chongkuiqi / s2anet Goto Github PK
View Code? Open in Web Editor NEWA reimplementation of the S2ANet algorithm for Oriented Object Detection
A reimplementation of the S2ANet algorithm for Oriented Object Detection
models/orn/src/cuda/ActiveRotatingFilter_cuda.cu:5:10: fatal error: THC/THC.h: 没有那个文件或目录
#include <THC/THC.h>
^~~~~~~~~~~
compilation terminated.
error: command '/usr/local/cuda-10.2/bin/nvcc' failed with exit code 1
models/orn/src/cuda/ActiveRotatingFilter_cuda.cu:5:10: fatal error: THC/THC.h: 没有那个文件或目录
5 | #include <THC/THC.h>
| ^~~~~~~~~~~
compilation terminated.
error: command '/usr/local/cuda/bin/nvcc' failed with exit code 1
我的配置是RTX3060,torch1.12.1+cu116
前面所有过程运行都没有问题了,运行train.py时出现这个错误
No labels in {cache_path}. Can not train without labels. See {HELP_URL}'
AssertionError: train: No labels in /home/mjh/图片/S2ANet/data/DOTA/train/labels.cache. Can not train without labels. See https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data
把labels.cache文件删除再来也还是不行,请问有什么办法吗
模型训练完成,但是没有找到可以输入空图片输出目标检测结果的.py文件,请问应该运行哪个文件
您好,我想请教一个问题,我已经将骨干网络替换成CSPDarket-53,但是不想下载初始权重文件,希望网络从0开始训练(对比试验的特殊需求),我应该修改backbone.py和train.py中的哪一部分呢,删除哪些类呢?望您在百忙之中给予指点,谢谢!
AssertionError: train: No labels in /media/mjh/F674A9D874A99BBD/DOTA/train/labels.cache. Can not train without labels. See https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data
正式训练时候报出上面这个错误,文件路径并没有错,查到一种解决方法是改变文件目录层级
#└─ mydata
但是这个文件目录层级与README中不同,我试了一下报出了这个错误
Exception: train: Error loading data from /home/mjh/文档/DOTA/images/train : train: /home/mjh/文档/DOTA/images/train does not exist
See https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data
我参考这篇博客,修改了一下https://blog.csdn.net/weixin_46085845/article/details/127903878
运行过后报错为
File "/home/mjh/文档/S2ANet-main/utils/general.py", line 415, in check_dataset
raise Exception('Dataset not found.')
Exception: Dataset not found.
找不到数据集位置了,请问有什么解决方法吗
更改主动旋转滤波器的cuda源码,将#include <THC/THC.h>注释掉,把THCudaCheck替换为AT_CUDA_CHECK,并替换THCCeilDiv(x,y)为(x+y-1)/y,完成以上操作之前我试了一下再次运行python setup.py build_ext --inplace观察是否为原本的THC问题,但是报出错误变成了IndexError: list index out of range,完成THC更改的操作后,运行同样出现了这个错误,使用了python setup.py clean命令再运行仍然报错,部分报错代码如下File "/home/mjh/anaconda3/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 1694, in _get_cuda_arch_flags
arch_list[-1] += '+PTX'
IndexError: list index out of range
麻烦作者大大了,感谢感谢
AssertionError: train: No labels in /media/mjh/F674A9D874A99BBD/DOTA/train/labels.cache. Can not train without labels. See https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data
正式训练时候报出上面这个错误,文件路径并没有错,查到一种解决方法是改变文件目录层级
#└─ mydata
├─ images
│ ├─ test # 下面放测试集图片
│ ├─ train # 下面放训练集图片
│ └─ val # 下面放验证集图片
└─ labels
├─ test # 下面放测试集标签
├─ train # 下面放训练集标签
├─ val # 下面放验证集标签
但是这个文件目录层级与README中不同,我试了一下报出了这个错误
Exception: train: Error loading data from /home/mjh/文档/DOTA/images/train : train: /home/mjh/文档/DOTA/images/train does not exist
See https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data
我参考这篇博客,修改了一下https://blog.csdn.net/weixin_46085845/article/details/127903878
运行过后报错为
File "/home/mjh/文档/S2ANet-main/utils/general.py", line 415, in check_dataset
raise Exception('Dataset not found.')
Exception: Dataset not found.
找不到数据集位置了,请问有什么解决方法吗
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.