Downloads · 30 days
87
6% of all-time downloads
resnet50_fmow_rgb_gassl
torchgeo/resnet50_fmow_rgb_gassl
resnet50_fmow_rgb_gassl is a image classification model from torchgeo. Use it when you need a label for an image. It is set up for torchgeo. The card lists the license as cc-by-4.0.
Weights for the MoCo-v2+Geo+TP model from https://github.com/sustainlab-group/geography-aware-ssl, adapted to only extract the encoder using the following code:
All-time downloads
1.5K
Public
Repo size
94.3 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth94.3 MB · 100%
At a glance
- Task
- Image Classification
- Library
- torchgeo
- License
- cc-by-4.0
- Access
- Public
- Created
- May 11, 2023
- Updated
- Sep 29, 2026
- SHA
- 865e4a90
Model card
From the Hugging Face model README
Weights for the MoCo-v2+Geo+TP model from https://github.com/sustainlab-group/geography-aware-ssl, adapted to only extract the encoder using the following code:
import torch
x = torch.load("moco_geo+tp.pth", map_location="cpu")
x = x["state_dict"]
x = {k.replace("module.encoder_q.", ""): v for k, v in x.items() if "encoder_q" in k and "fc" not in k}
torch.save(x, "resnet50_fmow_rgb_gassl-44b4461b.pth")
- Task
- Image Classification
- Library
- torchgeo
- License
- cc-by-4.0
- Languages
- en
- Created
- May 11, 2023
- Updated
- Sep 29, 2026