GluonCV is a deep learning computer vision toolkit originally built on Apache MXNet, now also supporting PyTorch. Version 0.10.5.post0 is the latest release. The project is in maintenance mode with infrequent releases.
pip install gluoncvNo compatibility data collected yet for this library.
Verified import paths — ran on the pinned version, not inferred.
Load a pre-trained YOLOv3 model and run inference on a random image (MXNet backend).
Upgrade MXNet to 1.8+ and use Python 3.6+.
Migrate to PyTorch backend using gluoncv.torch module.
Use gluoncv.model_zoo.get_model('...', pretrained=False) to skip download.