kevin

Results 6 comments of kevin

in my opinion, cause there not exist groundtruth for actual kiiti test datasets. So when evaluating the model when training, the author use the validation dataset. But when submitting detection...

question 2: can you provide a detailed procedure about how can i train the network with my own custom dataset, what kind of modification should i make in the config...

i am trying to train M3D-RPN with my own dataset (similar to kitti dataset), and i encounter a problem shown in the picture below: ![image](https://user-images.githubusercontent.com/26395975/68308060-2e276300-00e7-11ea-8783-5380d441c48c.png) i read the code and...

[problem solved!] Dame, it seems that if i ignore specific anchor, error will show up when i want to restore checkpoint or test the model ![image](https://user-images.githubusercontent.com/26395975/68353316-234eeb80-0144-11ea-829f-b6ee5b0abe91.png) i use 18 anchors...

same issue, i want to create a container with "--net=host", but when connecting using a browser, "http://127.0.0.1" or "http://127.0.0.1:80", it shows noVNC

问题是这样的,我利用自制数据集进行训练得到最终权重,那么如何利用这个权重进行inference呢