conv, output device: cuda:0 Layer 2: C2f, input device: cuda:0 Layer 2: C2f, output device: cuda:0 Layer 3: Conv, input device: cuda:0 Layer 3: Conv, output device: cuda:0 Layer 4: C2f, input device: cuda:0 Layer 4: C2f, output device: cuda:0 Layer 5: Conv, input device: cuda:0 Layer 5: Conv, output device: cuda:0 Layer 6: C2f, input device: cuda:0 Layer 6: C2f, output device: cuda:0 Layer 7: Conv, input device: cuda:0 Layer 7: Conv, output device: cuda:0 Layer 8: PWCMamba, input device: cuda:0 Layer 8: PWCMamba, output device: cuda:0 Layer 9: SPPF, input device: cuda:0 Layer 9: SPPF, output device: cuda:0 Layer 10: Conv, input device: cuda:0 Layer 10: Conv, output device: cuda:0 Layer 11: Upsample, input device: cuda:0 Layer 11: Upsample, output device: cuda:0 Layer 12: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 16, 16]) (通道数: 64) 输入1形状: torch.Size([1, 128, 16, 16]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 16, 16]) (拼接后通道数: 192) Layer 12: Concat, output device: cuda:0 Layer 13: Conv, input device: cuda:0 Layer 13: Conv, output device: cuda:0 Layer 14: PWCMamba, input device: cuda:0 Layer 14: PWCMamba, output device: cuda:0 Layer 15: Conv, input device: cuda:0 Layer 15: Conv, output device: cuda:0 Layer 16: Upsample, input device: cuda:0 Layer 16: Upsample, output device: cuda:0 Layer 17: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 32, 32]) (通道数: 32) 输入1形状: torch.Size([1, 64, 32, 32]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 32, 32]) (拼接后通道数: 96) Layer 17: Concat, output device: cuda:0 Layer 18: Conv, input device: cuda:0 Layer 18: Conv, output device: cuda:0 Layer 19: PWCMamba, input device: cuda:0 Layer 19: PWCMamba, output device: cuda:0 Layer 20: Conv, input device: cuda:0 Layer 20: Conv, output device: cuda:0 Layer 21: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 16, 16]) (通道数: 32) 输入1形状: torch.Size([1, 64, 16, 16]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 16, 16]) (拼接后通道数: 96) Layer 21: Concat, output device: cuda:0 Layer 22: Conv, input device: cuda:0 Layer 22: Conv, output device: cuda:0 Layer 23: PWCMamba, input device: cuda:0 Layer 23: PWCMamba, output device: cuda:0 Layer 24: Conv, input device: cuda:0 Layer 24: Conv, output device: cuda:0 Layer 25: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 8, 8]) (通道数: 64) 输入1形状: torch.Size([1, 128, 8, 8]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 8, 8]) (拼接后通道数: 192) Layer 25: Concat, output device: cuda:0 Layer 26: Conv, input device: cuda:0 Layer 26: Conv, output device: cuda:0 Layer 27: PWCMamba, input device: cuda:0 Layer 27: PWCMamba, output device: cuda:0 Layer 28: Detect, input device: cuda:0 Layer 28: Detect, output device: cuda:0 Layer 0: Conv, input device: cuda:0 Layer 0: Conv, output device: cuda:0 Layer 1: Conv, input device: cuda:0 Layer 1: Conv, output device: cuda:0 Layer 2: C2f, input device: cuda:0 Layer 2: C2f, output device: cuda:0 Layer 3: Conv, input device: cuda:0 Layer 3: Conv, output device: cuda:0 Layer 4: C2f, input device: cuda:0 Layer 4: C2f, output device: cuda:0 Layer 5: Conv, input device: cuda:0 Layer 5: Conv, output device: cuda:0 Layer 6: C2f, input device: cuda:0 Layer 6: C2f, output device: cuda:0 Layer 7: Conv, input device: cuda:0 Layer 7: Conv, output device: cuda:0 Layer 8: PWCMamba, input device: cuda:0 Layer 8: PWCMamba, output device: cuda:0 Layer 9: SPPF, input device: cuda:0 Layer 9: SPPF, output device: cuda:0 Layer 10: Conv, input device: cuda:0 Layer 10: Conv, output device: cuda:0 Layer 11: Upsample, input device: cuda:0 Layer 11: Upsample, output device: cuda:0 Layer 12: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 16, 16]) (通道数: 64) 输入1形状: torch.Size([1, 128, 16, 16]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 16, 16]) (拼接后通道数: 192) Layer 12: Concat, output device: cuda:0 Layer 13: Conv, input device: cuda:0 Layer 13: Conv, output device: cuda:0 Layer 14: PWCMamba, input device: cuda:0 Layer 14: PWCMamba, output device: cuda:0 Layer 15: Conv, input device: cuda:0 Layer 15: Conv, output device: cuda:0 Layer 16: Upsample, input device: cuda:0 Layer 16: Upsample, output device: cuda:0 Layer 17: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 32, 32]) (通道数: 32) 输入1形状: torch.Size([1, 64, 32, 32]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 32, 32]) (拼接后通道数: 96) Layer 17: Concat, output device: cuda:0 Layer 18: Conv, input device: cuda:0 Layer 18: Conv, output device: cuda:0 Layer 19: PWCMamba, input device: cuda:0 Layer 19: PWCMamba, output device: cuda:0 Layer 20: Conv, input device: cuda:0 Layer 20: Conv, output device: cuda:0 Layer 21: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 16, 16]) (通道数: 32) 输入1形状: torch.Size([1, 64, 16, 16]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 16, 16]) (拼接后通道数: 96) Layer 21: Concat, output device: cuda:0 Layer 22: Conv, input device: cuda:0 Layer 22: Conv, output device: cuda:0 Layer 23: PWCMamba, input device: cuda:0 Layer 23: PWCMamba, output device: cuda:0 Layer 24: Conv, input device: cuda:0 Layer 24: Conv, output device: cuda:0 Layer 25: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 8, 8]) (通道数: 64) 输入1形状: torch.Size([1, 128, 8, 8]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 8, 8]) (拼接后通道数: 192) Layer 25: Concat, output device: cuda:0 Layer 26: Conv, input device: cuda:0 Layer 26: Conv, output device: cuda:0 Layer 27: PWCMamba, input device: cuda:0 Layer 27: PWCMamba, output device: cuda:0 Layer 28: Detect, input device: cuda:0 Layer 28: Detect, output device: cuda:0 Layer 0: Conv, input device: cuda:0 Layer 0: Conv, output device: cuda:0 Layer 1: Conv, input device: cuda:0 Layer 1: Conv, output device: cuda:0 Layer 2: C2f, input device: cuda:0 Layer 2: C2f, output device: cuda:0 Layer 3: Conv, input device: cuda:0 Layer 3: Conv, output device: cuda:0 Layer 4: C2f, input device: cuda:0 Layer 4: C2f, output device: cuda:0 Layer 5: Conv, input device: cuda:0 Layer 5: Conv, output device: cuda:0 Layer 6: C2f, input device: cuda:0 Layer 6: C2f, output device: cuda:0 Layer 7: Conv, input device: cuda:0 Layer 7: Conv, output device: cuda:0 Layer 8: PWCMamba, input device: cuda:0 Layer 8: PWCMamba, output device: cuda:0 Layer 9: SPPF, input device: cuda:0 Layer 9: SPPF, output device: cuda:0 Layer 10: Conv, input device: cuda:0 Layer 10: Conv, output device: cuda:0 Layer 11: Upsample, input device: cuda:0 Layer 11: Upsample, output device: cuda:0 Layer 12: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 16, 16]) (通道数: 64) 输入1形状: torch.Size([1, 128, 16, 16]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 16, 16]) (拼接后通道数: 192) Layer 12: Concat, output device: cuda:0 Layer 13: Conv, input device: cuda:0 Layer 13: Conv, output device: cuda:0 Layer 14: PWCMamba, input device: cuda:0 Layer 14: PWCMamba, output device: cuda:0 Layer 15: Conv, input device: cuda:0 Layer 15: Conv, output device: cuda:0 Layer 16: Upsample, input device: cuda:0 Layer 16: Upsample, output device: cuda:0 Layer 17: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 32, 32]) (通道数: 32) 输入1形状: torch.Size([1, 64, 32, 32]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 32, 32]) (拼接后通道数: 96) Layer 17: Concat, output device: cuda:0 Layer 18: Conv, input device: cuda:0 Layer 18: Conv, output device: cuda:0 Layer 19: PWCMamba, input device: cuda:0 Layer 19: PWCMamba, output device: cuda:0 Layer 20: Conv, input device: cuda:0 Layer 20: Conv, output device: cuda:0 Layer 21: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 16, 16]) (通道数: 32) 输入1形状: torch.Size([1, 64, 16, 16]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 16, 16]) (拼接后通道数: 96) Layer 21: Concat, output device: cuda:0 Layer 22: Conv, input device: cuda:0 Layer 22: Conv, output device: cuda:0 Layer 23: PWCMamba, input device: cuda:0 Layer 23: PWCMamba, output device: cuda:0 Layer 24: Conv, input device: cuda:0 Layer 24: Conv, output device: cuda:0 Layer 25: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 8, 8]) (通道数: 64) 输入1形状: torch.Size([1, 128, 8, 8]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 8, 8]) (拼接后通道数: 192) Layer 25: Concat, output device: cuda:0 Layer 26: Conv, input device: cuda:0 Layer 26: Conv, output device: cuda:0 Layer 27: PWCMamba, input device: cuda:0 Layer 27: PWCMamba, output device: cuda:0 Layer 28: Detect, input device: cuda:0 Layer 28: Detect, output device: cuda:0 Layer 0: Conv, input device: cuda:0 Layer 0: Conv, output device: cuda:0 Layer 1: Conv, input device: cuda:0 Layer 1: Conv, output device: cuda:0 Layer 2: C2f, input device: cuda:0 Layer 2: C2f, output device: cuda:0 Layer 3: Conv, input device: cuda:0 Layer 3: Conv, output device: cuda:0 Layer 4: C2f, input device: cuda:0 Layer 4: C2f, output device: cuda:0 Layer 5: Conv, input device: cuda:0 Layer 5: Conv, output device: cuda:0 Layer 6: C2f, input device: cuda:0 Layer 6: C2f, output device: cuda:0 Layer 7: Conv, input device: cuda:0 Layer 7: Conv, output device: cuda:0 Layer 8: PWCMamba, input device: cuda:0 Layer 8: PWCMamba, output device: cuda:0 Layer 9: SPPF, input device: cuda:0 Layer 9: SPPF, output device: cuda:0 Layer 10: Conv, input device: cuda:0 Layer 10: Conv, output device: cuda:0 Layer 11: Upsample, input device: cuda:0 Layer 11: Upsample, output device: cuda:0 Layer 12: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 16, 16]) (通道数: 64) 输入1形状: torch.Size([1, 128, 16, 16]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 16, 16]) (拼接后通道数: 192) Layer 12: Concat, output device: cuda:0 Layer 13: Conv, input device: cuda:0 Layer 13: Conv, output device: cuda:0 Layer 14: PWCMamba, input device: cuda:0 Layer 14: PWCMamba, output device: cuda:0 Layer 15: Conv, input device: cuda:0 Layer 15: Conv, output device: cuda:0 Layer 16: Upsample, input device: cuda:0 Layer 16: Upsample, output device: cuda:0 Layer 17: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 32, 32]) (通道数: 32) 输入1形状: torch.Size([1, 64, 32, 32]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 32, 32]) (拼接后通道数: 96) Layer 17: Concat, output device: cuda:0 Layer 18: Conv, input device: cuda:0 Layer 18: Conv, output device: cuda:0 Layer 19: PWCMamba, input device: cuda:0 Layer 19: PWCMamba, output device: cuda:0 Layer 20: Conv, input device: cuda:0 Layer 20: Conv, output device: cuda:0 Layer 21: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 16, 16]) (通道数: 32) 输入1形状: torch.Size([1, 64, 16, 16]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 16, 16]) (拼接后通道数: 96) Layer 21: Concat, output device: cuda:0 Layer 22: Conv, input device: cuda:0 Layer 22: Conv, output device: cuda:0 Layer 23: PWCMamba, input device: cuda:0 Layer 23: PWCMamba, output device: cuda:0 Layer 24: Conv, input device: cuda:0 Layer 24: Conv, output device: cuda:0 Layer 25: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 8, 8]) (通道数: 64) 输入1形状: torch.Size([1, 128, 8, 8]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 8, 8]) (拼接后通道数: 192) Layer 25: Concat, output device: cuda:0 Layer 26: Conv, input device: cuda:0 Layer 26: Conv, output device: cuda:0 Layer 27: PWCMamba, input device: cuda:0 Layer 27: PWCMamba, output device: cuda:0 Layer 28: Detect, input device: cuda:0 Layer 28: Detect, output device: cuda:0 Layer 0: Conv, input device: cuda:0 Layer 0: Conv, output device: cuda:0 Layer 1: Conv, input device: cuda:0 Layer 1: Conv, output device: cuda:0 Layer 2: C2f, input device: cuda:0 Layer 2: C2f, output device: cuda:0 Layer 3: Conv, input device: cuda:0 Layer 3: Conv, output device: cuda:0 Layer 4: C2f, input device: cuda:0 Layer 4: C2f, output device: cuda:0 Layer 5: Conv, input device: cuda:0 Layer 5: Conv, output device: cuda:0 Layer 6: C2f, input device: cuda:0 Layer 6: C2f, output device: cuda:0 Layer 7: Conv, input device: cuda:0 Layer 7: Conv, output device: cuda:0 