Train & Test¶
MMDetection provides hundreds of pretrained detection models in Model Zoo, and supports multiple standard datasets, including Pascal VOC, COCO, CityScapes, LVIS, etc. This note will show how to perform common tasks on these existing models and standard datasets:
- Learn about Configs
- Inference with existing models
- Dataset Prepare
- Test existing models on standard datasets
- Train predefined models on standard datasets
- Train with customized datasets
- Train with customized models and standard datasets
- Finetuning Models
- Test Results Submission
- Weight initialization
- Use a single stage detector as RPN
- Semi-supervised Object Detection
Useful Tools¶
- Log Analysis
- Result Analysis
- Fusing results from multiple models
- Visualization
- Error Analysis
- Model Serving
- Model Complexity
- Model conversion
- Dataset Conversion
- Dataset Download
- Benchmark
- Miscellaneous
- Hyper-parameter Optimization
- Confusion Matrix
- COCO Separated & Occluded Mask Metric
- Useful Hooks
- Visualization
- Corruption Benchmarking
- Model Deployment
- Semi-automatic Object Detection Annotation with MMDetection and Label-Studio
- MOT Test-time Parameter Search
- MOT Error Visualize
- Browse dataset
- Learn about Configs
- Dataset Preparation
- Inference
- Learn to train and test
- Learn about Visualization