happynear / happynear/caffe-windows

Windows下编译fast rcnn的错误!!希望能够解答一下

Open
#90 7 comments 0 reactions 0 assignees View on GitHub
Dominant language
C++
Stars
1.3k
Forks
637
PR merge metrics
No merged PRs in 30d

Description

博主你好,感谢你分享这么宝贵的经验。我按照你第一篇博文编译了caffe的GPU版本,也可以跑MNIST历程。在编译pycaffe的时候也没有报错,就是时间很久,这个都不是什么问题。但是按照您第二篇编译fast rcnn的博文做的时候:将caffe_root/python 文件夹复制到caffe-fast-rcnn下以后,执行build/setup.py。这也可以执行。但是运行 #>Python tools/demo.py的时候 网络初始化完成,加载完模型和图片以后Python会崩。

> [net.cpp:270] This network produces output bbox_pred
> [net.cpp:270] This network produces output cls_pred
> [net.cpp:283] Network initialization done
> [net.cpp:816] Ignoring sourcr layer data
> [net.cpp:816] Ignoring sourcr layer loss_cls
> [net.cpp:816] Ignoring sourcr layer loss_bbox
>
> Loaded network %fast_rcnn_root% \ data\fast_rcnn_models\vgg16_fast_rcnn_iter_40000,caffemodel
>
> ```
> Demo for data/demo/00004.jpg
> ```

执行到这以后Python就崩溃了。 希望能得到解答,谢谢!!

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.