Jian Cheng comments

Results 13 comments of


                                            Jian Cheng

when i train a batch(batchsize 100) of flickr8k, it takes around 0.8 seconds,

I didn't do anything else... The only difference is probably my Ubuntu14.04 system... --- 发件人: Animesh Pandey [email protected] 发送时间: 2016年3月7日 3:52 收件人: karpathy/neuraltalk 抄送: evercherish 主题: Re: [neuraltalk] when i...

convert caffemodel ,the inference results was wrong

Hi, have you solved this problem? Could you please share your solution? Thanks!

关于稀疏化训练的问题

您好，我也遇到了这个问题。请问您是如何解决的啊，谢谢！

cmake successful but make failure

Hi, I've got the same problem, have you solved it? Could you please tell me how to modify the cmakelists.txt? Thanks

Has anyone tested the time-consuming of the code?

Hello. My inference time is (110+150)ms on GTX1080Ti while detecting a 608x608 image. Is there anything wrong when I build the projetc? Thanks!

how to detect airplane, ship and vehicle all together as a multiclass problem

Hi, have you solved this problem? Could you please tell me how to train a multi-classes model? Thanks!

how to detect airplane, ship and vehicle all together as a multiclass problem

> No I spent time on creating another algorithm for multi-class detection. I had to train on a custom dataset which we got from https://ternowai.eu/ so I did not focus...

[Feat] add monodet task

@ycdhqzhiai 你好我也遇到了一模一样的问题，请问你最后解决了吗？

failed after loading images and superpixel segmentation

@chituma110 I tried to create the directory by myself, and commented the relative codes in the .py file. And I also reduce the number of input images. Then it worked.

训练过程中会出现错误

请问有人解决这个问题了嘛