Layer 8: PWCMamba, input device: cuda:0 Layer 8: PWCMamba, output device: cuda:0 Layer 9: SPPF, input device: cuda:0 Layer 9: SPPF, output device: cuda:0 Layer 10: Conv, input device: cuda:0 Layer 10: Conv, output device: cuda:0 Layer 11: Upsample, input device: cuda:0 Layer 11: Upsample, output device: cuda:0 Layer 12: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 16, 16]) (通道数: 64) 输入1形状: torch.Size([1, 128, 16, 16]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 16, 16]) (拼接后通道数: 192) Layer 12: Concat, output device: cuda:0 Layer 13: Conv, input device: cuda:0 Layer 13: Conv, output device: cuda:0 Layer 14: PWCMamba, input device: cuda:0 Layer 14: PWCMamba, output device: cuda:0 Layer 15: Conv, input device: cuda:0 Layer 15: Conv, output device: cuda:0 Layer 16: Upsample, input device: cuda:0 Layer 16: Upsample, output device: cuda:0 Layer 17: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 32, 32]) (通道数: 32) 输入1形状: torch.Size([1, 64, 32, 32]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 32, 32]) (拼接后通道数: 96) Layer 17: Concat, output device: cuda:0 Layer 18: Conv, input device: cuda:0 Layer 18: Conv, output device: cuda:0 Layer 19: PWCMamba, input device: cuda:0 Layer 19: PWCMamba, output device: cuda:0 Layer 20: Conv, input device: cuda:0 Layer 20: Conv, output device: cuda:0 Layer 21: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 16, 16]) (通道数: 32) 输入1形状: torch.Size([1, 64, 16, 16]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 16, 16]) (拼接后通道数: 96) Layer 21: Concat, output device: cuda:0 Layer 22: Conv, input device: cuda:0 Layer 22: Conv, output device: cuda:0 Layer 23: PWCMamba, input device: cuda:0 Layer 23: PWCMamba, output device: cuda:0 Layer 24: Conv, input device: cuda:0 Layer 24: Conv, output device: cuda:0 Layer 25: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 8, 8]) (通道数: 64) 输入1形状: torch.Size([1, 128, 8, 8]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 8, 8]) (拼接后通道数: 192) Layer 25: Concat, output device: cuda:0 Layer 26: Conv, input device: cuda:0 Layer 26: Conv, output device: cuda:0 Layer 27: PWCMamba, input device: cuda:0 Layer 27: PWCMamba, output device: cuda:0 Layer 28: Detect, input device: cuda:0 Layer 28: Detect, output device: cuda:0 Ultralytics 8.3.63 🚀 Python-3.10.18 torch-2.1.1+cu118 CUDA:0 (NVIDIA GeForce RTX 2060, 6144MiB) engine\trainer: task=detect, mode=train, model=E:/ultralytics-v8.3.63/ultralytics/models/yolo/pwcmamba/yolov8pwcm.yaml, data=E:/ultralytics-v8.3.63/motogp.yaml, epochs=100, time=None, patience=100, batch=16, imgsz=768, save=True, save_period=-1, cache=True, device=0, workers=2, project=None, name=train12, exist_ok=False, pretrained=False, 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, multi_scale=False, 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, vid_stride=1, stream_buffer=False, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, embed=None, show=False, save_frames=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, show_boxes=True, line_width=None, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=True, opset=None, workspace=None, 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, 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, bgr=0.0, mosaic=1.0, mixup=0.0, copy_paste=0.0, copy_paste_mode=flip, auto_augment=randaugment, erasing=0.4, crop_fraction=1.0, cfg=None, tracker=botsort.yaml, save_dir=runs\detect\train12 WARNING ⚠️ no model scale passed. Assuming scale='n'. from n params module arguments 解析第0层，from=-1，当前ch列表长度=1 0 -1 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2] 解析第0层后，save列表：[] 解析第1层，from=-1，当前ch列表长度=1 1 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2] 解析第1层后，save列表：[] 解析第2层，from=-1，当前ch列表长度=2 2 -1 1 7360 ultralytics.nn.modules.block.C2f [32, 32, 1, True] 解析第2层后，save列表：[] 解析第3层，from=-1，当前ch列表长度=3 3 -1 1 18560 ultralytics.nn.modules.conv.Conv [32, 64, 3, 2] 解析第3层后，save列表：[] 解析第4层，from=-1，当前ch列表长度=4 4 -1 1 29056 ultralytics.nn.modules.block.C2f [64, 64, 1, True] 解析第4层后，save列表：[] 解析第5层，from=-1，当前ch列表长度=5 5 -1 1 73984 ultralytics.nn.modules.conv.Conv [64, 128, 3, 2] 解析第5层后，save列表：[] 解析第6层，from=-1，当前ch列表长度=6 6 -1 1 115456 ultralytics.nn.modules.block.C2f [128, 128, 1, True] 解析第6层后，save列表：[] 解析第7层，from=-1，当前ch列表长度=7 7 -1 1 184640 ultralytics.nn.modules.conv.Conv [128, 160, 3, 2] 解析第7层后，save列表：[] 解析第8层，from=-1，当前ch列表长度=8 8 -1 1 644690 ultralytics.nn.modules.block.PWCMamba [160, 64] 解析第8层后，save列表：[] 解析第9层，from=-1，当前ch列表长度=9 9 -1 1 18752 ultralytics.nn.modules.block.SPPF [64, 128, 5] 解析第9层后，save列表：[] 解析第10层，from=-1，当前ch列表长度=10 10 -1 1 8320 ultralytics.nn.modules.conv.Conv [128, 64, 1, 1] 解析第10层后，save列表：[] 解析第11层，from=-1，当前ch列表长度=11 11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 解析第11层后，save列表：[] 解析第12层，from=[-1, 6]，当前ch列表长度=12 Concat层12：将历史层6加入save列表 12 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1] 解析第12层后，save列表：[6] 解析第13层，from=-1，当前ch列表长度=13 13 -1 1 12416 ultralytics.nn.modules.conv.Conv [192, 64, 1, 1] 解析第13层后，save列表：[6] 解析第14层，from=-1，当前ch列表长度=14 14 -1 1 118178 ultralytics.nn.modules.block.PWCMamba [64, 64] 解析第14层后，save列表：[6] 解析第15层，from=-1，当前ch列表长度=15 15 -1 1 2112 ultralytics.nn.modules.conv.Conv [64, 32, 1, 1] 解析第15层后，save列表：[6] 解析第16层，from=-1，当前ch列表长度=16 16 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 解析第16层后，save列表：[6] 解析第17层，from=[-1, 4]，当前ch列表长度=17 Concat层17：将历史层4加入save列表 17 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1] 解析第17层后，save列表：[4, 6] 解析第18层，from=-1，当前ch列表长度=18 18 -1 1 3136 ultralytics.nn.modules.conv.Conv [96, 32, 1, 1] 解析第18层后，save列表：[4, 6] 解析第19层，from=-1，当前ch列表长度=19 19 -1 1 34770 ultralytics.nn.modules.block.PWCMamba [32, 32] 解析第19层后，save列表：[4, 6] 解析第20层，from=-1，当前ch列表长度=20 20 -1 1 9280 ultralytics.nn.modules.conv.Conv [32, 32, 3, 2] 解析第20层后，save列表：[4, 6] 解析第21层，from=[-1, 14]，当前ch列表长度=21 Concat层21：将历史层14加入save列表 21 [-1, 14] 1 0 ultralytics.nn.modules.conv.Concat [1] 解析第21层后，save列表：[4, 6, 14] 解析第22层，from=-1，当前ch列表长度=22 22 -1 1 6272 ultralytics.nn.modules.conv.Conv [96, 64, 1, 1] 解析第22层后，save列表：[4, 6, 14] 解析第23层，from=-1，当前ch列表长度=23 23 -1 1 118178 ultralytics.nn.modules.block.PWCMamba [64, 64] 解析第23层后，save列表：[4, 6, 14] 解析第24层，from=-1，当前ch列表长度=24 24 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2] 解析第24层后，save列表：[4, 6, 14] 解析第25层，from=[-1, 9]，当前ch列表长度=25 Concat层25：将历史层9加入save列表 25 [-1, 9] 1 0 ultralytics.nn.modules.conv.Concat [1] 解析第25层后，save列表：[4, 6, 9, 14] 解析第26层，from=-1，当前ch列表长度=26 26 -1 1 24832 ultralytics.nn.modules.conv.Conv [192, 128, 1, 1] 解析第26层后，save列表：[4, 6, 9, 14] 解析第27层，from=-1，当前ch列表长度=27 27 -1 1 430914 ultralytics.nn.modules.block.PWCMamba [128, 128] 解析第27层后，save列表：[4, 6, 9, 14] 解析第28层，from=[19, 23, 27]，当前ch列表长度=28 层28：将from列表中的19加入save列表 层28：将from列表中的23加入save列表 层28：将from列表中的27加入save列表 28 [19, 23, 27] 1 267123 ultralytics.nn.modules.head.Detect [1, [32, 64, 128]] 解析第28层后，save列表：[4, 6, 9, 14, 19, 23, 27] Layer 0: Conv, input device: cuda:0 Layer 0: Conv, output device: cuda:0 Layer 1: Conv, input device: cuda:0 Layer 1: Conv, output device: cuda:0 Layer 2: C2f, input device: cuda:0 Layer 2: C2f, output device: cuda:0 Layer 3: Conv, input device: cuda:0 Layer 3: Conv, output device: cuda:0 Layer 4: C2f, input device: cuda:0 Layer 4: C2f, output device: cuda:0 Layer 5: Conv, input device: cuda:0 Layer 5: Conv, output device: cuda:0 Layer 6: C2f, input device: cuda:0 Layer 6: C2f, output device: cuda:0 Layer 7: Conv, input device: cuda:0 Layer 7: Conv, output device: cuda:0 Layer 8: PWCMamba, input device: cuda:0 Layer 8: PWCMamba, output device: cuda:0 Layer 9: SPPF, input device: cuda:0 Layer 9: SPPF, output device: cuda:0 Layer 10: Conv, input device: cuda:0 Layer 10: Conv, output device: cuda:0 Layer 11: Upsample, input device: cuda:0 Layer 11: Upsample, output device: cuda:0 Layer 12: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 16, 16]) (通道数: 64) 输入1形状: torch.Size([1, 128, 16, 16]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 16, 16]) (拼接后通道数: 192) Layer 12: Concat, output device: cuda:0 Layer 13: Conv, input device: cuda:0 Layer 13: Conv, output device: cuda:0 Layer 14: PWCMamba, input device: cuda:0 Layer 14: PWCMamba, output device: cuda:0 Layer 15: Conv, input device: cuda:0 Layer 15: Conv, output device: cuda:0 Layer 16: Upsample, input device: cuda:0 Layer 16: Upsample, output device: cuda:0 Layer 17: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 32, 32]) (通道数: 32) 输入1形状: torch.Size([1, 64, 32, 32]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 32, 32]) (拼接后通道数: 96) Layer 17: Concat, output device: cuda:0 Layer 18: Conv, input device: cuda:0 Layer 18: Conv, output device: cuda:0 Layer 19: PWCMamba, input device: cuda:0 Layer 19: PWCMamba, output device: cuda:0 Layer 20: Conv, input device: cuda:0 Layer 20: Conv, output device: cuda:0 Layer 21: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 16, 16]) (通道数: 32) 输入1形状: torch.Size([1, 64, 16, 16]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 16, 16]) (拼接后通道数: 96) Layer 21: Concat, output device: cuda:0 Layer 22: Conv, input device: cuda:0 Layer 22: Conv, output device: cuda:0 Layer 23: PWCMamba, input device: cuda:0 Layer 23: PWCMamba, output device: cuda:0 Layer 24: Conv, input device: cuda:0 Layer 24: Conv, output device: cuda:0 Layer 25: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 8, 8]) (通道数: 64) 输入1形状: torch.Size([1, 128, 8, 8]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 8, 8]) (拼接后通道数: 192) Layer 25: Concat, output device: cuda:0 Layer 26: Conv, input device: cuda:0 Layer 26: Conv, output device: cuda:0 Layer 27: PWCMamba, input device: cuda:0 Layer 27: PWCMamba, output device: cuda:0 Layer 28: Detect, input device: cuda:0 Layer 28: Detect, output device: cuda:0 Layer 0: Conv, input device: cuda:0 Layer 0: Conv, output device: cuda:0 Layer 1: Conv, input device: cuda:0 Layer 1: Conv, output device: cuda:0 Layer 2: C2f, input device: cuda:0 Layer 2: C2f, output device: cuda:0 Layer 3: Conv, input device: cuda:0 Layer 3: Conv, output device: cuda:0 Layer 4: C2f, input device: cuda:0 Layer 4: C2f, output device: cuda:0 Layer 5: Conv, input device: cuda:0 Layer 5: Conv, output device: cuda:0 Layer 6: C2f, input device: cuda:0 Layer 6: C2f, output device: cuda:0 Layer 7: Conv, input device: cuda:0 Layer 7: Conv, output device: cuda:0 Layer 8: PWCMamba, input device: cuda:0 Layer 8: PWCMamba, output device: cuda:0 Layer 9: SPPF, input device: cuda:0 Layer 9: SPPF, output device: cuda:0 Layer 10: Conv, input device: cuda:0 Layer 10: Conv, output device: cuda:0 Layer 11: Upsample, input device: cuda:0 Layer 11: Upsample, output device: cuda:0 Layer 12: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 16, 16]) (通道数: 64) 输入1形状: torch.Size([1, 128, 16, 16]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 16, 16]) (拼接后通道数: 192) Layer 12: Concat, output device: cuda:0 Layer 13: Conv, input device: cuda:0 Layer 13: Conv, output device: cuda:0 Layer 14: PWCMamba, input device: cuda:0 Layer 14: PWCMamba, output device: cuda:0 Layer 15: Conv, input device: cuda:0 Layer 15: Conv, output device: cuda:0 Layer 16: Upsample, input device: cuda:0 Layer 16: Upsample, output device: cuda:0 Layer 17: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 32, 32]) (通道数: 32) 输入1形状: torch.Size([1, 64, 32, 32]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 32, 32]) (拼接后通道数: 96) Layer 17: Concat, output device: cuda:0 Layer 18: Conv, input device: cuda:0 Layer 18: Conv, output device: cuda:0 Layer 19: PWCMamba, input device: cuda:0 Layer 19: PWCMamba, output device: cuda:0 Layer 20: Conv, input device: cuda:0 Layer 20: Conv, output device: cuda:0 Layer 21: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 16, 16]) (通道数: 32) 输入1形状: torch.Size([1, 64, 16, 16]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 16, 16]) (拼接后通道数: 