zou jinyi

Results 9 comments of zou jinyi

@anqingjianke when I use MomentumOptimizer I also meet the loss can only reduce to 1.6 for long long time and the test accuracy is low. when I use AdamOptimizer I...

@hellochick Hi I follow your advice to python train.py --update-mean-var --train-beta-gamma and python train.py --train-beta-gamma. Finally the model failed. I am confused in tensorflow when train the BN layer it...

@hellochick Can you use the saved checkpoint model without --update-mean-var to evaluate the data. Is the result still right? This is my result with update mean and var train beat...

我没有具体提交过我将训练集按3,7分开,用70%训练30%验证,结果car的AP在76%左右

mAP 七十多 要是基础网络好就能更高 | | 邹进屹 邮箱:[email protected] | 签名由 网易邮箱大师 定制 在2018年08月21日 15:46,Zdafeng 写道: 您好,您有没有对数据集进行其他处理呢? — You are receiving this because you commented. Reply to this email directly, view it...

Well done 发自网易邮箱大师 On 07/09/2017 21:47, handong1587 wrote: Actually I have already done some translatings based on @manutdzou 's Chinese version README. Perhaps I can submit a PR on this?...

where? | | 邹进屹 邮箱:[email protected] | 签名由 网易邮箱大师 定制 On 03/23/2018 18:24, sgxu wrote: I did a test, your implementation of proposal layer is wrong. — You are receiving this...

我没用过那个工具箱我用的voc的评价标准 | | 邹进屹 邮箱:[email protected] | 签名由 网易邮箱大师 定制 在2018年06月02日 21:39,TFDeepbluesky 写道: @manutdzou 你好,感谢你的代码,我很想知道如何使用kitti开发工具箱对我的检测结果进行评估,因为我一直没有弄明白它是怎么使用的。 我的结果保存在data/result中,和你的格式是一样的,如果我想评估的话,我应该从哪里入手呢,你能帮帮我吗?真的非常感谢你。祝你生活愉快,谢谢啦。 — You are receiving this because you were mentioned. Reply to this email directly, view...

You can check the box gt if there is 0 or negative in some case | | 邹进屹 邮箱:[email protected] | 签名由 网易邮箱大师 定制 On 01/15/2018 08:44, blueardour wrote: @pobizheV Have...