leonnnop / GMMSeg

[NeurIPS 2022 Spotlight] GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models
Apache License 2.0
162 stars 14 forks source link

No such file or directory: 'mmseg/utils/sampler/city_lbl2idx.pth' #5

Open fangli333 opened 1 year ago

fangli333 commented 1 year ago

hi, when i try to reproduce your work for retraining on cityscapes dataset. It seems like I still miss one checkpoint. Can you help me to tackle this problem? thank you!

whiteinblue commented 1 year ago

the same question ? how to generate file of xx_lbl2idx.pth ?

leonnnop commented 10 months ago

Sorry for the confusion and inconvenience caused. In this work, we assume a uniform prior for class probabilities, but in practice, segmentation datasets like ADE20K, Cityscapes, and COCO-Stuff have long-tailed pixel distributions.

To address this issue, we propose a pixel balanced sampler to rebalance the pixel distribution as a uniform distribution. You can find the relevant code for the sampler in the following link: https://github.com/leonnnop/GMMSeg/blob/da1a5187a1eaa889bb101a5ab8974f9d1c7f1349/mmseg/utils/sampler.py#L42-L95

Regarding the xx_lbl2idx.pth files, they contain the mapping of each label to pixel indexes within the corresponding label class.

We are currently working on releasing both the code for generating these files and the files themselves. Please stay tuned for updates.