DOFA
DOFA copied to clipboard
zhu-xlab
Code for Neural Plasticity-Inspired Foundation Model for Observing the Earth Crossing Modalities
encoder_layer = nn.TransformerEncoderLayer( TypeError: __init__() got an unexpected keyword argument 'norm_first' This will show an error after I delete it： transformer_output = self.transformer_encoder(x) tgt_len, bsz, embed_dim = query.size() ValueError: not...
I see the code for fine tuning, but cannot see it for pretraining..?
Add fine-tuning examples on the Sentinel-1, Sentinel-2, and hyperspectral datasets; Add the usages for online demo based on the Gradio.
Hi DOFA team, Great work! I was wondering how to reproduce your result on the BigEarthNet dataset? Do you by any chance have code for it or for the dataloader?...
Hi - Thank you for this work - it is very useful. I am trying to run DOFA on downstream tasks from scratch, to try and recreate some value in...
Hello, I'm try running the SegMunich example. I downloaded the `TUM_128.zip` and unzipped it to the `dofa/downstream_tasks/segmentation/datasets`. I changed the top lines of the file `dofa/segmentation/configs/dofa_vit_segmunich.py` to : ```` dataset_type...
Hi, I'm very interested in this project. Can you add a more profound example using Torchgeo to load the pre-trained weights and use it for segmentation? I've tried to do...