tags:
- pytorch_model_hub_mixin
- model_hub_mixin
Messisis a crop classification model for Switzerland, trained on the ZueriCrop 2.0 dataset. It is fine-tuned from the Prithvi geospatial foundation model, optimized for high-resolution Sentinel-2 imagery specific to Swiss agricultural landscapes. Messis leverages a hierarchical label structure and pretrained weights.
Key Features
- Adapted for High-Resolution Crop Classification: Messis is fine-tuned from the Prithvi geospatial foundation model, originally trained on U.S. data, and optimized for high-resolution Sentinel-2 imagery specific to Swiss agricultural landscapes.
- Leveraged Hierarchical Label Structure: Utilizes a remote-sensing-focused hierarchical label structure, enabling more accurate classification across multiple levels of crop granularity.
- Pretrained Weight Utilization: Demonstrated significant performance improvement by leveraging Prithvi's pretrained weights, achieving a doubled F1 score compared to training from scratch.
- Dataset: Trained on the ZueriCrop 2.0 dataset, which features higher image dimension (224x224 pixels) compared to the original ZueriCrop dataset.
Usage
Experience the Messis model firsthand by trying it out in our interactive Hugging Face Spaces Demo. This demo allows you to test the model's capabilities directly on your own data or sample images.
For comprehensive details on how Messis was developed, including full access to the DVC pipeline producing the dataset, model code, preprocessing steps, and training scripts, visit our GitHub Repository. Here, you’ll find everything you need to understand, reproduce, or further fine-tune the model.