96) Layer 21: Concat, output device: cuda:0 Layer 22: Conv, input device: cuda:0 Layer 22: Conv, output device: cuda:0 Layer 23: PWCMamba, input device: cuda:0 Layer 23: PWCMamba, output device: cuda:0 Layer 24: Conv, input device: cuda:0 Layer 24: Conv, output device: cuda:0 Layer 25: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 8, 8]) (通道数: 64) 输入1形状: torch.Size([1, 128, 8, 8]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 8, 8]) (拼接后通道数: 192) Layer 25: Concat, output device: cuda:0 Layer 26: Conv, input device: cuda:0 Layer 26: Conv, output device: cuda:0 Layer 27: PWCMamba, input device: cuda:0 Layer 27: PWCMamba, output device: cuda:0 Layer 28: Detect, input device: cuda:0 Layer 28: Detect, output device: cuda:0 Layer 0: Conv, input device: cuda:0 Layer 0: Conv, output device: cuda:0 Layer 1: Conv, input device: cuda:0 Layer 1: Conv, output device: cuda:0 Layer 2: C2f, input device: cuda:0 Layer 2: C2f, output device: cuda:0 Layer 3: Conv, input device: cuda:0 Layer 3: Conv, output device: cuda:0 Layer 4: C2f, input device: cuda:0 Layer 4: C2f, output device: cuda:0 Layer 5: Conv, input device: cuda:0 Layer 5: Conv, output device: cuda:0 Layer 6: C2f, input device: cuda:0 Layer 6: C2f, output device: cuda:0 Layer 7: Conv, input device: cuda:0 Layer 7: Conv, output device: cuda:0 Layer 8: PWCMamba, input device: cuda:0 Layer 8: PWCMamba, output device: cuda:0 Layer 9: SPPF, input device: cuda:0 Layer 9: SPPF, output device: cuda:0 Layer 10: Conv, input device: cuda:0 Layer 10: Conv, output device: cuda:0 Layer 11: Upsample, input device: cuda:0 Layer 11: Upsample, output device: cuda:0 Layer 12: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 16, 16]) (通道数: 64) 输入1形状: torch.Size([1, 128, 16, 16]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 16, 16]) (拼接后通道数: 192) Layer 12: Concat, output device: cuda:0 Layer 13: Conv, input device: cuda:0 Layer 13: Conv, output device: cuda:0 Layer 14: PWCMamba, input device: cuda:0 Layer 14: PWCMamba, output device: cuda:0 Layer 15: Conv, input device: cuda:0 Layer 15: Conv, output device: cuda:0 Layer 16: Upsample, input device: cuda:0 Layer 16: Upsample, output device: cuda:0 Layer 17: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 32, 32]) (通道数: 32) 输入1形状: torch.Size([1, 64, 32, 32]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 32, 32]) (拼接后通道数: 96) Layer 17: Concat, output device: cuda:0 Layer 18: Conv, input device: cuda:0 Layer 18: Conv, output device: cuda:0 Layer 19: PWCMamba, input device: cuda:0 Layer 19: PWCMamba, output device: cuda:0 Layer 20: Conv, input device: cuda:0 Layer 20: Conv, output device: cuda:0 Layer 21: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 16, 16]) (通道数: 32) 输入1形状: torch.Size([1, 64, 16, 16]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 16, 16]) (拼接后通道数: 96) Layer 21: Concat, output device: cuda:0 Layer 22: Conv, input device: cuda:0 Layer 22: Conv, output device: cuda:0 Layer 23: PWCMamba, input device: cuda:0 Layer 23: PWCMamba, output device: cuda:0 Layer 24: Conv, input device: cuda:0 Layer 24: Conv, output device: cuda:0 Layer 25: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 8, 8]) (通道数: 64) 输入1形状: torch.Size([1, 128, 8, 8]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 8, 8]) (拼接后通道数: 192) Layer 25: Concat, output device: cuda:0 Layer 26: Conv, input device: cuda:0 Layer 26: Conv, output device: cuda:0 Layer 27: PWCMamba, input device: cuda:0 Layer 27: PWCMamba, output device: cuda:0 Layer 28: Detect, input device: cuda:0 Layer 28: Detect, output device: cuda:0 Layer 0: Conv, input device: cuda:0 Layer 0: Conv, output device: cuda:0 Layer 1: Conv, input device: cuda:0 Layer 1: Conv, output device: cuda:0 Layer 2: C2f, input device: cuda:0 Layer 2: C2f, output device: cuda:0 Layer 3: Conv, input device: cuda:0 Layer 3: Conv, output device: cuda:0 Layer 4: C2f, input device: cuda:0 Layer 4: C2f, output device: cuda:0 Layer 5: Conv, input device: cuda:0 Layer 5: Conv, output device: cuda:0 Layer 6: C2f, input device: cuda:0 Layer 6: C2f, output device: cuda:0 Layer 7: Conv, input device: cuda:0 Layer 7: Conv, output device: cuda:0 Layer 8: PWCMamba, input device: cuda:0 Layer 8: PWCMamba, output device: cuda:0 Layer 9: SPPF, input device: cuda:0 Layer 9: SPPF, output device: cuda:0 Layer 10: Conv, input device: cuda:0 Layer 10: Conv, output device: cuda:0 Layer 11: Upsample, input device: cuda:0 Layer 11: Upsample, output device: cuda:0 Layer 12: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 16, 16]) (通道数: 64) 输入1形状: torch.Size([1, 128, 16, 16]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 16, 16]) (拼接后通道数: 192) Layer 12: Concat, output device: cuda:0 Layer 13: Conv, input device: cuda:0 Layer 13: Conv, output device: cuda:0 Layer 14: PWCMamba, input device: cuda:0 Layer 14: PWCMamba, output device: cuda:0 Layer 15: Conv, input device: cuda:0 Layer 15: Conv, output device: cuda:0 Layer 16: Upsample, input device: cuda:0 Layer 16: Upsample, output device: cuda:0 Layer 17: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 32, 32]) (通道数: 32) 输入1形状: torch.Size([1, 64, 32, 32]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 32, 32]) (拼接后通道数: 96) Layer 17: Concat, output device: cuda:0 Layer 18: Conv, input device: cuda:0 Layer 18: Conv, output device: cuda:0 Layer 19: PWCMamba, input device: cuda:0 Layer 19: PWCMamba, output device: cuda:0 Layer 20: Conv, input device: cuda:0 Layer 20: Conv, output device: cuda:0 Layer 21: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 16, 16]) (通道数: 32) 输入1形状: torch.Size([1, 64, 16, 16]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 16, 16]) (拼接后通道数: 96) Layer 21: Concat, output device: cuda:0 Layer 22: Conv, input device: cuda:0 Layer 22: Conv, output device: cuda:0 Layer 23: PWCMamba, input device: cuda:0 Layer 23: PWCMamba, output device: cuda:0 Layer 24: Conv, input device: cuda:0 Layer 24: Conv, output device: cuda:0 Layer 25: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 8, 8]) (通道数: 64) 输入1形状: torch.Size([1, 128, 8, 8]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 8, 8]) (拼接后通道数: 192) Layer 25: Concat, output device: cuda:0 Layer 26: Conv, input device: cuda:0 Layer 26: Conv, output device: cuda:0 Layer 27: PWCMamba, input device: cuda:0 Layer 27: PWCMamba, output device: cuda:0 Layer 28: Detect, input device: cuda:0 Layer 28: Detect, output device: cuda:0 Layer 0: Conv, input device: cuda:0 Layer 0: Conv, output device: cuda:0 Layer 1: Conv, input device: cuda:0 Layer 1: Conv, output device: cuda:0 Layer 2: C2f, input device: cuda:0 Layer 2: C2f, output device: cuda:0 Layer 3: Conv, input device: cuda:0 Layer 3: Conv, output device: cuda:0 Layer 4: C2f, input device: cuda:0 Layer 4: C2f, output device: cuda:0 Layer 5: Conv, input device: cuda:0 Layer 5: Conv, output device: cuda:0 Layer 6: C2f, input device: cuda:0 Layer 6: C2f, output device: cuda:0 Layer 7: Conv, input device: cuda:0 Layer 7: Conv, output device: cuda:0 Layer 8: PWCMamba, input device: cuda:0 Layer 8: PWCMamba, output device: cuda:0 Layer 9: SPPF, input device: cuda:0 Layer 9: SPPF, output device: cuda:0 Layer 10: Conv, input device: cuda:0 Layer 10: Conv, output device: cuda:0 Layer 11: Upsample, input device: cuda:0 Layer 11: Upsample, output device: cuda:0 Layer 12: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 16, 16]) (通道数: 64) 输入1形状: torch.Size([1, 128, 16, 16]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 16, 16]) (拼接后通道数: 192) Layer 12: Concat, output device: cuda:0 Layer 13: Conv, input device: cuda:0 Layer 13: Conv, output device: cuda:0 Layer 14: PWCMamba, input device: cuda:0 Layer 14: PWCMamba, output device: cuda:0 Layer 15: Conv, input device: cuda:0 Layer 15: Conv, output device: cuda:0 Layer 16: Upsample, input device: cuda:0 Layer 16: Upsample, output device: cuda:0 Layer 17: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 32, 32]) (通道数: 32) 输入1形状: torch.Size([1, 64, 32, 32]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 32, 32]) (拼接后通道数: 96) Layer 17: Concat, output device: cuda:0 Layer 18: Conv, input device: cuda:0 Layer 18: Conv, output device: cuda:0 Layer 19: PWCMamba, input device: cuda:0 Layer 19: PWCMamba, output device: cuda:0 Layer 20: Conv, input device: cuda:0 Layer 20: Conv, output device: cuda:0 Layer 21: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 16, 16]) (通道数: 32) 输入1形状: torch.Size([1, 64, 16, 16]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 16, 16]) (拼接后通道数: 96) Layer 21: Concat, output device: cuda:0 Layer 22: Conv, input device: cuda:0 Layer 22: Conv, output device: cuda:0 Layer 23: PWCMamba, input device: cuda:0 Layer 23: PWCMamba, output device: cuda:0 Layer 24: Conv, input device: cuda:0 Layer 24: Conv, output device: cuda:0 Layer 25: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 8, 8]) (通道数: 64) 输入1形状: torch.Size([1, 128, 8, 8]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 8, 8]) (拼接后通道数: 192) Layer 25: Concat, output device: cuda:0 Layer 26: Conv, input device: cuda:0 Layer 26: Conv, output device: cuda:0 Layer 27: PWCMamba, input device: cuda:0 Layer 27: PWCMamba, output device: cuda:0 Layer 28: Detect, input device: cuda:0 Layer 28: Detect, output device: cuda:0 Layer 0: Conv, input device: cuda:0 Layer 0: Conv, output device: cuda:0 Layer 1: Conv, input device: cuda:0 Layer 1: Conv, output device: cuda:0 Layer 2: C2f, input device: cuda:0 Layer 2: C2f, output device: cuda:0 Layer 3: Conv, input device: cuda:0 Layer 3: Conv, output device: cuda:0 Layer 4: C2f, input device: cuda:0 Layer 4: C2f, output device: cuda:0 Layer 5: Conv, input device: cuda:0 Layer 5: Conv, output device: cuda:0 Layer 6: C2f, input device: cuda:0 Layer 6: C2f, output device: cuda:0 Layer 7: Conv, input device: cuda:0 Layer 7: Conv, output device: cuda:0 Layer 8: PWCMamba, input device: cuda:0 Layer 8: PWCMamba, output device: cuda:0 Layer 9: SPPF, input device: cuda:0 Layer 9: SPPF, output device: cuda:0 Layer 10: Conv, input device: cuda:0 Layer 10: Conv, output device: cuda:0 Layer 11: Upsample, input device: cuda:0 Layer 11: Upsample, output device: cuda:0 Layer 12: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 16, 16]) (通道数: 64) 输入1形状: torch.Size([1, 128, 16, 16]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 16, 16]) (拼接后通道数: 192) Layer 12: Concat, output device: cuda:0 Layer 13: Conv, input device: cuda:0 Layer 13: Conv, output device: cuda:0 Layer 14: PWCMamba, input device: cuda:0 Layer 14: PWCMamba, output device: cuda:0 Layer 15: Conv, input device: cuda:0 Layer 15: Conv, output device: cuda:0 Layer 16: Upsample, input device: cuda:0 Layer 16: Upsample, output device: cuda:0 Layer 17: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 32, 32]) (通道数: 32) 输入1形状: torch.Size([1, 64, 32, 32]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 32, 32]) (拼接后通道数: 96) Layer 17: Concat, output device: cuda:0 Layer 18: Conv, input device: cuda:0 Layer 18: Conv, output device: cuda:0 Layer 19: PWCMamba, input device: cuda:0 Layer 19: PWCMamba, output device: cuda:0 Layer 20: Conv, input device: cuda:0 Layer 20: Conv, output device: cuda:0 Layer 21: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 16, 16]) (通道数: 32) 输入1形状: torch.Size([1, 64, 16, 16]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 16, 16]) (拼接后通道数: 96) Layer 21: Concat, output device: cuda:0 Layer 22: Conv, input device: cuda:0 Layer 22: Conv, output device: cuda:0 Layer 23: PWCMamba, input device: cuda:0 Layer 23: PWCMamba, output device: cuda:0 Layer 24: Conv, input device: cuda:0 Layer 24: Conv, output device: cuda:0 Layer 25: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 8, 8]) (通道数: 64) 输入1形状: torch.Size([1, 128, 8, 8]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 8, 8]) (拼接后通道数: 