search

isl-org / lang-seg

Language-Driven Semantic Segmentation
MIT License
706 stars 87 forks source link

Replace DPT backbone with ResNet101 #18

Closed devinluo27 closed 2 years ago

devinluo27 commented 2 years ago

I want to use a ResNet-based LSeg and I did the following:

Generally, I added a elif branch in _make_encoder(), which returns a resnet101, and modified the dimension in _make_scratch as [256,512,1024,2048]. I also replaced the forward_vit in lseg_net.py with a vanilla ResNet forward (return 4-stage output). To this end, I could start training, but could not get expected performance .

I might plug in ResNet wrongly or miss some points. Is there any demos of ResNet-based LSeg and if there is any ResNet pre-trained weights of LSeg? Thanks!

devinluo27 commented 2 years ago

Found new files pushed to repo, will check them first.