hellochick
indoor model
I want to test indoor scenes semantic segmentation,and do some research about merging.I tried to train on sun rgb-d but can't converge,would you be willing to provide your own data model?I would be very thankful.
Hey @limitime , Since my indoor model is used to robot navigation, it can only recognize the walls, floors, and ceilings. If you need, I can provide you.
@hellochick That is completely enough,and I just want to get a baseline right now.Thank you very much!
@limitime, okay, I'll upload the checkpoint and weight soon. Could you tell me what you are working with XD? I'm curious about where you can use indoor segmentation.
@hellochick 3d scene reconstruction and understanding with a camera and lidar.Now we are exploring the probable use of our system.
@limitime Here is the model weight: https://drive.google.com/drive/folders/1zHFCXRyaW7OFn9zA41_c7Hfnl1HMhgK_?usp=sharing Remember to change the class number from 19 to 27.
@hellochick Do I need to change the IMG_MEAN?And when you train,did you change it?
@limitime, sorry for late reply. You don't need change the IMG_MEAN, and I don't change it when training, either.
hi,your project listed the original text's effect based on ade20k,but your model folder don't contain the model of ade20k,just have the model of cityscapes,can you tell where have the ade20k model
