mqchen1993

Results 9 comments of mqchen1993

How to guarantee that refined depths have the exact same value at those valid pixels in sparse depth map?

@XinJCheng

why is this sorted according to cv_kpts.size?

Hi, Thank you very much for your answer. Because I try not to add this sort, the result will be very poor. Is it generally octave is relatively large, then...

where is the Non-Maximum Suppression

@zhreshold

KeyError: "Unable to open object (object 'conv1s.0.0.bn.num_batches_tracked' doesn't exist)"

I also encountered the same problem. Have you solved it? @kevinpzy

code and model

I also encountered the same problem. @Jianlong-Fu Thanks！

error/ loss aways equal 87.3362. I change the lr but not work.

I trained on the cifar10. Attached is my prototxt file. Thanks! 2017-11-28 17:33 GMT+08:00 Sven Koitka : > Without further information about your training setup, I am unable to help...

error/ loss aways equal 87.3362. I change the lr but not work.

Hello, why not this, this can not be used in cifar10. I downloaded from your homepage. Thanks! ​ 2017-11-28 17:55 GMT+08:00 Sven Koitka : > No, it is not. >...

error/ loss aways equal 87.3362. I change the lr but not work.

I am sorry, it may be my side of the transmission error. I'll pass it again. Thanks！ net: "examples/cifar10/wrn/cifar100_WRN-16-4_dropout_train_val.prototxt" test_iter: 100 test_interval: 1000 base_lr: 0.0001 #clip_gradients:30 display: 100 max_iter: 64000...

error/ loss aways equal 87.3362. I change the lr but not work.

I modified the solver file as you gave it. But still failed. Dataset is no problem, because I use other network training is possible. Thanks！ 2017-11-28 19:08 GMT+08:00 Sven Koitka...