train SSD on my own data,but the rusult of detector is so bad

[moonyoung430]

I trained SSD-tensorflow on my own data, just to detect one thing,the lounge bridge.Test result like this: trained on the GPU two days, I want to know what caused this result.

[Fan9]

i have the same problem, i train and test on kitti datasets,but the result is no good.

[HiKapok]

Maybe you can try this, it's easier to train.

[LJXLJXLJX]

@HiKapok Thanks ! Your version seems easier to understand

[HiKapok]

@LJXLJXLJX thank you

[yangdi92]

I have the same problem, so, have you solved it ?

[zyz111]

@moonyoung430 Hello, has your problem been solved？ I meet the same problem, but I don't know how to solve it. can you tell me your method to solve the problem? Thank you!

[yangdi92]

no, i suggest you use other respo

zyz111 [email protected] 于2019年12月5日周四 下午4:15写道：

@moonyoung430 https://github.com/moonyoung430 Hello, has your problem been solved？ I meet the same problem, but I don't know how to solve it. can you tell me your method to solve the problem? Thank you!

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/balancap/SSD-Tensorflow/issues/250?email_source=notifications&email_token=AF5ZUEQKXR6WE3HY77DNIWLQXC2ANA5CNFSM4FDBOVG2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEF74AYQ#issuecomment-562020450, or unsubscribe https://github.com/notifications/unsubscribe-auth/AF5ZUEVP4JME6HQHPGYXTPTQXC2ANANCNFSM4FDBOVGQ .

[zyz111]

@moonyoung430 thank you for your reply