192) Layer 25: Concat, output device: cuda:0 Layer 26: Conv, input device: cuda:0 Layer 26: Conv, output device: cuda:0 Layer 27: PWCMamba, input device: cuda:0 Layer 27: PWCMamba, output device: cuda:0 Layer 28: Detect, input device: cuda:0 Layer 28: Detect, output device: cuda:0 Layer 0: Conv, input device: cuda:0 Layer 0: Conv, output device: cuda:0 Layer 1: Conv, input device: cuda:0 Layer 1: Conv, output device: cuda:0 Layer 2: C2f, input device: cuda:0 Layer 2: C2f, output device: cuda:0 Layer 3: Conv, input device: cuda:0 Layer 3: Conv, output device: cuda:0 Layer 4: C2f, input device: cuda:0 Layer 4: C2f, output device: cuda:0 Layer 5: Conv, input device: cuda:0 Layer 5: Conv, output device: cuda:0 Layer 6: C2f, input device: cuda:0 Layer 6: C2f, output device: cuda:0 Layer 7: Conv, input device: cuda:0 Layer 7: Conv, output device: cuda:0 Layer 8: PWCMamba, input device: cuda:0 Layer 8: PWCMamba, output device: cuda:0 Layer 9: SPPF, input device: cuda:0 Layer 9: SPPF, output device: cuda:0 Layer 10: Conv, input device: cuda:0 Layer 10: Conv, output device: cuda:0 Layer 11: Upsample, input device: cuda:0 Layer 11: Upsample, output device: cuda:0 Layer 12: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 4, 4]) (通道数: 64) 输入1形状: torch.Size([1, 128, 4, 4]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 4, 4]) (拼接后通道数: 192) Layer 12: Concat, output device: cuda:0 Layer 13: Conv, input device: cuda:0 Layer 13: Conv, output device: cuda:0 Layer 14: PWCMamba, input device: cuda:0 Layer 14: PWCMamba, output device: cuda:0 Layer 15: Conv, input device: cuda:0 Layer 15: Conv, output device: cuda:0 Layer 16: Upsample, input device: cuda:0 Layer 16: Upsample, output device: cuda:0 Layer 17: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 8, 8]) (通道数: 32) 输入1形状: torch.Size([1, 64, 7, 7]) (通道数: 64) Concat拼接失败: Sizes of tensors must match except in dimension 1. Expected size 8 but got size 7 for tensor number 1 in the list. Layer 0: Conv, input device: cuda:0 Layer 0: Conv, output device: cuda:0 Layer 1: Conv, input device: cuda:0 Layer 1: Conv, output device: cuda:0 Layer 2: C2f, input device: cuda:0 Layer 2: C2f, output device: cuda:0 Layer 3: Conv, input device: cuda:0 Layer 3: Conv, output device: cuda:0 Layer 4: C2f, input device: cuda:0 Layer 4: C2f, output device: cuda:0 Layer 5: Conv, input device: cuda:0 Layer 5: Conv, output device: cuda:0 Layer 6: C2f, input device: cuda:0 Layer 6: C2f, output device: cuda:0 Layer 7: Conv, input device: cuda:0 Layer 7: Conv, output device: cuda:0 Layer 8: PWCMamba, input device: cuda:0 Layer 8: PWCMamba, output device: cuda:0 Layer 9: SPPF, input device: cuda:0 Layer 9: SPPF, output device: cuda:0 Layer 10: Conv, input device: cuda:0 Layer 10: Conv, output device: cuda:0 Layer 11: Upsample, input device: cuda:0 Layer 11: Upsample, output device: cuda:0 Layer 12: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 40, 40]) (通道数: 64) 输入1形状: torch.Size([1, 128, 40, 40]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 40, 40]) (拼接后通道数: 192) Layer 12: Concat, output device: cuda:0 Layer 13: Conv, input device: cuda:0 Layer 13: Conv, output device: cuda:0 Layer 14: PWCMamba, input device: cuda:0 Layer 14: PWCMamba, output device: cuda:0 Layer 15: Conv, input device: cuda:0 Layer 15: Conv, output device: cuda:0 Layer 16: Upsample, input device: cuda:0 Layer 16: Upsample, output device: cuda:0 Layer 17: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 80, 80]) (通道数: 32) 输入1形状: torch.Size([1, 64, 80, 80]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 80, 80]) (拼接后通道数: 96) Layer 17: Concat, output device: cuda:0 Layer 18: Conv, input device: cuda:0 Layer 18: Conv, output device: cuda:0 Layer 19: PWCMamba, input device: cuda:0 Layer 19: PWCMamba, output device: cuda:0 Layer 20: Conv, input device: cuda:0 Layer 20: Conv, output device: cuda:0 Layer 21: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 32, 40, 40]) (通道数: 32) 输入1形状: torch.Size([1, 64, 40, 40]) (通道数: 64) Concat输出形状: torch.Size([1, 96, 40, 40]) (拼接后通道数: 96) Layer 21: Concat, output device: cuda:0 Layer 22: Conv, input device: cuda:0 Layer 22: Conv, output device: cuda:0 Layer 23: PWCMamba, input device: cuda:0 Layer 23: PWCMamba, output device: cuda:0 Layer 24: Conv, input device: cuda:0 Layer 24: Conv, output device: cuda:0 Layer 25: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([1, 64, 20, 20]) (通道数: 64) 输入1形状: torch.Size([1, 128, 20, 20]) (通道数: 128) Concat输出形状: torch.Size([1, 192, 20, 20]) (拼接后通道数: 192) Layer 25: Concat, output device: cuda:0 Layer 26: Conv, input device: cuda:0 Layer 26: Conv, output device: cuda:0 Layer 27: PWCMamba, input device: cuda:0 Layer 27: PWCMamba, output device: cuda:0 Layer 28: Detect, input device: cuda:0 Layer 28: Detect, output device: cuda:0 YOLOv8pwcm summary: 643 layers, 2,170,157 parameters, 2,170,141 gradients, 5.0 GFLOPs Freezing layer 'model.28.dfl.conv.weight' AMP: running Automatic Mixed Precision (AMP) checks... AMP: checks skipped ⚠️. Unable to load YOLO11n for AMP checks due to possible Ultralytics package modifications. Setting 'amp=True'. If you experience zero-mAP or NaN losses you can disable AMP with amp=False. WARNING ⚠️ imgsz=[768] must be multiple of max stride 51, updating to [816] train: Scanning E:\ultralytics-v8.3.63\datasets\Motogp.v1i.yolov8\train\labels.cache... 97 images, 11 backgrounds, 0 corrupt: 100%|██████████| 97/97 [00:00<?, ?it/s] WARNING ⚠️ cache='ram' may produce non-deterministic training results. Consider cache='disk' as a deterministic alternative if your disk space allows. train: Caching images (0.1GB RAM): 100%|██████████| 97/97 [00:00<00:00, 549.04it/s] val: Scanning E:\ultralytics-v8.3.63\datasets\Motogp.v1i.yolov8\valid\labels.cache... 28 images, 4 backgrounds, 0 corrupt: 100%|██████████| 28/28 [00:00<?, ?it/s] WARNING ⚠️ cache='ram' may produce non-deterministic training results. Consider cache='disk' as a deterministic alternative if your disk space allows. val: Caching images (0.0GB RAM): 100%|██████████| 28/28 [00:00<00:00, 282.27it/s] WARNING ⚠️ imgsz=[816] must be multiple of max stride 32, updating to [832] No module named 'seaborn' optimizer: 'optimizer=auto' found, ignoring 'lr0=0.01' and 'momentum=0.937' and determining best 'optimizer', 'lr0' and 'momentum' automatically... optimizer: AdamW(lr=0.002, momentum=0.9) with parameter groups 145 weight(decay=0.0), 177 weight(decay=0.0005), 161 bias(decay=0.0) Image sizes 816 train, 816 val Using 2 dataloader workers Logging results to runs\detect\train12 Starting training for 100 epochs... Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size Layer 0: Conv, input device: cuda:0 0%| | 0/7 [00:00<?, ?it/s]Layer 0: Conv, output device: cuda:0 Layer 1: Conv, input device: cuda:0 Layer 1: Conv, output device: cuda:0 Layer 2: C2f, input device: cuda:0 Layer 2: C2f, output device: cuda:0 Layer 3: Conv, input device: cuda:0 Layer 3: Conv, output device: cuda:0 Layer 4: C2f, input device: cuda:0 Layer 4: C2f, output device: cuda:0 Layer 5: Conv, input device: cuda:0 Layer 5: Conv, output device: cuda:0 Layer 6: C2f, input device: cuda:0 Layer 6: C2f, output device: cuda:0 Layer 7: Conv, input device: cuda:0 Layer 7: Conv, output device: cuda:0 Layer 8: PWCMamba, input device: cuda:0 Layer 8: PWCMamba, output device: cuda:0 Layer 9: SPPF, input device: cuda:0 Layer 9: SPPF, output device: cuda:0 Layer 10: Conv, input device: cuda:0 Layer 10: Conv, output device: cuda:0 Layer 11: Upsample, input device: cuda:0 Layer 11: Upsample, output device: cuda:0 Layer 12: Concat, input device: cuda:0 Concat层输入张量数量: 2 输入0形状: torch.Size([16, 64, 52, 52]) (通道数: 64) 输入1形状: torch.Size([16, 128, 51, 51]) (通道数: 128) Concat拼接失败: Sizes of tensors must match except in dimension 1. Expected size 52 but got size 51 for tensor number 1 in the list. 0%| | 0/7 [00:00<?, ?it/s] Traceback (most recent call last): File "E:\ultralytics-v8.3.63\ultralytics\models\yolo\pwcmamba\ceshi.py", line 21, in <module> train() File "E:\ultralytics-v8.3.63\ultralytics\models\yolo\pwcmamba\ceshi.py", line 8, in train results = model.train( File "E:\ultralytics-v8.3.63\ultralytics\engine\model.py", line 806, in train self.trainer.train() File "E:\ultralytics-v8.3.63\ultralytics\engine\trainer.py", line 207, in train self._do_train(world_size) File "E:\ultralytics-v8.3.63\ultralytics\engine\trainer.py", line 381, in _do_train self.loss, self.loss_items = self.model(batch) File "D:\anaconda\envs\mamba\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "D:\anaconda\envs\mamba\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "E:\ultralytics-v8.3.63\ultralytics\nn\tasks.py", line 525, in forward return super().forward(x, *args, **kwargs) File "E:\ultralytics-v8.3.63\ultralytics\nn\tasks.py", line 110, in forward return self.predict(x, *args, **kwargs) File "E:\ultralytics-v8.3.63\ultralytics\nn\tasks.py", line 128, in predict return self._predict_once(x, profile, visualize, embed) File "E:\ultralytics-v8.3.63\ultralytics\nn\tasks.py", line 175, in _predict_once x = m(x) # 前向传播 File "D:\anaconda\envs\mamba\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "D:\anaconda\envs\mamba\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) File "E:\ultralytics-v8.3.63\ultralytics\nn\modules\conv.py", line 350, in forward result = torch.cat(x, dim=self.d) RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 52 but got size 51 for tensor number 1 in the list. 进程已结束，退出代码为 1
09-03
from torchvision import transforms transform = transforms.Compose([ transforms.Resize((52, 52)), transforms.ToTensor() ]) # 假设 image 是输入图像 # resized_image = transform(image) ```
warnings.warn( Ultralytics YOLOv8.0.98 Python-3.9.23 torch-2.7.1+cu126 CUDA:0 (NVIDIA GeForce RTX 4060 Laptop GPU, 8188MiB) yolo\engine\trainer: task=detect, mode=train, model=yolov8n.pt, data=weilong.yaml, epochs=500, patience=50, batch=32, imgsz=640, save=True, save_period=-1, cache=False, device=0, workers=8, project=None, name=None, exist_ok=False, pretrained=False, optimizer=SGD, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=0, resume=False, amp=True, 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, 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, v5loader=False, tracker=botsort.yaml, save_dir=runs\detect\train Overriding model.yaml nc=80 with nc=1 from n params module arguments 0 -1 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2] 1 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2] 2 -1 1 7360 ultralytics.nn.modules.block.C2f [32, 32, 1, True] 3 -1 1 18560 ultralytics.nn.modules.conv.Conv [32, 64, 3, 2] 4 -1 2 49664 ultralytics.nn.modules.block.C2f [64, 64, 2, True] 5 -1 1 73984 ultralytics.nn.modules.conv.Conv [64, 128, 3, 2] 6 -1 2 197632 ultralytics.nn.modules.block.C2f [128, 128, 2, True] 7 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2] 8 -1 1 460288 ultralytics.nn.modules.block.C2f [256, 256, 1, True] 9 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5] 10 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 11 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1] 12 -1 1 148224 ultralytics.nn.modules.block.C2f [384, 128, 1] 13 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 14 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1] 15 -1 1 37248 ultralytics.nn.modules.block.C2f [192, 64, 1] 16 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2] 17 [-1, 12] 1 0 ultralytics.nn.modules.conv.Concat [1] 18 -1 1 123648 ultralytics.nn.modules.block.C2f [192, 128, 1] 19 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2] 20 [-1, 9] 1 0 ultralytics.nn.modules.conv.Concat [1] 21 -1 1 493056 ultralytics.nn.modules.block.C2f [384, 256, 1] 22 [15, 18, 21] 1 751507 ultralytics.nn.modules.head.Detect [1, [64, 128, 256]] Model summary: 225 layers, 3011043 parameters, 3011027 gradients, 8.2 GFLOPs Transferred 319/355 items from pretrained weights AMP: running Automatic Mixed Precision (AMP) checks with YOLOv8n... D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py:658: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with torch.cuda.amp.autocast(True): AMP: checks passed D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py:218: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead. self.scaler = amp.GradScaler(enabled=self.amp) optimizer: SGD(lr=0.01) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0005), 63 bias train: Scanning D:\yolov8.98\ultralytics-v8.0.98\weilong\labels\train.cache... 