Closed dlazares closed 6 months ago
in zoedepth\models\base_models\midas.py i changed the line 341: midas = torch.hub.load("intel-isl/MiDaS", midas_model_type, pretrained=use_pretrained_midas, force_reload=force_reload)
to : midas = torch.hub.load("AyaanShah2204/MiDaS", midas_model_type, pretrained=use_pretrained_midas, force_reload=force_reload)
We're currently doing something about this. Thanks for your interest!
Torch2.0 has been supported. Thanks
I was able to hack it to work by changing midas.py and using timm==0.6.12
and also changed the cached model code at
~/.cache/torch/hub/intel-isl_MiDaS_master/midas/backbones/beit.py
tonew_sub_table = F.interpolate(old_sub_table, size=(new_height.item(), new_width.item()), mode="bilinear")
is there a better way to do this?