Install & Compatibility
Where this runs
tested against v? · pip install
Install × environment matrix
Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux
muslpy 3.10–3.95 runs
build_error
Code
Verified usage
Verified import paths — ran on the pinned version, not inferred.
TerraTorchTrainer
✓ from terratorch import TerraTorchTrainer
✗ from terratorch.trainer import TerraTorchTrainer
TerraTorchTrainer is now exposed at the top level.
PrithviModel
✓ from terratorch.models import PrithviModel
✗ from terratorch.backbones import PrithviModel
Models are in the `models` module.
Minimal example fine-tuning a Prithvi model.
from terratorch import TerraTorchTrainer
from terratorch.datamodules import GeoSpatialDataModule
import os
trainer = TerraTorchTrainer(
model_name='prithvi_eo_v2_300',
backbone='prithvi_eo_v2_300',
num_classes=10,
learning_rate=1e-4,
)
datamodule = GeoSpatialDataModule(
data_root=os.environ.get('DATA_ROOT', './data'),
batch_size=4,
)
trainer.fit(datamodule=datamodule)
terratorch --version
Upgrade
Version history
1.2.8latest on PyPI · released May 29, 2026
Audit
Dependencies
torchrequiredCore deep learning framework
lightningrequiredPyTorch Lightning for training loops
torchgeorequiredGeospatial datasets and transforms
peftrequiredParameter-Efficient Fine-Tuning (LoRA, etc.)