5 images, 0 backgrounds, 0 corrupt: 100%|██████████| 5/5 [00:00<?, ?it/s] D:\ai\anaconda\envs\py391\lib\site-packages\requests\__init__.py:86: RequestsDependencyWarning: Unable to find acceptable character detection dependency (chardet or charset_normalizer). warnings.warn( D:\ai\anaconda\envs\py391\lib\site-packages\requests\__init__.py:86: RequestsDependencyWarning: Unable to find acceptable character detection dependency (chardet or charset_normalizer). warnings.warn( D:\ai\anaconda\envs\py391\lib\site-packages\requests\__init__.py:86: RequestsDependencyWarning: Unable to find acceptable character detection dependency (chardet or charset_normalizer). warnings.warn( D:\ai\anaconda\envs\py391\lib\site-packages\requests\__init__.py:86: RequestsDependencyWarning: Unable to find acceptable character detection dependency (chardet or charset_normalizer). warnings.warn( val: Scanning D:\yolov8.98\ultralytics-v8.0.98\weilong\labels\val.cache... 2 images, 0 backgrounds, 0 corrupt: 100%|██████████| 2/2 [00:00<?, ?it/s] D:\ai\anaconda\envs\py391\lib\site-packages\requests\__init__.py:86: RequestsDependencyWarning: Unable to find acceptable character detection dependency (chardet or charset_normalizer). warnings.warn( Image sizes 640 train, 640 val Using 5 dataloader workers Logging results to runs\detect\train Starting training for 500 epochs... Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 0%| | 0/1 [00:00<?, ?it/s]D:\ai\anaconda\envs\py391\lib\site-packages\requests\__init__.py:86: RequestsDependencyWarning: Unable to find acceptable character detection dependency (chardet or charset_normalizer). No module named 'seaborn' warnings.warn( D:\ai\anaconda\envs\py391\lib\site-packages\requests\__init__.py:86: RequestsDependencyWarning: Unable to find acceptable character detection dependency (chardet or charset_normalizer). warnings.warn( New https://pypi.org/project/ultralytics/8.3.179 available Update with 'pip install -U ultralytics' Ultralytics YOLOv8.0.98 Python-3.9.23 torch-2.7.1+cu126 CUDA:0 (NVIDIA GeForce RTX 4060 Laptop GPU, 8188MiB) yolo\engine\trainer: task=detect, mode=train, model=yolov8n.pt, data=weilong.yaml, epochs=500, patience=50, batch=32, imgsz=640, save=True, save_period=-1, cache=False, device=0, workers=8, project=None, name=None, exist_ok=False, pretrained=False, optimizer=SGD, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=0, resume=False, amp=True, 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, 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, v5loader=False, tracker=botsort.yaml, save_dir=runs\detect\train2 Overriding model.yaml nc=80 with nc=1 from n params module arguments 0 -1 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2] 1 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2] 2 -1 1 7360 ultralytics.nn.modules.block.C2f [32, 32, 1, True] 3 -1 1 18560 ultralytics.nn.modules.conv.Conv [32, 64, 3, 2] 4 -1 2 49664 ultralytics.nn.modules.block.C2f [64, 64, 2, True] 5 -1 1 73984 ultralytics.nn.modules.conv.Conv [64, 128, 3, 2] 6 -1 2 197632 ultralytics.nn.modules.block.C2f [128, 128, 2, True] 7 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2] 8 -1 1 460288 ultralytics.nn.modules.block.C2f [256, 256, 1, True] 9 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5] 10 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 11 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1] 12 -1 1 148224 ultralytics.nn.modules.block.C2f [384, 128, 1] 13 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 14 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1] 15 -1 1 37248 ultralytics.nn.modules.block.C2f [192, 64, 1] 16 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2] 17 [-1, 12] 1 0 ultralytics.nn.modules.conv.Concat [1] 18 -1 1 123648 ultralytics.nn.modules.block.C2f [192, 128, 1] 19 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2] 20 [-1, 9] 1 0 ultralytics.nn.modules.conv.Concat [1] 21 -1 1 493056 ultralytics.nn.modules.block.C2f [384, 256, 1] 22 [15, 18, 21] 1 751507 ultralytics.nn.modules.head.Detect [1, [64, 128, 256]] New https://pypi.org/project/ultralytics/8.3.179 available Update with 'pip install -U ultralytics' Ultralytics YOLOv8.0.98 Python-3.9.23 torch-2.7.1+cu126 CUDA:0 (NVIDIA GeForce RTX 4060 Laptop GPU, 8188MiB) Model summary: 225 layers, 3011043 parameters, 3011027 gradients, 8.2 GFLOPs Transferred 319/355 items from pretrained weights yolo\engine\trainer: task=detect, mode=train, model=yolov8n.pt, data=weilong.yaml, epochs=500, patience=50, batch=32, imgsz=640, save=True, save_period=-1, cache=False, device=0, workers=8, project=None, name=None, exist_ok=False, pretrained=False, optimizer=SGD, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=0, resume=False, amp=True, 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, 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, v5loader=False, tracker=botsort.yaml, save_dir=runs\detect\train3 Overriding model.yaml nc=80 with nc=1 from n params module arguments 0 -1 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2] 1 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2] 2 -1 1 7360 ultralytics.nn.modules.block.C2f [32, 32, 1, True] 3 -1 1 18560 ultralytics.nn.modules.conv.Conv [32, 64, 3, 2] 4 -1 2 49664 ultralytics.nn.modules.block.C2f [64, 64, 2, True] 5 -1 1 73984 ultralytics.nn.modules.conv.Conv [64, 128, 3, 2] 6 -1 2 197632 ultralytics.nn.modules.block.C2f [128, 128, 2, True] 7 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2] 8 -1 1 460288 ultralytics.nn.modules.block.C2f [256, 256, 1, True] 9 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5] 10 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 11 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1] 12 -1 1 148224 ultralytics.nn.modules.block.C2f [384, 128, 1] 13 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 14 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1] 15 -1 1 37248 ultralytics.nn.modules.block.C2f [192, 64, 1] 16 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2] 17 [-1, 12] 1 0 ultralytics.nn.modules.conv.Concat [1] 18 -1 1 123648 ultralytics.nn.modules.block.C2f [192, 128, 1] 19 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2] 20 [-1, 9] 1 0 ultralytics.nn.modules.conv.Concat [1] 21 -1 1 493056 ultralytics.nn.modules.block.C2f [384, 256, 1] 22 [15, 18, 21] 1 751507 ultralytics.nn.modules.head.Detect [1, [64, 128, 256]] AMP: running Automatic Mixed Precision (AMP) checks with YOLOv8n... Model summary: 225 layers, 3011043 parameters, 3011027 gradients, 8.2 GFLOPs Transferred 319/355 items from pretrained weights AMP: running Automatic Mixed Precision (AMP) checks with YOLOv8n... D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py:658: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with torch.cuda.amp.autocast(True): D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py:658: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with torch.cuda.amp.autocast(True): AMP: checks passed D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py:218: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead. self.scaler = amp.GradScaler(enabled=self.amp) optimizer: SGD(lr=0.01) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0005), 63 bias train: Scanning D:\yolov8.98\ultralytics-v8.0.98\weilong\labels\train.cache... 5 images, 0 backgrounds, 0 corrupt: 100%|██████████| 5/5 [00:00<?, ?it/s] Traceback (most recent call last): File "<string>", line 1, in <module> File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 116, in spawn_main exitcode = _main(fd, parent_sentinel) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 125, in _main prepare(preparation_data) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 236, in prepare _fixup_main_from_path(data['init_main_from_path']) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path main_content = runpy.run_path(main_path, File "D:\ai\anaconda\envs\py391\lib\runpy.py", line 288, in run_path return _run_module_code(code, init_globals, run_name, File "D:\ai\anaconda\envs\py391\lib\runpy.py", line 97, in _run_module_code _run_code(code, mod_globals, init_globals, File "D:\ai\anaconda\envs\py391\lib\runpy.py", line 87, in _run_code exec(code, run_globals) File "D:\yolov8.98\ultralytics-v8.0.98\train.py", line 3, in <module> a1.train( File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\model.py", line 370, in train self.trainer.train() File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 191, in train self._do_train(world_size) File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 268, in _do_train self._setup_train(world_size) File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 250, in _setup_train self.train_loader = self.get_dataloader(self.trainset, batch_size=batch_size, rank=RANK, mode='train') File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\v8\detect\train.py", line 65, in get_dataloader return build_dataloader(dataset, batch_size, workers, shuffle, rank) # return dataloader File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\data\build.py", line 100, in build_dataloader return InfiniteDataLoader(dataset=dataset, File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\data\build.py", line 29, in __init__ self.iterator = super().__iter__() File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 493, in __iter__ return self._get_iterator() File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 424, in _get_iterator return _MultiProcessingDataLoaderIter(self) File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 1171, in __init__ w.start() File "D:\ai\anaconda\envs\py391\lib\multiprocessing\process.py", line 121, in start self._popen = self._Popen(self) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\context.py", line 224, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\context.py", line 327, in _Popen return Popen(process_obj) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\popen_spawn_win32.py", line 45, in __init__ prep_data = spawn.get_preparation_data(process_obj._name) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 154, in get_preparation_data _check_not_importing_main() File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main raise RuntimeError(''' RuntimeError: An attempt has been made to start a new process before the current process has finished its bootstrapping phase. This probably means that you are not using fork to start your child processes and you have forgotten to use the proper idiom in the main module: if __name__ == '__main__': freeze_support() ... The "freeze_support()" line can be omitted if the program is not going to be frozen to produce an executable. Ultralytics YOLOv8.0.98 Python-3.9.23 torch-2.7.1+cu126 CUDA:0 (NVIDIA GeForce RTX 4060 Laptop GPU, 8188MiB) yolo\engine\trainer: task=detect, mode=train, model=yolov8n.pt, data=weilong.yaml, epochs=500, patience=50, batch=32, imgsz=640, save=True, save_period=-1, cache=False, device=0, workers=8, project=None, name=None, exist_ok=False, pretrained=False, optimizer=SGD, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=0, resume=False, amp=True, 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, 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, v5loader=False, tracker=botsort.yaml, save_dir=runs\detect\train4 Overriding model.yaml nc=80 with nc=1 from n params module arguments 0 -1 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2] 1 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2] 2 -1 1 7360 ultralytics.nn.modules.block.C2f [32, 32, 1, True] 3 -1 1 18560 ultralytics.nn.modules.conv.Conv [32, 64, 3, 2] AMP: checks passed 4 -1 2 49664 ultralytics.nn.modules.block.C2f [64, 64, 2, True] D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py:218: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead. self.scaler = amp.GradScaler(enabled=self.amp) 5 -1 1 73984 ultralytics.nn.modules.conv.Conv [64, 128, 3, 2] optimizer: SGD(lr=0.01) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0005), 63 bias 6 -1 2 197632 ultralytics.nn.modules.block.C2f [128, 128, 2, True] 7 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2] train: Scanning D:\yolov8.98\ultralytics-v8.0.98\weilong\labels\train.cache... 