Welcome to MMRotate’s documentation!¶ Learn the Basics Learn the Basics Get Started Prerequisites Installation Best Practices Verify the installation Customize Installation Trouble shooting Dataset Preparation Test a model Train a model Train with a single GPU Train with multiple GPUs Train with multiple machines Manage jobs with Slurm Launch multiple jobs on a single machine Benchmark and Model Zoo Results on DOTA v1.0 Tutorials Tutorial 1: Learn about Configs Modify a config through script arguments Config file naming convention An example of RotatedRetinaNet FAQ Tutorial 2: Customize Datasets Support new data format Customize datasets by dataset wrappers Tutorial 3: Customize Models Develop new components Tutorial 4: Customize Runtime Settings Customize optimization settings Customize training schedules Customize workflow Customize hooks Useful Tools and Scripts Log Analysis Visualization Visualize Datasets Model Serving 1. Convert model from MMRotate to TorchServe 2. Build mmrotate-serve docker image 3. Run mmrotate-serve 4. Test deployment Model Complexity Prepare a model for publishing Benchmark FPS Benchmark Miscellaneous Print the entire config Confusion Matrix Notes Changelog v0.3.4 (01/02/2023) v0.3.3 (27/10/2022) v0.3.2 (6/7/2022) v0.3.1 (6/6/2022) v0.3.0 (29/4/2022) v0.2.0 (30/3/2022) v0.1.1 (14/3/2022) Frequently Asked Questions MMCV Installation PyTorch/CUDA Environment E2CNN Training Evaluation Switch Language English 简体中文 API Reference mmrotate.apis mmrotate.core anchor bbox patch evaluation post_processing visualization mmrotate.datasets datasets pipelines mmrotate.models detectors backbones necks dense_heads roi_heads losses utils mmrotate.utils Indices and tables¶ Index Search Page