hlwang1124

icon indicating a website link https://hlwang1124.github.io/ icon indicating an email [email protected]

icon location Ph.D. in Robotics from HKUST

Results 8 comments of hlwang1124

ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 256, 1, 1])

@lyd953621450 @HuangLian126 I think the reason is that the BatchNorm in the global_avg_pool requires the batch size to be larger than 1. If you have already set a batch size...

About palette.txt

Hi, @heguohao0728 . Sorry for the late response. This file stores the RGB values of semantic labels and predictions for visualization.

epochs

Hi, @jiyeooong . Sorry that I do not remember the specific epoch value. One sure thing is that the network can converge within 200 epochs.

epochs

Sorry for the late response. Did you adopt the same data split as mentioned in #2 ?

Testing without depth image input

Hi, @cteckwee . Sorry for the late response. I suggest you adopt existing single-modal networks. For example, [mmsegmentation](https://github.com/open-mmlab/mmsegmentation) has provided many existing networks with their pre-trained weights on the Cityscapes...

论文阅读 comments

Awesome!

diffKernelArray

Yes.

Question about data-refinement in V2

@EasternJournalist Thanks for your great work! I would like to ask when will the refinement scripts be open sourced. Looking forward to your reply!