5 images, 0 backgrounds, 0 corrupt: 100%|██████████| 5/5 [00:00<?, ?it/s] 8 -1 1 460288 ultralytics.nn.modules.block.C2f [256, 256, 1, True] Traceback (most recent call last): File "<string>", line 1, in <module> 9 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5] 10 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 11 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1] File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 116, in spawn_main exitcode = _main(fd, parent_sentinel) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 125, in _main prepare(preparation_data) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 236, in prepare _fixup_main_from_path(data['init_main_from_path']) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path 12 -1 1 148224 ultralytics.nn.modules.block.C2f [384, 128, 1] 13 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 14 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1] main_content = runpy.run_path(main_path, File "D:\ai\anaconda\envs\py391\lib\runpy.py", line 288, in run_path return _run_module_code(code, init_globals, run_name, File "D:\ai\anaconda\envs\py391\lib\runpy.py", line 97, in _run_module_code _run_code(code, mod_globals, init_globals, File "D:\ai\anaconda\envs\py391\lib\runpy.py", line 87, in _run_code exec(code, run_globals) File "D:\yolov8.98\ultralytics-v8.0.98\train.py", line 3, in <module> 15 -1 1 37248 ultralytics.nn.modules.block.C2f [192, 64, 1] a1.train( File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\model.py", line 370, in train self.trainer.train() File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 191, in train 16 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2] 17 [-1, 12] 1 0 ultralytics.nn.modules.conv.Concat [1] self._do_train(world_size) File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 268, in _do_train self._setup_train(world_size) File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 250, in _setup_train self.train_loader = self.get_dataloader(self.trainset, batch_size=batch_size, rank=RANK, mode='train') File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\v8\detect\train.py", line 65, in get_dataloader return build_dataloader(dataset, batch_size, workers, shuffle, rank) # return dataloader File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\data\build.py", line 100, in build_dataloader return InfiniteDataLoader(dataset=dataset, File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\data\build.py", line 29, in __init__ 18 -1 1 123648 ultralytics.nn.modules.block.C2f [192, 128, 1] self.iterator = super().__iter__() File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 493, in __iter__ return self._get_iterator() File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 424, in _get_iterator return _MultiProcessingDataLoaderIter(self) File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 1171, in __init__ w.start() File "D:\ai\anaconda\envs\py391\lib\multiprocessing\process.py", line 121, in start 19 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2] 20 [-1, 9] 1 0 ultralytics.nn.modules.conv.Concat [1] self._popen = self._Popen(self) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\context.py", line 224, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\context.py", line 327, in _Popen return Popen(process_obj) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\popen_spawn_win32.py", line 45, in __init__ prep_data = spawn.get_preparation_data(process_obj._name) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 154, in get_preparation_data _check_not_importing_main() File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main raise RuntimeError(''' RuntimeError: An attempt has been made to start a new process before the current process has finished its bootstrapping phase. This probably means that you are not using fork to start your child processes and you have forgotten to use the proper idiom in the main module: if __name__ == '__main__': freeze_support() ... The "freeze_support()" line can be omitted if the program is not going to be frozen to produce an executable. 21 -1 1 493056 ultralytics.nn.modules.block.C2f [384, 256, 1] 22 [15, 18, 21] 1 751507 ultralytics.nn.modules.head.Detect [1, [64, 128, 256]] Model summary: 225 layers, 3011043 parameters, 3011027 gradients, 8.2 GFLOPs Transferred 319/355 items from pretrained weights AMP: running Automatic Mixed Precision (AMP) checks with YOLOv8n... Ultralytics YOLOv8.0.98 Python-3.9.23 torch-2.7.1+cu126 CUDA:0 (NVIDIA GeForce RTX 4060 Laptop GPU, 8188MiB) yolo\engine\trainer: task=detect, mode=train, model=yolov8n.pt, data=weilong.yaml, epochs=500, patience=50, batch=32, imgsz=640, save=True, save_period=-1, cache=False, device=0, workers=8, project=None, name=None, exist_ok=False, pretrained=False, optimizer=SGD, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=0, resume=False, amp=True, 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, 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, v5loader=False, tracker=botsort.yaml, save_dir=runs\detect\train5 Overriding model.yaml nc=80 with nc=1 from n params module arguments 0 -1 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2] 1 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2] 2 -1 1 7360 ultralytics.nn.modules.block.C2f [32, 32, 1, True] 3 -1 1 18560 ultralytics.nn.modules.conv.Conv [32, 64, 3, 2] 4 -1 2 49664 ultralytics.nn.modules.block.C2f [64, 64, 2, True] 5 -1 1 73984 ultralytics.nn.modules.conv.Conv [64, 128, 3, 2] 6 -1 2 197632 ultralytics.nn.modules.block.C2f [128, 128, 2, True] 7 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2] 8 -1 1 460288 ultralytics.nn.modules.block.C2f [256, 256, 1, True] 9 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5] 10 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 11 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1] 12 -1 1 148224 ultralytics.nn.modules.block.C2f [384, 128, 1] 13 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 14 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1] 15 -1 1 37248 ultralytics.nn.modules.block.C2f [192, 64, 1] 16 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2] 17 [-1, 12] 1 0 ultralytics.nn.modules.conv.Concat [1] 18 -1 1 123648 ultralytics.nn.modules.block.C2f [192, 128, 1] 19 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2] 20 [-1, 9] 1 0 ultralytics.nn.modules.conv.Concat [1] 21 -1 1 493056 ultralytics.nn.modules.block.C2f [384, 256, 1] 22 [15, 18, 21] 1 751507 ultralytics.nn.modules.head.Detect [1, [64, 128, 256]] Model summary: 225 layers, 3011043 parameters, 3011027 gradients, 8.2 GFLOPs Transferred 319/355 items from pretrained weights AMP: running Automatic Mixed Precision (AMP) checks with YOLOv8n... New https://pypi.org/project/ultralytics/8.3.179 available Update with 'pip install -U ultralytics' Ultralytics YOLOv8.0.98 Python-3.9.23 torch-2.7.1+cu126 CUDA:0 (NVIDIA GeForce RTX 4060 Laptop GPU, 8188MiB) yolo\engine\trainer: task=detect, mode=train, model=yolov8n.pt, data=weilong.yaml, epochs=500, patience=50, batch=32, imgsz=640, save=True, save_period=-1, cache=False, device=0, workers=8, project=None, name=None, exist_ok=False, pretrained=False, optimizer=SGD, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=0, resume=False, amp=True, 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, 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, v5loader=False, tracker=botsort.yaml, save_dir=runs\detect\train6 Overriding model.yaml nc=80 with nc=1 from n params module arguments 0 -1 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2] 1 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2] 2 -1 1 7360 ultralytics.nn.modules.block.C2f [32, 32, 1, True] 3 -1 1 18560 ultralytics.nn.modules.conv.Conv [32, 64, 3, 2] 4 -1 2 49664 ultralytics.nn.modules.block.C2f [64, 64, 2, True] 5 -1 1 73984 ultralytics.nn.modules.conv.Conv [64, 128, 3, 2] 6 -1 2 197632 ultralytics.nn.modules.block.C2f [128, 128, 2, True] 7 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2] 8 -1 1 460288 ultralytics.nn.modules.block.C2f [256, 256, 1, True] 9 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5] 10 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 11 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1] 12 -1 1 148224 ultralytics.nn.modules.block.C2f [384, 128, 1] 13 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 14 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1] 15 -1 1 37248 ultralytics.nn.modules.block.C2f [192, 64, 1] 16 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2] 17 [-1, 12] 1 0 ultralytics.nn.modules.conv.Concat [1] 18 -1 1 123648 ultralytics.nn.modules.block.C2f [192, 128, 1] 19 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2] 20 [-1, 9] 1 0 ultralytics.nn.modules.conv.Concat [1] 21 -1 1 493056 ultralytics.nn.modules.block.C2f [384, 256, 1] 22 [15, 18, 21] 1 751507 ultralytics.nn.modules.head.Detect [1, [64, 128, 256]] Model summary: 225 layers, 3011043 parameters, 3011027 gradients, 8.2 GFLOPs Transferred 319/355 items from pretrained weights D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py:658: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with torch.cuda.amp.autocast(True): AMP: running Automatic Mixed Precision (AMP) checks with YOLOv8n... AMP: checks passed D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py:218: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead. self.scaler = amp.GradScaler(enabled=self.amp) optimizer: SGD(lr=0.01) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0005), 63 bias train: Scanning D:\yolov8.98\ultralytics-v8.0.98\weilong\labels\train.cache... 5 images, 0 backgrounds, 0 corrupt: 100%|██████████| 5/5 [00:00<?, ?it/s] Traceback (most recent call last): File "<string>", line 1, in <module> File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 116, in spawn_main exitcode = _main(fd, parent_sentinel) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 125, in _main prepare(preparation_data) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 236, in prepare _fixup_main_from_path(data['init_main_from_path']) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path main_content = runpy.run_path(main_path, File "D:\ai\anaconda\envs\py391\lib\runpy.py", line 288, in run_path return _run_module_code(code, init_globals, run_name, File "D:\ai\anaconda\envs\py391\lib\runpy.py", line 97, in _run_module_code _run_code(code, mod_globals, init_globals, File "D:\ai\anaconda\envs\py391\lib\runpy.py", line 87, in _run_code exec(code, run_globals) File "D:\yolov8.98\ultralytics-v8.0.98\train.py", line 3, in <module> a1.train( File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\model.py", line 370, in train self.trainer.train() File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 191, in train self._do_train(world_size) File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 268, in _do_train self._setup_train(world_size) File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 250, in _setup_train self.train_loader = self.get_dataloader(self.trainset, batch_size=batch_size, rank=RANK, mode='train') File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\v8\detect\train.py", line 65, in get_dataloader return build_dataloader(dataset, batch_size, workers, shuffle, rank) # return dataloader File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\data\build.py", line 100, in build_dataloader return InfiniteDataLoader(dataset=dataset, File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\data\build.py", line 29, in __init__ self.iterator = super().