why does the model have to pre-trained on ImageNet-1k datasets? Did you test results directly on ADE20K without using pre-training?

NVlabs / SegFormer

Official PyTorch implementation of SegFormer

https://arxiv.org/abs/2105.15203

Other

2.36k stars 332 forks source link

why does the model have to pre-trained on ImageNet-1k datasets? Did you test results directly on ADE20K without using pre-training? #119

Open 754467737 opened 1 year ago

marcelampc commented 1 year ago

I am not sure about your question, but I'll try to help =) The pre-trained model on ImageNet-1k was used as starting point to train on ADE20k or another dataset. The final trained models should be found in the following links:

google drive | onedrive