meteorshowers / RCF-pytorch

Richer Convolutional Features for Edge Detection model in pytorch CVPR2017
515 stars 145 forks source link

请问,需要用matlab工具箱进行最极大抑制吗? #17

Open bigyi2013 opened 5 years ago

bigyi2013 commented 5 years ago

Note: Before evaluating the predicted edges, you should do the standard non-maximum suppression (NMS) and edge thinning. We used Piotr's Structured Forest matlab toolbox available here. 这个是https://github.com/yun-liu/rcf 中的note。

meteorshowers commented 5 years ago

是的,需要使用

fangxu622 commented 5 years ago

是之在进行预测之前需要 使用 matlab 工具向作 极大值抑制处理吗

mingweiY commented 4 years ago

请问怎么样进行NMS,测评工具自动进行还是自己做完nms再去用工具测试

clelouch commented 4 years ago

请问怎么样进行NMS,测评工具自动进行还是自己做完nms再去用工具测试

@mingweiY [这里有进行评估的pipeline] (https://github.com/s9xie/hed_release-deprecated/blob/master/examples/eval/EVAL_README.txt)

mingweiY commented 4 years ago

自动进行了,好像有一个快速版本

---原始邮件--- 发件人: "clelouch"<notifications@github.com> 发送时间: 2020年4月7日(周二) 晚上11:01 收件人: "meteorshowers/RCF-pytorch"<RCF-pytorch@noreply.github.com>; 抄送: "Comment"<comment@noreply.github.com>;"mingweiY"<1337442535@qq.com>; 主题: Re: [meteorshowers/RCF-pytorch] 请问,需要用matlab工具箱进行最极大抑制吗? (#17)

请问怎么样进行NMS,测评工具自动进行还是自己做完nms再去用工具测试 这里有进行评估的pipeline https://github.com/s9xie/hed_release-deprecated/blob/master/examples/eval/EVAL_README.txt

— You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.