__iter__() File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 493, in __iter__ return self._get_iterator() File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 424, in _get_iterator return _MultiProcessingDataLoaderIter(self) File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 1171, in __init__ w.start() File "D:\ai\anaconda\envs\py391\lib\multiprocessing\process.py", line 121, in start self._popen = self._Popen(self) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\context.py", line 224, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\context.py", line 327, in _Popen return Popen(process_obj) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\popen_spawn_win32.py", line 45, in __init__ prep_data = spawn.get_preparation_data(process_obj._name) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 154, in get_preparation_data _check_not_importing_main() File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main raise RuntimeError(''' RuntimeError: An attempt has been made to start a new process before the current process has finished its bootstrapping phase. This probably means that you are not using fork to start your child processes and you have forgotten to use the proper idiom in the main module: if __name__ == '__main__': freeze_support() ... The "freeze_support()" line can be omitted if the program is not going to be frozen to produce an executable. D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py:658: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with torch.cuda.amp.autocast(True): AMP: checks passed D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py:218: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead. self.scaler = amp.GradScaler(enabled=self.amp) optimizer: SGD(lr=0.01) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0005), 63 bias train: Scanning D:\yolov8.98\ultralytics-v8.0.98\weilong\labels\train.cache... 5 images, 0 backgrounds, 0 corrupt: 100%|██████████| 5/5 [00:00<?, ?it/s] Traceback (most recent call last): File "<string>", line 1, in <module> File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 116, in spawn_main exitcode = _main(fd, parent_sentinel) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 125, in _main prepare(preparation_data) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 236, in prepare _fixup_main_from_path(data['init_main_from_path']) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path main_content = runpy.run_path(main_path, File "D:\ai\anaconda\envs\py391\lib\runpy.py", line 288, in run_path return _run_module_code(code, init_globals, run_name, File "D:\ai\anaconda\envs\py391\lib\runpy.py", line 97, in _run_module_code _run_code(code, mod_globals, init_globals, File "D:\ai\anaconda\envs\py391\lib\runpy.py", line 87, in _run_code exec(code, run_globals) File "D:\yolov8.98\ultralytics-v8.0.98\train.py", line 3, in <module> a1.train( File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\model.py", line 370, in train self.trainer.train() File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 191, in train self._do_train(world_size) File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 268, in _do_train self._setup_train(world_size) File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 250, in _setup_train self.train_loader = self.get_dataloader(self.trainset, batch_size=batch_size, rank=RANK, mode='train') File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\v8\detect\train.py", line 65, in get_dataloader return build_dataloader(dataset, batch_size, workers, shuffle, rank) # return dataloader File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\data\build.py", line 100, in build_dataloader return InfiniteDataLoader(dataset=dataset, File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\data\build.py", line 29, in __init__ self.iterator = super().__iter__() File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 493, in __iter__ return self._get_iterator() File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 424, in _get_iterator return _MultiProcessingDataLoaderIter(self) File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 1171, in __init__ w.start() File "D:\ai\anaconda\envs\py391\lib\multiprocessing\process.py", line 121, in start self._popen = self._Popen(self) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\context.py", line 224, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\context.py", line 327, in _Popen return Popen(process_obj) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\popen_spawn_win32.py", line 45, in __init__ prep_data = spawn.get_preparation_data(process_obj._name) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 154, in get_preparation_data _check_not_importing_main() File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main raise RuntimeError(''' RuntimeError: An attempt has been made to start a new process before the current process has finished its bootstrapping phase. This probably means that you are not using fork to start your child processes and you have forgotten to use the proper idiom in the main module: if __name__ == '__main__': freeze_support() ... The "freeze_support()" line can be omitted if the program is not going to be frozen to produce an executable. D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py:658: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with torch.cuda.amp.autocast(True): AMP: checks passed D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py:218: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead. self.scaler = amp.GradScaler(enabled=self.amp) optimizer: SGD(lr=0.01) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0005), 63 bias train: Scanning D:\yolov8.98\ultralytics-v8.0.98\weilong\labels\train.cache... 5 images, 0 backgrounds, 0 corrupt: 100%|██████████| 5/5 [00:00<?, ?it/s] Traceback (most recent call last): File "<string>", line 1, in <module> File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 116, in spawn_main exitcode = _main(fd, parent_sentinel) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 125, in _main prepare(preparation_data) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 236, in prepare _fixup_main_from_path(data['init_main_from_path']) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path main_content = runpy.run_path(main_path, File "D:\ai\anaconda\envs\py391\lib\runpy.py", line 288, in run_path return _run_module_code(code, init_globals, run_name, File "D:\ai\anaconda\envs\py391\lib\runpy.py", line 97, in _run_module_code _run_code(code, mod_globals, init_globals, File "D:\ai\anaconda\envs\py391\lib\runpy.py", line 87, in _run_code exec(code, run_globals) File "D:\yolov8.98\ultralytics-v8.0.98\train.py", line 3, in <module> a1.train( File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\model.py", line 370, in train self.trainer.train() File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 191, in train self._do_train(world_size) File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 268, in _do_train self._setup_train(world_size) File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 250, in _setup_train self.train_loader = self.get_dataloader(self.trainset, batch_size=batch_size, rank=RANK, mode='train') File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\v8\detect\train.py", line 65, in get_dataloader return build_dataloader(dataset, batch_size, workers, shuffle, rank) # return dataloader File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\data\build.py", line 100, in build_dataloader return InfiniteDataLoader(dataset=dataset, File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\data\build.py", line 29, in __init__ self.iterator = super().__iter__() File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 493, in __iter__ return self._get_iterator() File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 424, in _get_iterator return _MultiProcessingDataLoaderIter(self) File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 1171, in __init__ w.start() File "D:\ai\anaconda\envs\py391\lib\multiprocessing\process.py", line 121, in start self._popen = self._Popen(self) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\context.py", line 224, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\context.py", line 327, in _Popen return Popen(process_obj) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\popen_spawn_win32.py", line 45, in __init__ prep_data = spawn.get_preparation_data(process_obj._name) File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 154, in get_preparation_data _check_not_importing_main() File "D:\ai\anaconda\envs\py391\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main raise RuntimeError(''' RuntimeError: An attempt has been made to start a new process before the current process has finished its bootstrapping phase. This probably means that you are not using fork to start your child processes and you have forgotten to use the proper idiom in the main module: if __name__ == '__main__': freeze_support() ... The "freeze_support()" line can be omitted if the program is not going to be frozen to produce an executable. 0%| | 0/1 [00:15<?, ?it/s] Traceback (most recent call last): File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 1284, in _try_get_data data = self._data_queue.get(timeout=timeout) File "D:\ai\anaconda\envs\py391\lib\queue.py", line 179, in get raise Empty _queue.Empty The above exception was the direct cause of the following exception: Traceback (most recent call last): File "D:\yolov8.98\ultralytics-v8.0.98\train.py", line 3, in <module> a1.train( File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\model.py", line 370, in train self.trainer.train() File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 191, in train self._do_train(world_size) File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\engine\trainer.py", line 306, in _do_train for i, batch in pbar: File "D:\ai\anaconda\envs\py391\lib\site-packages\tqdm\std.py", line 1181, in __iter__ for obj in iterable: File "D:\yolov8.98\ultralytics-v8.0.98\ultralytics\yolo\data\build.py", line 38, in __iter__ yield next(self.iterator) File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 733, in __next__ data = self._next_data() File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 1491, in _next_data idx, data = self._get_data() File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 1443, in _get_data success, data = self._try_get_data() File "D:\ai\anaconda\envs\py391\lib\site-packages\torch\utils\data\dataloader.py", line 1297, in _try_get_data raise RuntimeError( RuntimeError: DataLoader worker (pid(s) 3912, 22312, 32356, 6452) exited unexpectedly
08-16
在使用 YOLOv8 进行训练时，出现 `RuntimeError: DataLoader worker (pid(s) ...) exited unexpectedly` 错误，通常与多进程数据加载机制有关。以下是具体的解决方案： ### 调整 `num_workers` 参数 YOLOv8 的 `...
