KeyError: 'van_tiny is not in the models registry' about enjoy-hamburger HOT 4 CLOSED

Thank you!

from enjoy-hamburger.

Hi! Thank you for being so interested in the Hamburger! I guess that you need to import van in your train/test.py file to register the VAN backbone. For example, you may use the /seg_light_ham/dist_test.sh instead of the script under the /tools/ directory because this command applies to the correct train/test.py portal.

BTW, you can deploy the Light-Ham (VAN-Base) model. This one balances efficiency and performance very well.

Please feel free to ping me if you have additional questions!

from enjoy-hamburger.

Thank you!
One more question: The batch size I inputed should be one, but when I was checking the data, there is actually 12 images batched together. Do you know where is the setting for that?
By the way, do you have model pretrained on cityscapes?

from enjoy-hamburger.

Hi! I am not sure about the test batch size. The test batch size may be related to the number of GPUs you use because it is actually DistributedDataParallel (bs 1 per GPU to enable multi-GPU MSFlip test). Perhaps you can try to use one GPU only.

Good question. I only have pretrained checkpoints on ADE20K because some computing got expired. The good news here is that one of my collaborators will release a new paper regarding the power of VAN+Ham on segmentation. You may expect this paper.

Thanks!

from enjoy-hamburger.