运行train文件后报错：按照方案一修改后报错：(yolov5_new) PS E:\YOLO\ultralytics-yolo11-main> python train.py New https://pypi.org/project/ultralytics/8.3.225 available 😃 Update with 'pip install -U ultralytics' Ultralytics 8.3.9 🚀 Python-3.8.18 torch-2.0.1+cu117 CUDA:0 (NVIDIA GeForce RTX 4060 Laptop GPU, 8188MiB) engine\trainer: task=detect, mode=train, model=ultralytics/cfg/models/11/yolo11-HGNetV2_1.yaml, data=dataset/data.yaml, epochs=2, time=None, patien ce=100, batch=8, imgsz=416, save=True, save_period=-1, cache=False, device=None, workers=0, project=runs/train, name=exp14, exist_ok=False, pretrai ned=True, optimizer=SGD, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=0, resume=False, amp=Fa lse, fraction=1.0, profile=False, freeze=None, multi_scale=False, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=Fals e, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, vid_stride=1, stream_buffer=False, visualize =False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, embed=None, show=False, save_frames=False, save_txt=False, save_conf=F alse, save_crop=False, show_labels=True, show_conf=True, show_boxes=True, line_width=None, format=torchscript, keras=False, optimize=False, int8=Fa lse, dynamic=False, simplify=True, 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, bgr=0.0, mosaic=1.0, mixup=0.0, copy_paste=0.0, copy_paste_mode=flip, auto_augment=randaugment, erasing=0.4, crop_fraction=1.0, cfg=None, tracker=botsort.yaml, save_dir=runs\train\exp14 from n params module arguments 0 -1 1 6752 ultralytics.nn.modules.block.HGStem [3, 16, 32] 1 -1 2 15456 ultralytics.nn.modules.Light_HGNet.Light_HGBlock[32, 32, 64, 3, 2] 2 -1 1 704 ultralytics.nn.modules.conv.DWConv [64, 64, 3, 2, 1, False] 3 -1 2 44400 ultralytics.nn.modules.Light_HGNet.Light_HGBlock[64, 48, 128, 3, 2] 4 -1 1 1408 ultralytics.nn.modules.conv.DWConv [128, 128, 3, 2, 1, False] 5 -1 2 346080 ultralytics.nn.modules.Light_HGNet.Light_HGBlock[128, 96, 256, 5, 2] 6 -1 1 2816 ultralytics.nn.modules.conv.DWConv [256, 256, 3, 2, 1, False] 7 -1 2 1377216 ultralytics.nn.modules.Light_HGNet.Light_HGBlock[256, 192, 512, 5, 2] 8 -1 1 656896 ultralytics.nn.modules.block.SPPF [512, 512, 5] 9 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 10 [-1, 5] 1 0 ultralytics.nn.modules.conv.Concat [1] 11 -1 1 849984 ultralytics.nn.modules.block.C3k2 [768, 384, 1] 12 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 13 [-1, 3] 1 0 ultralytics.nn.modules.conv.Concat [1] 14 -1 1 237600 ultralytics.nn.modules.block.C3k2 [512, 192, 1] 15 -1 1 332160 ultralytics.nn.modules.conv.Conv [192, 192, 3, 2] 16 [-1, 11] 1 0 ultralytics.nn.modules.conv.Concat [1] 17 -1 1 776256 ultralytics.nn.modules.block.C3k2 [576, 384, 1] 18 -1 1 1327872 ultralytics.nn.modules.conv.Conv [384, 384, 3, 2] 19 [-1, 8] 1 0 ultralytics.nn.modules.conv.Concat [1] 20 -1 1 2904192 ultralytics.nn.modules.block.C3k2 [896, 768, 1] 21 [14, 17, 20] 1 1291801 ultralytics.nn.modules.head.Detect [3, [192, 384, 768]] YOLO11-HGNetV2_1 summary: 282 layers, 10,171,593 parameters, 10,171,577 gradients, 22.2 GFLOPs TensorBoard: Start with 'tensorboard --logdir runs\train\exp14', view at http://localhost:6006/ Freezing layer 'model.21.dfl.conv.weight' train: Scanning E:\YOLO\ultralytics-yolo11-main\dataset\labels\train.cache... 1720 images, 0 backgrounds, 0 corrupt: 100%|██████████| 1720/1720 [0 train: WARNING ⚠️ E:\YOLO\ultralytics-yolo11-main\dataset\images\train\cc_304.jpg: 2 duplicate labels removed train: WARNING ⚠️ E:\YOLO\ultralytics-yolo11-main\dataset\images\train\cc_325.jpg: 2 duplicate labels removed train: WARNING ⚠️ E:\YOLO\ultralytics-yolo11-main\dataset\images\train\cc_362.jpg: 1 duplicate labels removed val: Scanning E:\YOLO\ultralytics-yolo11-main\dataset\labels\text.cache... 176 images, 0 backgrounds, 0 corrupt: 100%|██████████| 176/176 [00:00<? Plotting labels to runs\train\exp14\labels.jpg... optimizer: SGD(lr=0.01, momentum=0.937) with parameter groups 70 weight(decay=0.0), 77 weight(decay=0.0005), 76 bias(decay=0.0) TensorBoard: model graph visualization added ✅ Image sizes 416 train, 416 val Using 0 dataloader workers Logging results to runs\train\exp14 Starting training for 2 epochs... Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 0%| | 0/215 [00:00<?, ?it/s] Traceback (most recent call last): File "train.py", line 32, in <module> model.train(data='dataset/data.yaml', File "E:\YOLO\ultralytics-yolo11-main\ultralytics\engine\model.py", line 802, in train self.trainer.train() File "E:\YOLO\ultralytics-yolo11-main\ultralytics\engine\trainer.py", line 208, in train self._do_train(world_size) File "E:\YOLO\ultralytics-yolo11-main\ultralytics\engine\trainer.py", line 390, in _do_train self.loss, self.loss_items = self.model(batch) File "C:\Users\JJCHAN\.conda\envs\yolov5_new\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "E:\YOLO\ultralytics-yolo11-main\ultralytics\nn\tasks.py", line 167, in forward return self.loss(x, *args, **kwargs) File "E:\YOLO\ultralytics-yolo11-main\ultralytics\nn\tasks.py", line 387, in loss return self.criterion(preds, batch) File "E:\YOLO\ultralytics-yolo11-main\ultralytics\utils\loss.py", line 375, in __call__ loss, batch_size = self.compute_loss(preds, batch) File "E:\YOLO\ultralytics-yolo11-main\ultralytics\utils\loss.py", line 383, in compute_loss pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split( File "E:\YOLO\ultralytics-yolo11-main\ultralytics\utils\loss.py", line 383, in <listcomp> pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split( RuntimeError: shape '[8, 67, -1]' is invalid for input of size 1384448
最新发布
11-07
我们正在处理一个在运行YOLOv5的train.py时出现的RuntimeError。错误信息是：shape '[8, 67, -1]' is invalid for input of size 1384448。 这个错误通常表示在重塑张量（tensor）时，给定的形状与元素总数不匹配。...
Could not run ‘torchvision::nms‘ .. from the ‘CUDA‘ backend 原因分析和解决
m0_54041074的博客
07-23 1981
报错的直接原因是torchvision库中的文件： ... python311\Lib\site-packages\torchvision\ops\boxes.py 第41行，然后pip install torchvision-0.17.1+cu121-cp311-cp311-win_amd64.whl 即可。因此我下载的whl文件是 torchvision-0.17.1+cu121-cp311-cp311-win_amd64.whl。其中cuda版本可以比官方的版本高，可以不用强制要求一样。
解决：Could not run ‘torchvision::nms‘ with arguments from the ‘CUDA‘ backend
小老板_BK
04-07 531
发现torchvision使用的是0.21.0+cpu版本的，使用CPU导致无法运行nms函数。重新按照CUDA版本的torchvision即可解决。在使用CUDA运行YOLOE模型时报错。
NotImplementedError: Could not run ‘torchvision::nms‘ with arguments from the ‘CUDA‘ backend.
wyw0000的博客
01-17 1628
NotImplementedError: Could not run ‘torchvision::nms‘ with arguments from the ‘CUDA‘ backend.
【问题解决】NotImplementedError: Could not run ‘torchvision::nms‘ with arguments from the ‘CUDA‘ backend.
m0_55213577的博客
10-20 3011
本文描述了关于Pytorch的报错“NotImplementedError: Could not run 'torchvision::nms' with arguments from the 'CUDA' backend.”并提供了解决方案。
Could not run ‘torchvision::nms‘ with arguments from the ‘CUDA‘ backend的解决；用GPU跑Detectron2的demo
weixin_41793473的博客
07-08 1万+
Could not run ‘torchvision::nms’ with arguments from the ‘CUDA’ backend的解决；用GPU跑Detectron2的demo 在上一篇文章中，有一个问题没有解决。 Detectron2-入门1-极链AI云平台部署-多图好玩测试 Traceback (most recent call last): File "demo.py", line 112, in <module> predictions, visualized_
成功解决：NotImplementedError: Could not run ‘torchvision::nms‘ with arguments from the ‘CUDA‘ backend.
m0_74890428的博客
05-31 1万+
成功解决：NotImplementedError: Could not run 'torchvision::nms' with arguments from the 'CUDA' backend.
NotImplementedError: Could not run ‘torchvision::nms‘ with arguments from the ‘CUDA‘ backend解决办法
编程研究坊的博客
03-13 6019
NotImplementedError: Could not run 'torchvision::nms' with arguments from the 'CUDA' backend解决办法
“NotImplementedError: Could not run ‘torchvision::nms‘ with arguments from the ‘CUDA‘ backend.”
qq_42548064的博客
05-30 4227
当前环境： CUDA-11.3 torch-1.11.0 torchvision-0.10.0+cpu 报错原因： 在官网下的torchvision是cpu版本：torchvision-0.10.0+cpu，不能调用CUDA 尝试解决： 在官网用conda重新安装 但是安装torchvision仍然是cpu版本。折腾几番，发现是因为torch-1.11.0还没有对应torchvision的gpu版本。 解决方案： 换成CUDA 11.3 对应的更低版本的torch与torchvision pip3 ins
评论
成就一亿技术人!
拼手气红包6.0元
还能输入1000个字符
 
红包 添加红包
表情包 插入表情
表情包 代码片
 条评论被折叠 查看
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

小小的学徒

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付：¥1
获取中
扫码支付

您的余额不足，请更换扫码支付或充值

打赏作者

实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值